Breast: What's New
Body Monday, 17 May 2021
Oral
Digital Poster

Oral Session - Breast: What's New
Body
Monday, 17 May 2021 12:00 - 14:00
  • Diffusion weighted and kurtosis breast cancer imaging for b=0-1800 s/mm2: Comparisons to dynamic contrast enhanced MRI
    Martins Otikovs1, Noam Nissan2, Edna Furman-Haran1, Debbie Anaby2, Tanir M. Allweis3, Ravit Agassi4, Miri Sklair-Levy2,5, and Lucio Frydman1
    1Weizmann Institute of Science, Rehovot, Israel, 2Sheba Medical Center, Ramat Gan, Israel, 3Kaplan Medical Center, Rehovot, Israel, 4Ben Gurion University Hospital, Beer Sheba, Israel, 5Tel Aviv University, Tel Aviv, Israel
    Spatiotemporal encoding (SPEN) is an alternative ultrafast imaging technique. Its performance for breast cancer characterization using DW and diffusion kurtosis imaging and the potential of using SPEN DW images acquired with high b-values as an alternative to DCE subtractions are assessed.
    Figure 4. Comparison between DW images acquired using a series of b-encoding gradients (right-hand panels), and DCE subtraction images on the same patient. Diffusion encoding b-values are indicated on top of each column for SPEN DW images. In the two left columns T2w TSE and T1w DCE subtraction images are also presented. Shown are exams for four IDC (rows 1, 4, 5 and 6) and two ILC (rows 2 and 3) patients. These images suggests the possibility to identify and delineate lesions solely on the basis of strongly b-weighted images –without a need for contrast and for DCE subtractions.
    Figure 2. Representative ADC and kurtosis maps obtained from SPEN and RESOLVE data for four patients, displaying three IDC breast lesions and one ILC lesion (bottom left panel). Shown for each patient are single-breast anatomical T2w TSE and T1w DCE subtraction images, with the latter highlighting as bright regions the cancerous masses. Shown as well are the kurtosis and the ADC maps derived by the SPEN and RESOLVE exams (ADC maps were calculated solely on the basis of images acquired with 0 and 850 s/mm2 nominal b-values).
  • Impact of retrospective gradient nonlinearity correction on lesion ADCs and performance in the ECOG-ACRIN A6702 multicenter breast DWI trial
    Debosmita Biswas1, Justin Romanoff2, Dariya Malyarenko3, Wesley Surrento4, Habib Rahbar1, Nola Hylton5, David C Newitt5, Thomas L Chenevert3, and Savannah C Partridge1
    1Radiology, University of Washington, Seattle, WA, United States, 2Center for Statistical Sciences, Brown University, Providence, RI, United States, 3Radiology, University of Michigan, Ann Arbor, MI, United States, 4Biomedical and Health Informatics, University of Washington, Seattle, WA, United States, 5Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, United States
    Gradient nonlinearity (GNL) correction for ADCs of 81 breast lesions in the A6702 multicenter breast DWI trial showed ADC error varied across vendors and gradient systems. Results suggest GNL correction may improve generalizability of diagnostic ADC thresholds.
    Figure 1. Example of the direction averaged correction map Cave and impact on tumor ADC values. A 50 year old woman with a 7 mm suspicious BIRADS 4 lesion, which was found to be malignant on biopsy. (a,b,c) show the uncorrected ADC map, GNL correction map and the resulting ADC map after applying GNL correction. Insets on images (a) and (c) show lesion area. The lesion ADC values were lower after GNL correction. (Hotspot ADCs Uncorrected = 1.19 x10-3 mm2/s Corrected = 0.99 x10-3 mm2/s)
    Figure 2. Bland-Altman plot for uncorrected and corrected hotspot ADCs by MRI gradient system
  • Breast MRI functional tumor volume segmentation quality may impact the prediction of pathological complete response
    Natsuko Onishi1, Jessica Gibbs1, Teffany Joy Bareng1, Wen Li1, Elissa R. Price1, Bonnie N. Joe1, Laura J. Esserman2, The I-SPY 2 Consortium3, David C. Newitt1, and Nola M. Hylton1
    1Department of Radiology & Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 2Department of Surgery, University of California, San Francisco, San Francisco, CA, United States, 3Quantum Leap Healthcare Collaborative, San Francisco, CA, United States
    Segmentation quality of functional tumor volume (FTV), measured prospectively from breast DCE-MRI performed sequentially during neoadjuvant chemotherapy, may impact the predictive performance of FTV for pathological complete response.

    Figure 1: I-SPY 2 treatment de-escalation strategy

    The treatment de-escalation decision will be made at T2 based on combined MRI and biopsy results. Qualified subjects will be given the option to skip anthracycline-cyclophosphamide (AC) treatment and proceed directly to surgery.

    Figure 3: Predictive performance of pCR in the optimal and non-optimal segmentation groups (Main analysis: Reader 1)

    AUC values for the prediction of pCR were higher for the optimal segmentation group versus non-optimal group for ∆FTV1, ∆FTV2 and the multivariable model (0.68 vs. 0.66, 0.70 vs. 0.62, and 0.84 vs. 0.64, respectively), with the difference reaching statistical significance for the multivariable model.

  • Evaluating pCR after neoadjuvant systemic treatment of invasive breast cancer using DWI in comparison to DCE-based kinetic analysis
    Rie Ota1, Masako Kataoka1, Maya Honda1, Mami Iima1, Kanae Kwai Miyake1, Akane Ohashi2, Yosuke Yamada3, Masakazu Toi4, and Yuji Nakamoto1
    1Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University graduate school of medicine, Kyoto, Japan, 2Kyoto Medical Center, Kyoto, Japan, 3Department of Pathology, Kyoto University Hospital, Kyoto, Japan, 4Department of Breast Surgery, Kyoto University Hospital, Kyoto, Japan
    DWI-based scoring system can be used to evaluate pCR with diagnostic performance similar to that in kinetic analysis, particularly in triple negative subtypes.

    -ROC analysis for diagnosing pCR based on DWI score/Kinetic score-

    Kinetic score showed slightly higher AUC while 95% confidence interval overlapped with that of DWI score. Both kinetic score and DWI score demonstrated excellent diagnostic performance among triple negative subtype compared to other subtype with AUC of 0.88-0.95. For luminal subtype, DWI score tended to perform better than kinetic score.

    -Image evaluation-

    • DWI score

    DWI of the target lesion was evaluated and categorized as 3-point scale.

    0: no abnormal signal, 1: small focus of high - intermediate signal intensity, 2: obvious high signal intensity.

    • Kinetic score

    Kinetic patterns of the lesions on DCE-MRI was scored as

    0 : no enhancement, 1 : persistent, 2 : plateau and 3 : washout.

    For both scores Low score indicates pCR.

  • Multiparametric MRI signatures of immune response in patients with HER2+ breast cancer treated with trastuzumab
    Bonny Chau1, Debosmita Biswas1, Anum S. Kazerouni1, Daniel S. Hippe1, Rebeca Alvarez1, Suzanne Dintzis1, Laura C. Kennedy2, Vijayakrishna Gadi3, and Savannah C. Partridge 1
    1University of Washington, Seattle, WA, United States, 2Vanderbilt University, Nashville, TN, United States, 3University of Illinois, Chicago, IL, United States
    In patients with HER2+ breast cancer treated with trastuzumab, pre-treatment ADC on DW-MRI and change in peak percent enhancement on DCE-MRI were significantly associated with immune response.
    Figure 3. Example cases
  • BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning
    Jiejie Zhou1, Yan-Lin Liu2, Yang Zhang2, Jeon-Hor Chen2,3, Freddie J. Combs2, Ritesh Parajuli4, Rita S. Mehta4, Huiru Liu1, Zhongwei Chen1, Youfan Zhao1, Meihao Wang1, and Min-Ying Su2
    1Department of Radiology, First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China, 2Department of Radiological Sciences, University of California, Irvine, CA, United States, 3Department of Radiology, E-Da Hospital and I-Shou University, Kaohsiung, Taiwan, 4Department of Medicine, University of California, Irvine, CA, United States
    150 non-mass-like enhancements were analyzed by radiologists performing BI-RADS reading. Radiomics and deep learning were used to build diagnostic models. SVM yielded the highest accuracy. ResNet50 had better diagnostic performance, 91.5% in training, and 83.3% in testing datasets.
    Figure 1: A 41-year-old patient with a DCIS. (a) F1 Pre-contrast image. (b) F2 post-contrast image. (c-i): The zoom-in smallest bounding box containing the tumor. (c) F1 pre-contrast, (d) F2 post-contrast, (e) F3 post-contrast, (f) The last F6 post-contrast image, showing a comparable enhancement as in F3. (g) The wash-in signal enhancement map F2-F1, (h) The maximum F3-F1 signal enhancement map, (i) The wash-out F6-F3 map. A small portion of the tumor shows the wash-out pattern. (J) The DCE time course shows a plateau pattern, after reaching the maximum in F3.
    Figure 2: A 63-year-old patient with an invasive ductal cancer (IDC). (a) F1 Pre-contrast image. (b) F2 post-contrast image. (c) F1 pre-contrast, (d) F2 post-contrast, (e) F3 post-contrast, (f) The last F6 post-contrast image, showing wash-out DCE pattern with decreased intensity after reaching maximum in F3. (g) The wash-in signal enhancement map F2-F1, (h) The maximum F3-F1 signal enhancement map, (i) The wash-out F6-F3 map. (j) The DCE time course shows a typical wash-out pattern, reaching maximum in F3, followed by decreased intensity from F4 to F6.
  • Radiomics based classification of breast mass with a multiparametric MRI protocol with DCE-MRI, T2, and DWI
    Jing Zhang1, Chenao Zhan2, Tao Ai2, Xu Yan3, and Guang Yang1
    1Shanghai key lab of magnetic resonance, shanghai, China, 2Tongji Medical College, Huazhong University of Science and Technology, Department of Radiology,Tongji Hospital, Wuhan, Hubei Province, China, 3Siemens Healthcare, MR Scientific Marketing, shanghai, China
        A combined radiomics model using features from multi-parametric MRI achieved an AUC of 0.948 to differentiate maglinant and benign breast cancers in the test cohort, with an increased accuracy and a decreased false positive rate.
    Figure 1 Flow chart. A tumor region was contoured manually on T1Wpost 90s­, to which other images were aligned. First order and texture features were extracted from T1W, DCE kinetic maps, T2W, and ADC maps, and used to build radiomics models, together with shape features. The dataset was split into training and test cohort by scanning date. After feature selection, radiomics models were constructed using SVM or LR, before evaluated with ROC analysis, DCA
    Figure 2 Model evaluation. (a) ROC in internel test cohort. (b) Decision curve analysis for each model in the testing dataset. The decision curve showed that when the threshold probability is in the range 0.85-0.95, the application of the final model adds more benefit than treating all or none of the patients and other models. (c) Calibration curve of the union model prediction in the internal and external test cohort. (d) Weights of selected features in the final model
  • Predicting Gadolinium Contrast Enhancement for Structural Lesion Analysis using DeepContrast
    Dipika Sikka1,2, Nanyan Zhu3, Chen Liu4, Scott Small5, and Jia Guo6
    1Department of Biomedical Engineering, Columbia University, New York, NY, United States, 2VantAI, New York, NY, United States, 3Department of Biological Sciences and the Taub Institute, Columbia University, New York, NY, United States, 4Department of Electrical Engineering and the Taub Institute, Columbia University, New York, NY, United States, 5Department of Neurology, the Taub Institute, the Sergievsky Center, Radiology and Psychiatry, Columbia University, New York, NY, United States, 6Department of Psychiatry, Mortimer B. Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, United States
    Contrast produced by a deep learning algorithm shows comparable predictions of gadolinium uptake for brain and breast lesion enhancement, using a single T1-weighted pre-contrast scan.
    Figure 1. 3D Residual Attention U-Net architecture for brain lesion data. The network consists of 6 encoding layers (purple) and 6 decoding layers (orange). Spatial dimension decreases by 2 and channel dimension increases by 2 as the data propagates through the encoding layers while the reverse happens along the decoding layers. A full scan is then returned as the model output, as the prediction of the entire scan.
    Figure 2. 2D Residual Attention U-Net architecture for breast lesion data. The network consists of 5 encoding layers (purple) and 5 decoding layers (orange). Spatial dimension decreases by 2 and channel dimension increases by 2 as the data propagates through the encoding layers while the reverse happens along the decoding layers. A single slice of the predicted scan is then returned as the model output.
  • Multimodal magnetic resonance elastography and optical imaging of breast cancer
    Bin Deng1,2,3, Mansi Saksena2,3, Steven Jay Isakoff3,4, Ralph Sinkus5, Samuel Patz3,6, and Stefan Alexandru Carp1,2,3
    1Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, United States, 2Department of Radiology, Massachusetts General Hospital, Boston, MA, United States, 3Harvard Medical School, Boston, MA, United States, 4Cancer Center, Massachusetts General Hospital, Boston, MA, United States, 5Laboratory for Vascular Translational Science (LVTS), Institut National de la Santé et de la Recherche Médicale (INSERM), Paris, France, 6Department of Radiology, Brigham and Women’s Hospital, Boston, MA, United States
    A multimodal MRE and optical imaging method, validated in a dual-contrast tissue mimicking phantom, offers complementary contrasts that highlight the heterogeneity of tumor biomechanical and vascular environment in a breast cancer patient.
    Fig. 3: Multimodal images of a 33-y.o. breast cancer patient diagnosed of high-grade HER2+ invasive ductal carcinoma measured 4.5×2.6×2.6 cm. (a) T1-weighted fat saturated (FS) post-contrast MRI. (b) DOT image of total hemoglobin concentration (HbT) overlaid with simultaneously acquired T1 non-FS MRI. (c) Image of shear modulus measured by MRE. Red line – tumor marking. White dotted line – MRE actuator contact.
    Fig. 2: Multimodal MRE/DOT imaging results of a dual-contrast tissue phantom. (a) T1 image showing three 20-mm diameter inclusions marked in circles. (b) MRE phase image obtained using 100Hz vibration showing wave propagation within the entire 12-cm diameter phantom with longer wavelengths inside inclusions. (c) Reconstructed shear modulus map and (d) absorption coefficient map shows clear contrasts in expected inclusion locations. Inclusion 3 was out of the optical coverage marked by the vertical dotted line in subplot (d), resulting in failure to recover its optical contrast.
  • Radiomics model based on MAGIC acquisition for predicting neoadjuvant systemic treatment response in triple-negative breast cancer.
    Nabil Elshafeey1, Gaiane M. Rauch2, Aikaterini Kotrotsou3, Beatriz E. Adrada1, Rosalind P. Candelaria1, Abeer H. Abdelhafez1, Huiqin Chen4, Jia Sun4, Medine Boge1, Rania M. M Mohamed1, Benjamin C. Musall5, Jong Bum Son5, Shu Zhang6, Jason B. White7, Brandy Willis5, Elizabeth Ravenberg7, Wei Peng4, Stacy L. Moulder7, Wei Yang1, Mark D. Pagel6, Jingfei Ma5, and Ken-Pin Hwang5
    1Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 2Breast and Abdominal imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 3The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 4Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 5Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 6Cancer Systems Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 7Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
    Our results showed that the radiomic signature derived from MAGIC maps (T1, PD and T2) can help differentiate responders from non-responders at baseline evaluation.
    Figure 1: Example T1, T2, and PD maps processed from the MAGIC sequence using SyMRI
    Figure 2: The variable importance features within the T2 radiomic model
Back to Top
Digital Poster Session - Breast: DWI, AI & Emerging Techniques
Body
Monday, 17 May 2021 13:00 - 14:00
  • Diagnosis of Breast Cancer Using Radiomics Models Built Based on DCE-MRI and Mammography Compared to BI-RADS Reading
    Zhongwei Chen1, Yang Zhang2, Jiejie Zhou1, Youfan Zhao1, Haiwei Miao1, Huiru Liu1, Shuxin Ye1, Nina Xu1, Meihao Wang1, and Min-Ying Su2
    1Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, wenzhou, China, 2Department of Radiological Sciences, University of California, Irvine, CA, United States
    The model built based on all MRI and mammography features yielded the highest accuracy and had significantly better diagnostic performance than BI-RADS using threshold of 4A or 4B.
    Figure 1: A 50-year-old patient with a malignant cancer showing smooth boundary. (a) F1 Precontrast image. (b) The F2 postcontrast image. (c) The F1 precontrast image. (d) The F2 postcontrast image. (e) The F3 postcontrast image. (f) The last F6 postcontrast image,showing persistent enhancement with increased intensity over time. (g) The washin signal enhancement map F2-F1. (h) The F3-F1 signal enhancement map. (i) The washout F6-F3 map. (j) The corresponding CC view mammography, the lesion mass was outlined by green line.
    Figure 2: A 58-year-old patient with a malignant cancer showing smooth boundary. (a) F1 Precontrast image. (b) The F2 postcontrast image. (c) The F1 precontrast image. (d) The F2 postcontrast image. (e) The F3 postcontrast image. (f) The last F6 postcontrast image, showing persistent enhancement with increased intensity over time. (g) The washin signal enhancement map F2-F1. (h) The F3-F1 signal enhancement map. (i) The washout F6-F3 map. (j) The corresponding CC view mammography, the lesion mass was outlined by green line.
  • Predicting Underestimation of Invasive Cancer in Patients with Core-needle Biopsy-diagnosed Ductal Carcinoma in Situ using Deep Learning
    Luu-Ngoc Do1, Chae Yeong Im2, Jae Hyuk Park2, So Yeon Ki3, Ilwoo Park2,4,5, and Hyo Soon Lim2,3
    1Department of Radiology, Chonnam National University, Gwangju, Korea, Republic of, 2College of Medicine, Chonnam National University, Gwangju, Korea, Republic of, 3Department of Radiology, Chonnam National University Hwasun Hospital, Hwasun, Korea, Republic of, 4Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, Korea, Republic of, 5Department of Radiology, Chonnam National University Hospital, Gwangju, Korea, Republic of
    In this paper, we developed a 2-step algorithm utilizing a recurrent CNN model and demonstrated that the proposed algorithm can provide a method to predict invasiveness in the core needle biopsy-proven DCIS with the results comparable to the previous reports.
    Figure 1. The diagram of the proposed two-step deep learning model.
    Figure 3. ROC curves of 3 models on testing data
  • Combination of pharmacokinetic parameters and texture features of DCE-MRI for predicting preoperative classification of breast cancer
    Xia Wu1,2,3, Zhou Liu4, Meng Wang4, Zhe Ren1,2,3, Ya Ren4, Jie Wen4, Qian Yang4, Xin Liu1,2,3, Hairong Zheng1,2,3, and Na Zhang1,2,3
    1Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Synopsis, ShenZhen, China, 2Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, ShenZhen, China, 3CAS key laboratory of health informatics, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, ShenZhen, China, 4Department of Radiology, National Cancer Center/Cancer Hospital and Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, ShenZhen, China
    Combination of texture features and pharmacokinetic parameters for a classifier can improve the accuracy of classification.
    Table 1: The accuracy of breast cancer grading using three classifiers according to different feature sets
    Figure 1: Representative images of Grade Ⅰ-Ⅲ breast cancer. The arrows point to the breast cancer lesions.
  • Classification of Breast Cancer Molecular Subtypes on DCE-MRI Using Radiomics Analysis with Various Machine Learning Algorithm
    Yan-Lin Liu1, Yang Zhang1,2, Jeon-Hor Chen1,3, Siwa Chan4, Jiejie Zhou5, Meihao Wang5, and Min-Ying Su1
    1Department of Radiological Sciences, University of California, Irvine, CA, United States, 2Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, NJ, United States, 3Department of Radiology, E-Da Hospital and I-Shou University, Kaohsiung, Taiwan, 4Department of Medical Imaging, Taichung Tzu-Chi Hospital, Taichung, Taiwan, 5Department of Radiology, The First Affiliate Hospital of Wenzhou Medical University, Wenzhou, China

    Patients were classified into three molecular Subtypes. Five machine learning algorithms were implemented to build models. For TN vs. Non-TN, accuracy was 91.0% in training and 88.2% in testing datasets. For HER2+ vs. HER2-, accuracy was 90.4% in training and 86.2% in testing datasets.

    Figure 1: The flowchart of the experimental design. The tumor is segmented by Fuzzy-C-means clustering algorithm on F2 post-contrast image, and then the tumor ROI is mapped to 3 generated DCE parametric maps. On each map, 32 first-order and 75 texture parameters are extracted using the PyRadiomics. For each case, a total of 268 radiomics features with ICC ³ 0.8 are used to build models using five machine learning algorithms to differentiate three different molecular subtypes.
    Figure 2: A 48-year-old patient with an invasive ductal cancer (TN). (a) F1 Pre-contrast image. (b) F2 post-contrast image. (c-i): The zoom-in smallest bounding box containing the tumor. (c) F1 pre-contrast, (d) F2 post-contrast, (e) F3 post-contrast, (f) The last F6 post-contrast image. (g) The wash-in signal enhancement map F2-F1, (h) The maximum F3-F1 signal enhancement map, (i) The wash-out F6-F3 map. (J) The DCE time course shows a typical wash-out pattern.
  • Characterization of Breast Tumor using Machine Learning based upon Multi-parametric MRI Features.
    Snekha Thakran1, Rakesh Kumar Gupta2, and Anup Singh1,3
    1Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India, Delhi, India, 2Department of Radiology, Fortis Memorial Research Institute, Haryana, Gurgaon, India, Delhi, India, 3Department of Biomedical Engineering, All India Institute of Medical Science, New Delhi, India, Delhi, India
    The combination of support-vector-machine(SVM) with Wrapper method using Adaptive-Boosting(AdaBoost) technique resulted in high sensitivity(0.94±0.07), specificity(0.80±0.05), and accuracy(0.90±5.48) in classification of low-grade vs. high-grade tumors. 
    Figure-1: The flow chart of the proposed framework.
    Table-1: List of different feature vectors and their description.
  • A meta-analysis of the diagnostic performance of machine learning–based MRI for axillary lymph node metastasis in breast cancer patients
    Chen Chen1, Fabao Gao1, and Xiaoyue Zhou2
    1Department of Radiology, West China Hospital, Chengdu, China, 2MR Collaboration, Siemens Healthineers Ltd., Shanghai, China
    Machine learning can be used to predict the presence of axillary lymph node metastasis in breast cancer patients.
    Fig. 3. Forest plot of single studies for the pooled diagnostic odds ratio and 95% CI
  • Early prediction of pathologic complete response to neoadjuvant systemic therapy for triple-negative breast cancer using deep learning
    Zijian Zhou1, David E. Rauch1, Jong Bum Son1, Benjamin C. Musall1, Nabil A. Elshafeey2, Jason B. White3, Mark D. Pagel4, Stacy Moulder3, and Jingfei Ma1
    1Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 2Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 3Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, 4Cancer Systems Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
    Using convolutional and recursive neural networks on pre-treatment DCE and DWI, the deep learning ensemble can predict pathologic complete response to neoadjuvant systemic therapy for triple-negative breast cancer patients.
    Figure 1. Illustration of the deep learning ensemble developed for pathologic complete response (pCR) prediction for the triple-negative breast cancer cohort. The ensemble took the pre-treatment DCE and DWI as input. Two convolutional neural networks extracted features from the DCE and DWI, respectively. The sequences of features were then input to the two recursive neural networks, respectively. Outputs of the recursive neural networks were concatenated and used for pCR or non-pCR prediction.
    Figure 3. Receiver operating characteristic curve (blue) of the prediction using the deep learning ensemble. Using the pre-treatment DCE and DWI, the ensemble achieved the best accuracy of 69%, with the sensitivity of 75% for pCR patients and specificity of 63% for non-pCR patients. The area under the curve (AUC) was 0.68.
  • Application of Two Deep Learning Networks for Diagnosis of Breast Cancer on MRI: Automatic Detection Using Mask R-CNN Followed by Classification Using ResNet50
    Yang Zhang1,2, Yan-Lin Liu2, Ke Nie1, Jiejie Zhou3, Siwa Chan4, Vivian Youngjean Park5, Min Jung Kim5, Zhongwei Chen3, Jeon-Hor Chen2,4, Meihao Wang3, and Min-Ying Su2
    1Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, NJ, United States, 2Department of Radiological Sciences, University of California, Irvine, CA, United States, 3Department of Radiology, The First Affiliate Hospital of Wenzhou Medical University, Wenzhou, China, 4Department of Medical Imaging, Taichung Tzu-Chi Hospital, Taichung, Taiwan, 5Department of Radiology and Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea, Republic of
    These research shows the potential of Mask R-CNN detection followed by ResNet50 classification for automatic detection and further characterization of identified lesions to develop a fully-automatic computer-aided diagnosis system for breast MRI.
    Figure 5: True negative (TN) case example from a 44-year-old patient with a confirmed benign adenosis in the left breast. Extensive parenchymal enhancements are seen in both breasts. (a) Pre-contrast image acquired using fat-sat sequence; (b) Post-contrast image; (c) Tumor detection results searched by the Mask R-CNN algorithm. Two boxes are generated to identify two suspicious lesions, one in each breast. After evaluation by ResNet50 network, the left lesion has a malignant probability of 0.44, thus correctly diagnosed as benign. The parenchymal enhancements from normal tissues in the right breast has a very low malignant probability of 0.12. These results illustrate the potential of Mask R-CNN detection followed by ResNet50 classification for automatic detection and further characterization of identified lesions to develop a fully-automatic computer-aided diagnosis system for breast MRI.
    Figure 1: Flow diagram of the training and testing courses using Mask R-CNN for detection (shown in purple) and ResNet50 for classification (shown in blue).
  • A Parsimonious Assessment of Breast Density Classes from Quantitative, AI-based FGT Volume Segmentations
    Pablo F. Damasceno1,2, Tatiana Kelil1,2, Rutwik Shah1,2, Bruno Astuto Arouche Nunes1,2, Jason Crane1,2, and Sharmila Majumdar1,2
    1Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, United States, 2Center for Intelligent Imaging, University of California San Francisco, San Francisco, CA, United States
    We use deep learning to compute FGT amounts in breast MRI and evaluate its relationship to qualitative FGT categories assigned by a radiologist at the time of examination, opening the door for a parsimonious relationship between qualitative classes and quantitative density values.
    Fig. 1 Methods of FGT ratio calculation. (a) Example slices of pre-contrast image (top), whole breast (middle) and FGT segmentations (bottom) for one typical exam labelled ‘extreme fibroglandular tissue’ according to the radiology report. (b) Ratio of FGT (orange) to whole breast (blue) segmentations is higher for center slices (ρ=49%, inset) compared to all slices (ρ=36%). (c) Resulting FGT segmentation following the Maximal Intensity Projection method skews densities even more toward higher values (ρ=70%).
    Fig. 2. Distribution of FGT amounts per radiology-defined class for different density calculation methods. (a) Simple density, where all slices were considered for the FGT amount calculation, (b) threshold-based density, where only slices with a significant amount of FGT are considered, and (c) maximal intensity projection, where segmentations across all slices were projected onto a 2-dimensional array prior to the density calculation.
  • Correction of Artifacts Induced by B0 Inhomogeneities with RPG on a Breast Diffusion Phantom
    Lauren K Fang1, Ana E Rodriguez-Soto1, Summer J Batasin2, Kathryn E Keenan3, and Rebecca A Rakow-Penner2
    1Radiology, University of California San Diego, La Jolla, CA, United States, 2University of California San Diego, La Jolla, CA, United States, 3National Institute of Standards and Technology, Boulder, CO, United States
    Reduced-FOV DWI without parallel imaging (PI) and full-FOV DWI with PI reduced initial distortions in the phase encoding (PE) direction. Reduced-FOV images had the largest initial distortion in the frequency encoding direction. RPG improved distortion artifacts in the PE direction.
    Figure 1. Representative images of breast distortion phantom polycarbonate grid collected with full-FOV EPI with (left) and without (middle) parallel imaging (PI) and reduced-FOV EPI without PI (right). Images of positive (A-C) and negative (D-F) PE direction before RPG distortion correction. (G-I) Positive PE direction images after RPG correction. (J-L) Overlay of each circle’s center location from DWI data before (magenta) and after (green) RPG on anatomical reference image.
    Figure 2. Magnitudes of distortion artifacts before and after RPG correction in (A,B) the phase-encoding, (C,D) frequency-encoding directions for full-FOV EPI with (red) and without (green) parallel imaging (PI) and reduced-FOV EPI without PI (blue). Horizontal black bars indicate p<0.05 significance.
  • Influence of gadolinium-based contrast agent on DWI and ADC values in breast lesions
    Kay van der Hoogt1, Robert-Jan Schipper1, Ronni Wessels1, Cees de Graaf1, Arjan te Boekhorst1, Leon ter Beek2, Regina Beets-Tan1, and Ritse Mann1
    1Radiology, the Netherlands Cancer Institute – Antoni van Leeuwenhoek, Amsterdam, Netherlands, 2Medical Physics, the Netherlands Cancer Institute – Antoni van Leeuwenhoek, Amsterdam, Netherlands

    Currently, preliminary data shows a decrease in ADC after contrast administration.

    Table 2: ADC measures for pre and post-contrast DWI
    Figure 1: Bland-altman plot for all lesions, comparing pre and post-contrast ADC
  • A Comparison of different models of diffusion-weighted MRI in distinguishing benign and malignant breast lesions
    Muzhen He1, Huiping Ruan1, Mingping Ma1, Zhongshuai Zhang2, and Robert Grimm2
    1Radiology, Provincial Clinical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou, China, 2Siemens Healthcare Ltd, Shanghai, China
    A Comparison of apparent diffusion coefficient (ADC), intravoxel incoherent motion (IVIM) and diffusional kurtosis imaging (DKI) in distinguishing benign and malignant breast lesions
    Figure 7. The area under the ROC curve of the mean ADC, IVIM-D, IVIM-DP, DKI-K and DKI-D values are 0.915, 0.909, 0.574, 0.768 and 0.895, which indicates that the ADC value is the best single quantitative parameters to distinguish benign and malignant breast lesions. The area under the ROC curve of combined ADC and DKI-K value is 0.923.
    Table2:Diagnostic Effectiveness for Benign and Malignant Lesions of Quantitative Parameters
  • A BI-RADS like lexicon for Breast DWI: Proposal and early evaluation
    Mami Iima1,2, Aika Okazawa3, Ryosuke Okumura3, Sachiko Takahara4, Tomotaka Noda3, Taro Nishi3, Yuji Nakamoto1, and Masako Kataoka1
    1Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan, 2Clinical Innovative Medicine, Institute for Advancement of Clinical and Translational Science, Kyoto University Hospital, Kyoto, Japan, 3Radiology, Kitano Hospital, The Tazuke Kofukai Medical Research Institute, Osaka, Japan, 4Breast Surgery, Kitano Hospital, The Tazuke Kofukai Medical Research Institute, Osaka, Japan
    Our proposed DWI reading method based on BI-RADS lexicons from multiple b-value images had comparable specificity and NPV to standard BI-RADS. DWI reading method might increase diagnostic confidence in differentiating malignancy from benignity.

    Figure 2:

    the representative case of the typical malignant tumor (left). The tumor shows moderate signal intensity at low b-value, an increased signal at high b-value, and decreased ADC, suggesting malignancy. Invasive ductal carcinoma.

    the representative case of the typical benign tumor (right). The tumor shows marked signal intensity at low b-value, decreased signal at high b-value, and slightly low ADC, suggesting a benign breast tumor. Fibroadenoma.

    Table 2: Diagnostic performance for DWI and DCE-MRI
  • Evaluation of the efficacy of therapy for breast cancer using DWI and DCE-MRI based on acquired radial golden-angle compressed sensing
    Haiyun Wang1, Qian Xu1, Gaofeng Shi1, Lijia Wang1, Qinglei Shi2, and Chen Zhang2
    1CTMRI, The Fourth Hospital of Hebei Medical University, Shijiazhuang,Hebei, China, 2MR Scientific Marketing,Siemens Healthcar, Beijing, China
    In this study, we studied the feasibility of GRASP based DCE technique and readout-segmented DWI technique in early evaluation of breast cancer response to neoadjuvant therapy. We found the combination of these demonstrated great potential in  breast cancer with neoadjuvant therapy.
    Table5 and Figure show ROC curve of the parameters in Table 5 and parameters in forecasting performance of model
    Table 4.Comparison of the change rate of parameters in histopathological response groups during and before NAT
  • Accuracy and Precision of a Breast Diffusion Phantom Across 3T Scanners
    Lauren K Fang1, Ana E Rodríguez-Soto1, Kathryn E Keenan2, and Rebecca A Rakow-Penner1
    1Radiology, University of California San Diego, La Jolla, CA, United States, 2National Institute of Standards and Technology, Boulder, CO, United States
    Overall accuracy and precision of DWI estimates was >88% and improved when normalized by an internal reference. High inter- and intra-scanner variability highlight the need for investigating spatial effects on breast tumor ADC heterogeneity.
    Figure 1. (A) Diffusion breast phantom schematic. Percentages indicate % w/w PVP in water. (B) Schematic with tubes and fibroglandular ROI locations. (C) Axial view of ADC map. Yellow line shows the slice at which ROIs of water (black) and fibroglandular tissue (pink) were drawn in the (D) coronal view. Green line shows the slice at which (C) was taken. (E) Median ADC, shown as dots for each tube. Red lines indicate expected values.6,8
    Figure 2. Coefficient of variation across scanners of (A) absolute ADC, and (B) ADC relative to water for each tube.
  • Evaluation of Lactating Breasts Using Diffusion Tensor Magnetic Resonance Imaging: A Feasibility Study.
    Anabel M Scaranelo1, Hadassa Degani2, Dov Grobgeld3, Vivianne Freitas1, Shelley Westergard4, Christine Elser5, and Edna Furman-Haran3
    1Medical Imaging, University of Toronto, Toronto, ON, Canada, 2DDE MRI Solutions Ltd., Tel Aviv, Israel, 3Weizmann Institute of Science, Rehovot, Israel, 4Princess Margaret Cancer Center, Toronto, ON, Canada, 5University of Toronto, Toronto, ON, Canada
    A prospective feasibility study of breast DTI in high-risk lactating patients indicated high diagnostic sensitivity and specificity and a more accurate cancer detection rate than breast DCE imaging.
    Figure 2: DTI λ1 parametric map (A) and maximum intensity projection (MIP) of the DCE images (B) in a lactating 33 years old BRCA-1 carrier woman. The λ1 parametric map depicted in the left breast a non-palpable invasive ductal carcinoma lesion (low λ1 values) that was detected by screening DTI but was not demonstrated by DCE because of the masking effect of marked background parenchymal enhancement (BIRADS 1 DCE and BIRADS 5 DTI).
    Figure 1: DTI λ1 parametric map (A) and maximum intensity projection (MIP) of the DCE images (B) in a lactating 33 years old breast cancer patient. The λ1 parametric map and the DCE images both show in the left breast a triple negative invasive ductal carcinoma mass lesion (low λ1 values ). The cancer lesion was diagnosed by both DCE (assigned BIRADS 4) and by DTI (assigned BIRADS 5).
  • Feasibility of Using a Deep Learning Reconstruction to Increase Protocol Flexibility for Breast MRI
    Timothy Allen1,2, Leah C Henze Bancroft2, Lloyd Estkowski3, Ty A Cashen3, Frederick Kelcz2, Frank R Korosec1,2, Roberta M Strigel1,2,4, Orhan Unal1,2, and James H Holmes2
    1Medical Physics, University of Wisconsin-Madison, Madison, WI, United States, 2Radiology, University of Wisconsin-Madison, Madison, WI, United States, 3Global MR Applications and Workflow, GE Healthcare, Madison, WI, United States, 4Carbone Cancer Center, University of Wisconsin-Madison, Madison, WI, United States
    A deep learning reconstruction was found to increase perceived signal-to-noise ratio, sharpness, and overall image quality in T2w breast MRI. Preliminary results show that deep learning can help reverse image degradation associated with rapid high-resolution imaging. 
    Figure 1: Axial T2w breast MR images reconstructed with deep learning scored significantly higher in SNR and image sharpness than those without deep learning. (a,d) A patient with substantial fibroglandular tissue; (b,e) a patient with multiple simple and complicate cysts; and (c,f) a lactating patient.
    Figure 3: T2w images acquired at 0.714 x 0.714 mm2 resolution (a) appear noisier than those acquired at the standard 1.1 x 1.1 mm2 resolution (c). However, application of DL (b) increases SNR to achieve SNR more similar to the lower spatial resolution protocol.
  • Quantitative evaluation of different models of diffusion-weighted MRI for the correlation with molecular subtype of breast cancer
    Muzhen He1, Huiping Ruan1, Mingping Ma2, Zhongshuai Zhang3, and Robert Grimm3
    1Radiology, Provincial Clinical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou, China, 2Provincial Clinical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou, China, 3Siemens Healthcare Ltd, Shanghai, China
    Quantitative evaluation of different models of diffusion-weighted magnetic resonance imaging for the correlation with molecular subtype of breast cancer
    Table1: Diffusion Parameters of molecular subtype
    Table2: Diffusion Parameters of molecular prognostic factors
  • Differentiating breast adenosis and breast cancer lesions: Value of Synthetic MRI
    Peiying Zhu1, Xiaoan Zhang1, Lin Lu1, Xin Zhao1, Qingna Xing1, Yafei Guo1, Kaiyu Wang2, Jinxia Guo2, Xueyuan Wang1, and Penghua Zhang1
    1Department of Radiology, The Third Affiliated Hospital of Zhengzhou University, Zhengzhou, China, zhengzhou, China, 2GE Healthcare, MR Research China, Beijing, China, zhengzhou, China
    Synthetic MRI is able to obtain various image comtrasts and quantitative parameters.These parameters( T1, T2, and PD values) directly reflect the composition of the tissue.The objective of this study was to assess Synthetic magnetic resonance imaging (MRI) ability for differentiation between breast adenosis and breast cancer.Our results show that show that Synthetic MRI is a useful tool that can be utilised to discriminate between breast adenosis and breast cancer.
    Figure. 1 Synthetic MR, DCE-MRI and DWI images of a 42-year-old woman with Invasive cancer in the left breast. the synthetic images obtained 11 minutes after contrast agent injection. A T2WI (Synthetic),the position of the ROI is outlined with a red circle; B T1 map (Synthetic); C T2 map (Synthetic); D proton density map (Synthetic); E DCE-MRI (2 min 31s after contrast injection); F ADC map (DWI).
    Figure. 2 Synthetic MR, DCE-MRI and DWI images of a 39-year-old woman with adenosis in the left breast. the synthetic images obtained 11 minutes after contrast agent injection. A T2WI (Synthetic), the position of the ROI is outlined with a red circle; B T1map (Synthetic); C T2map (Synthetic); D proton density map (Synthetic); E DCE-MRI (2 min 31s after contrast injection); F ADC map (DWI).
  • Clinical utility of breast DWI in the assessments of breast lesions using different b values
    Mami Iima1,2, Maya Honda1, Rie Ota1, Masako Kataoka1, Masakazu Toi3, and Yuji Nakamoto1
    1Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan, 2Clinical Innovative Medicine, Institute for Advancement of Clinical and Translational Science, Kyoto University Hospital, Kyoto, Japan, 3Breast Surgery, Kyoto University Graduate School of Medicine, Kyoto, Japan
    Diagnostic performance based on b800 and b1500 DW images was not uniform among 3 readers. Beside b values attention should be given to standardization on reading protocols and experience from DWI readers.
    Figure 3. The DW image findings are different among 3 readers. Fibroadenoma.
    Table 1. Agreement in DW-based BI-RADS categories. Agreement in DW-based BI-RADS categories tended to be higher in b1500 compared to b800 DW images. Mean and confidence intervals for kappa values are shown.
Back to Top
Digital Poster Session - Breast: All About Cancer
Body
Monday, 17 May 2021 13:00 - 14:00
  • Histogram analysis of synthetic MRI parameters  correlations with prognostic factors and molecular subtypes in invasive ductal breast cancer
    Qin Li1, Pu-Yeh Wu2, and Yajia Gu1
    1Fudan University Shanghai Cancer Center, Shanghai, China, 2GE Healthcare, Beijing, China
    IDC with high nuclear grade had higher PD10th, PDmean, PDmedian and PDmax. PDmedian was higher in IDC with HER2 positivity. T110th was higher in cancers with PR negativity. Cancers with hormone receptornegativity had higher T210th, T2mean and T2median than that with hormone receptor positivity.
    Fig 1. The ROC of T210th, T2mean, T2median and T290th values distinguishing TNBC from luminal A subtypes
    Fig 2. The ROC of T210th, T2mean, T2median and T290th values distinguishing TNBC from luminal B subtypes
  • Quantitative transport mapping for classifying malignant breast lesion: Comparison with kinetic modeling and enhancement characteristics
    Qihao Zhang1, Michele B Drotman1, Christine Chen1, Thanh Nguyen1, Pascal Spincemaille1, and Yi Wang2
    1Weill Cornell Medical College, New York, NY, United States, 2Cornell University, New York, NY, United States
    For postprocessing dynamic contrast enhanced MRI, automated quantitative transport mapping based on inverting the transport equation is more accurate than traditional Kety’s method and enhancement curve characteristics for differentiating benign from malignant tumors in the breast.
    Figure 2. Comparison of QTM method and Kety’s method on a malignant lesion. This is a 73 years old patient with biopsy proven malignant lesion. a) post-Gd T1 weighted image, b) QTM |u| map, c) Ktrans and d) Ve map using internal mammary (IM) AIF.
    Figure 3. Differentiating malignant breast lesions from benign breast lesions. a) QTM |u| (p<0.001), b) Ktrans (p=0.007), c) Ve (p=0.006) and d) A (p=0.001) demonstrating significance difference between malignant and benign lesions. There were no other parameters demonstrating significant difference between malignant and benign lesions.
  • Feasibility of respiratory self-gated free breathing supine breast DCE-MRI using data-driven model consistency condition reconstruction
    Ping N Wang1, Julia V Velikina2, Alexey A Samsonov2, Lloyd Estkowski3, Ty A Cashen3, Frederick Felcz2, Roberta M Strigel1,2,4, Frank R Korosec1,2, and James H Holmes2
    1Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States, 2Department of Radiology, University of Wisconsin-Madison, Madison, WI, United States, 3Global MR Applications & Workflow, GE Healthcare, Madison, WI, United States, 4Carbone Cancer Center, University of Wisconsin-Madison, Madison, WI, United States
    This work demonstrates the feasibility of providing motion-free high spatial-temporal resolution breast DCE-MRI using radial acquisition combined with self-gating and MOCCO reconstruction.
    Figure 4: Individual time frames at peak contrast enhancement (time = 240 s) reconstructed using SENSE (A), CS-TV (B), MOCCO with model order K=3 (C) with temporal resolution of 15 s. High image quality is observed for both regularized reconstructions (B, C). Note the late-phase image (D) was acquired with a navigator-gated Cartesian acquisition, which resulted in a longer acquisition time (8:43 min:s).
    Figure 5: Supine image (A) from a patient volunteer reconstructed using SENSE (green, X), CS-TV (blue, circles), and MOCCO with model order K=3 (red, stars) with 15 s temporal resolution. PSC (%) are plotted from ROIs placed in the lesion, fibroglandular tissue, and aorta (A, red outlines). Rapid wash-in and wash-out contrast kinetics are observed in the aorta D). The lesion B) showed relatively rapid contrast update, while the fibroglandular tissue C) showed slower contrast uptake.
  • Increased Saturated Fatty Acid Fraction in the Adipose Tissue Near Malignant Tumors in Breast Cancer Patients
    Mehran Baboli1, Pippa Storey2, Terlika Pandit Sood2, Justin Fogarty2, Melanie Moccaldi2, Alana Lewin2, Linda Moy2, and Sungheon Gene Kim1
    1Radiology, Weill Cornell Medicine, New York, NY, United States, 2Radiology, NYU Langone Health, New York, NY, United States
    The SFA was significantly higher around the malignant tumor than on the contralateral normal breast while no significant changes were observed in benign tumors. The results showed that the SFA could potentially be used to understand the role of adipose tissue and the development of breast cancer
    Figure 2: Examples of the SFA maps in contra- and ipsilateral breast and small ROI around the tumor. Only the voxels with >90% fat fraction were included in the maps.
    Figure 3: SFA comparison between contralateral, ipsilateral breast, and a small ROI around the lesions for patients with (a) benign and (b) malignant lesions. A significantly higher (p= 0.007) SFA was observed around the malignant lesions.
  • The value of IVIM-DWI in early prediction of efficacy of neoadjuvant chemotherapy for breast cancer
    Ting-ting Lin1 and Jiang-ning Dong2
    1Radiology Department, Anhui Provincial Cancer Hospital, Hefei, China, 2Radiology department, Anhui Provincial Cancer Hospital, Hefei, China
    IVIM-DWI can predict the early curative effect of neoadjuvant chemotherapy for breast cancer and evaluate its effectiveness. It can assist conventional MRI to evaluate the curative effect.
    Fig1 ROC curve of IVIM parameters D, D* and F for the diagnosis of neoadjuvant chemotherapy in breast cancer
    Fig2 A-H A 64-year-old woman has a large tumor on her right breast. The tumor is isointensity on T1WI, slight hyperintensity on T2WI, and heterogeneous enhancement. E, F, G, and H: The value of ADC, D, D*, and f is 1.04×10-3 mm2/s, 0.905×10-3 mm2/s, 23.1×10-3 mm2/s, 9.94%.
  • Peri-tumoural spatial distribution of lipid composition and tubule formation in breast cancer
    Kwok Shing Chan1,2, Sai Man Cheung1, Nicholas Senn1, Yazan Masannat3,4, Ehab Husain4,5, Steven D Heys3, and Jiabao He1
    1Institute of Medical Sciences, University of Aberdeen, Aberdeen, United Kingdom, 2Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands, 3Breast Unit, Aberdeen Royal Infirmary, Aberdeen, United Kingdom, 4School of Medicine, University of Aberdeen, Aberdeen, United Kingdom, 5Pathology Department, Aberdeen Royal Infirmary, Aberdeen, United Kingdom
    Peri-tumoural spatial distribution of lipid composition in the breast is an imaging biomarker sensitive to neoplastic tubule formation and is associated with tumour proliferative activity.

    Figure 1. Study design.

    A two-group cross-sectional study in a flow chart. Eight specimens were excluded due to small tumour size and mixed phenotype. Regions of interests (ROI) were drawn on chemical shift-encoded images (CSEI) to define the adipose tissue boundary. Fat, water and the number of double bonds in triglyceride molecules were estimated from the CSEI data, from which saturated, monounsaturated and polyunsaturated fatty acids (SFA, MUFA and PUFA) were derived. Statistical comparison was conducted on lipid components between Scores 2 and 3 tubule formation.

    Figure 2. Group differences in peri-tumoural monounsaturated fatty acids (MUFA) in breast adipose tissue.

    The difference in MUFA (a) mean, (b) skewness, (c) entropy and (d) kurtosis between breast cancer with Scores 2 and 3 tubule formation are shown in dot plots. Each dot represents the spatial distribution around the breast tumour, and the dots are organised in two columns corresponding to the two groups. The error bar indicates the mean and standard deviation. The t-tests were performed and p value is shown for each plot. Statistically significant p values (< 0.05) are marked by ‘*’.

  • Differential Subsampling with Cartesian Ordering in Differentiating Benign and Malignant Lesions of the Breast
    Yafei Guo1, Lin Lu1, Meiying Cheng1, Kaiyu Wang2, Jinxia Guo2, Xin Zhao1, and Xiaoan Zhang1
    1the Third Affiliated Hospital of Zhengzhou University, Zhengzhou, China, 2GE Healthcare, MR Research China, Beijing, China
    There were important differences of Ktrans, CER, IAUGC, Ve, MaxSlope(P<0.05). DISCO can provide important reference information for the selection of treatment plan and the formulation of surgical plan for breast lesions.
    Table 2 ROC curve analysis of quantitative and semi quantitative parameters of benign and malignant breast lesions groups
    Figure.2 the ROC curve of Ktrans, CER, IAUGC, Ve, MaxSlope distinguishing between benign and malignant breast lesions groups
  • Combination of IVIM with DCE-MRI in diagnosis and prognostic evaluation of breast cancer
    Yurong Zheng1, Rui Wang1, Li Li1, Haoyuan Li1, Pengfei Wang1, Tiejun Gan1, Jing Zhang1, and Kai Ai2
    1Department of Magnetic Resonance, LanZhou University Second Hospital, Lanzhou, China, 2Philips Healthcare, Xi’an, China
    This research showed that  DCE-derived Ktrans, Kep and IVIM-derived D and f are associated with prognostic factors of breast cancer.
    FIGURE 1. ROC curves of different methods (DCE-MRI, IVIM, and DCE-MRI + IVIM) for discriminating malignant and benign breast lesions.
    TABLE 1. The correction analysis of DCE-MRI, IVIM and the prognosis of breast cancer indexes.
  • The Performance of Breast Diffusion Tensor Imaging in the Evaluation of Pre-Surgical Treatment of Breast Cancer.
    Anabel M Scaranelo1, Edna Furman-Haran2, Abdullah Alabousi3, Dov Grobgeld2, Vivianne Freitas1, and Hadassa Degani4
    1Medical Imaging, University of Toronto, Toronto, ON, Canada, 2Weizmann Institute of Science, Rehovot, Israel, 3Department of Radiology, St Joseph's Healthcare. McMaster University, Hamilton, ON, Canada, 4DDE MRI Solutions Ltd., Tel Aviv, Israel
    We have investigated the capability of breast DTI-MRI parameters to monitor and quantitatively evaluate response to neoadjuvant systemic therapy in the four major breast cancer biological subtypes. DTI shows correlation with surgical pathology size and detected pCR in all subtypes. 
  • Multisite generalizability comparison of Dynamic Contrast Enhanced Breast MRI Breast Cancer Recurrence Score Models at multiple scales
    Michael Liu1, Richard Ha1, Terry Button2, Yucheng Liu1, Yun-Hsu Hao3, and Sachin Jambawalikar1
    1Radiology, Columbia University, New York, NY, United States, 2Stonybrook University, Stonybrook, NY, United States, 3Columbia University, New York, NY, United States
    Generalizability of Breast Dynamic Contrast Enhanced MRI based Oncotype DX score models benefit from multiscale sampling in multi-institutional data.
    This chart illustrates the flow of data into the network.

    1) The first three phases of each DCE Exam are gathered and stacked in the 4th dimension.

    2) Slices containing the biopsy site are then isolated and annotated.

    3) Before introduction to the model, the data is exposed to different scales of patch sampling, Hue shifts, and standard affine transforms.

    4) The network is trained using 5 fold cross validation with leave one out testing

    Performance Statistics for various sampling techniques
  • Registration-based whole breast segmentation enables highly reproducible quantitative MR-based breast density
    Jia Ying1, Renee Cattell1, and Chuan Huang1,2,3
    1Biomedical Engineering, Stony Brook University, Stony Brook, NY, United States, 2Radiology, Stony Brook Medicine, Stony Brook, NY, United States, 3Psychiatry, Stony Brook Medicine, Stony Brook, NY, United States
    MR-based quantitative assessment of breast density has a few unique advantages over mammography, which requires precise and accurate whole breast segmentation. In this work, a new whole breast segmentation strategy based on image registration has been proposed.
    Figure 1. Pipeline for registration-based breast segmentation algorithm
    Figure 3. Registration-based breast segmentation method better identifies the lower boundary of the breast region. The resulting segmentations (red) are overlaid to the breast images with the problematic area circled in green.
  • B-value derivation for diffusion-weighted Double-Echo Steady-State (dwDESS) sequences
    Ulrich Katscher1, Jakob Meineke1, Shuo Zhang2, and Jochen Keupp1
    1Philips Research Europe, Hamburg, Germany, 2Philips Healthcare, Hamburg, Germany
    An effective b-value has been defined for distortion-free diffusion-weighted imaging using a bipolar double-echo steady-state sequence, and successfully evaluated with phantom and volunteer breast measurements.
    Fig. 5: Comparison of breast DWI of a healthy volunteer. Upper row: standard DWI based on EPI, lower row: DWI based on DESS (dwDESS). The b-value for dwDESS is calculated using the proposed method and leads to same image contrast as standard DWI.
    Fig. 2: Overview of the diffusion signal model for a double-echo steady-state sequence in the bipolar case (details see text)
  • High spatial and temporal resolution breast DCE-MRI using MOCCO reconstruction for quantitative PK analysis
    Ping N Wang1, Julia V Velikina2, Leah C Henze Bancroft2, Alexey A Samsonov2, Frederick Felcz2, Roberta M Strigel1,2,3, and James H Holmes2
    1Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States, 2Department of Radiology, University of Wisconsin-Madison, Madison, WI, United States, 3Carbone Cancer Center, University of Wisconsin-Madison, Madison, WI, United States
    This work demonstrated that MOCCO can provide high temporal fidelity including robustness to recover different temporal enhancement curves for quantitative analysis in the setting of breast DCE-MRI.
    Figure 4. Visualization of error maps of (A) Ktrans = 0.133, 0.399, 0.666, 1.602 min-1 and Ve = 0.3 obtained by measuring the % differences between the fitted parameters and the true values (% error) for the lesion region depicted in (B). Red and blue represent the level of overestimation and underestimation, respectively.
    Figure 2: Simulated contrast agent concentration uptake curves (displayed for a subset of time from 150 s to 400 s). Mean concentration for eight lesions with varying pharmacokinetics reconstructed using MOCCO (A-H, red squares). Standard deviations are shown with banded areas. The input time curves (“truth”) used to generate the source data are plotted in black for all frames.
  • Impact of low-rank denoising on abbreviated breast diffusion-weighted acquisitions: accuracy and repeatability
    Patrick J Bolan1, Jessica A McKay2, Mehmet Akcakaya3, An L Church4, Michael T Nelson4, Kamil Ugurbil1, and Steen Moeller1
    1Radiology / Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States, 2Radiology, Stanford University, Palo Alto, CA, United States, 3Electrical and Computer Engineering /CMRR, University of Minnesota, Minneapolis, MN, United States, 4Radiology, University of Minnesota, Minneapolis, MN, United States
    This study describes the application of a low-rank denoising technique (NORDIC) on quantitative breast DWI. We found that this increased the accuracy and reproducibility of ADC maps, especially in low-SNR regions of the images.
    Fig 1: Example ADC maps from standard DWI scan, showing full acquisition (top row) and retrospectively shortened scans (middle and bottom row). The columns show the original scan (left), with low-rank denoising (middle), and the difference (right). Note the low-ADC tumor indicated by the red arrow.
    Fig 2: Patch-based analysis showing the impact of NORDIC on ADC maps as a function of SNR. For this example, all 40 ADC slices from a single subject were divided into 12x12 pixel patches, and the mean absolute difference between original and denoised patches was plotted as a function of SNR. The black line is a filtered moving average. In the full acquisition (A) the greatest impact of denoising is for patches with SNRdB<10, with the effect decreasing with increasing SNRdB. In the abbreviated acquisitions (B, C) the overall SNR is lower and more patches are affected by the denoising operation.
  • Triple negative breast cancer COX-2 expression distinctly alters spleen metabolism in immunocompromised mice compared to immunocompetent mice
    James Dion Barnett1, Marie-France Penet1, Balaji Krishnamachary 1, Zaver Bhujwalla1, Flonne Wildes1, Santosh Kumar Bharti1, and Yelena Mironchik1
    1The Johns Hopkins University School of Medicine, Baltimore, MD, United States
    Here we demonstrate how COX-2 expression may alter spleen metabolism that greatly impacts tumor progression and cancer persistence. Our findings suggest that tumor burden alone may drive metabolic alterations in the spleen.
    Data summarizing the spleen weights in (A) SCID mouse groups with non-tumor-bearing control (n=6), SUM-149-EV (n=9), SUM-149-COX-2 (n=12) mice and (B) BALB/c mouse groups with non-tumor-bearing control (n=5), 4T1-wt (n=3), 4T1-EV (n=5) and 4T1-COX2shRNA (n=5) mice. Values represent Mean ± SEM.
    Intensity quantification normalized to SCID mouse spleen weight from non-tumor-bearing control (n=6), SUM-149-EV (n=9), SUM-149-COX-2 (n=12) groups illustrated respectively for (A) glutamate, (B) glutamine, (C) glutathione, (D) lactate and (E) aspartate. Values represent Mean ± SEM.
  • Intra-tumoural lipid composition and lymphovascular invasion in breast cancer via non-invasive magnetic resonance spectroscopy
    Sai Man Cheung1, Ehab Husain2,3, Vasiliki Mallikourti1, Yazan Masannat3,4, Steven D Heys4, and Jiabao He1
    1Institute of Medical Sciences, University of Aberdeen, Aberdeen, United Kingdom, 2Pathology Department, Aberdeen Royal Infirmary, Aberdeen, United Kingdom, 3School of Medicine, University of Aberdeen, Aberdeen, United Kingdom, 4Breast Unit, Aberdeen Royal Infirmary, Aberdeen, United Kingdom
    Lipid composition, quantified using non-invasive double quantum filtered correlation spectroscopy, might provide a sensitive biomarker of lymphovascular invasion in breast tumours, providing an early prognostic marker of metastatic disease.

    Figure 1. Study design.

    A two-group cross sectional study in a flow chart. Freshly excised breast tumours from wide local excision or mastectomy were immediately scanned on a clinical 3 T MRI scanner to derive lipid composition using double quantum filtered–correlation spectroscopy (DQF-COSY). Immunohistochemical examinations were conducted to assess lymphovascular invasion (LVI), Ki-67 expression and Nottingham Prognostic Index (NPI). In total, 30 patients with invasive ductal carcinoma (IDC), 13 with LVI negative and 17 with LVI positive, participated in the study.

    Figure 2. Group difference in lipid composition.

    The difference in (a) monounsaturated fatty acids (MUFA), (b) triglycerides (TRG), (c) saturated FA (SFA) and (d) polyunsaturated FA (PUFA), are shown in dot plots. Each dot represents the measurement from a patient, and the dots are organised in two columns corresponding to the lymphovascular invasion (LVI) status. The error bar indicates the median and interquartile range. The Mann Whitney U tests were performed between the groups and p value is shown for each plot. Statistically significant p values (< 0.05) are marked by ‘*’.

  • Fast Longitudinal Image REgistration (FLIRE) for Breast MRI
    Michelle W Tong1, Maren M. Sjaastad Andreassen2, Ana Rodríguez-Soto1, Christopher C Conlin1, Tyler Seibert3, Michael Hahn1, Rebecca Rakow-Penner1, and Anders M Dale1
    1Radiology, University of California, San Diego, La Jolla, CA, United States, 2Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, Norway, 3Radiation Oncology, University of California, San Diego, La Jolla, CA, United States
    This study compared a novel registration technique, Fast Longitudinal Image REgistration (FLIRE) to a well established method (DRAMMS) for longitudinal breast registration. The study found comparable accuracy, but at a 12-18× faster processing time.
    Figure 1: (A,B) T1 images from a signal patient acquired throughout neoadjuvant chemotherapy treatment. (C,E) Images from follow-up visits were registered to baseline using FLIRE and (D,F) a well established registration program, DRAMMS. (E,F) Registered images are overlaid with baseline to evaluate differences. White indicates image similarities, blue is unique to baseline, and red is unique to the registered images. Both registration methods adequately correct for displacements in breast tissue.
    Figure 3: To compare registration accuracy, similarity measures for each patient were averaged across time points. In the box plot, the red line indicates the median value across all patients, the box indicates the range of values between the 25th and 75th percentile, the whiskers indicate minimum and maximum values within 1.5 times the interquartile range, and the red plus signs indicate values beyond this range.
  • Time-dependent IVIM/Non-Gaussian parameters between in vivo and post-mortem breast cancer xenograft models
    Yuko Someya1, Mami Iima1,2, Hirohiko Imai3, Hiroyoshi Isoda1, Masako Kataoka1, Denis Le Bihan4,5,6, and Yuji Nakamoto1
    1Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University, Kyoto, Japan, 2Department of Clinical Innovative medicine, Institute for advancement of clinical and translational science, Kyoto University Hospital, Kyoto, Japan, 3Department of Systems science, Graduate School of Informatics, Kyoto University, Kyoto, Japan, 4NeuroSpin/Joliot, CEA-Saclay Center, Paris-Saclay University, Gif-sur-Yvette, France, 5Human Brain Research Center, Kyoto University Graduate School of Medicine, Kyoto, Japan, 6National Institute for Physiological Sciences, Okazaki, Japan
    iWe investigated the time-dependency of IVIM /non-Gaussian diffusion parameters in vivo and post-mortem using breast xenograft models (MDA-MB-231). The change in these parameters might provide additional information to evaluate a tissue microstructure.
    Figure4. A representative case of fIVIM map at long diffusion time (A; in vivo, B; post-mortem and C: CD31 staining). fIVIM values dropped post-mortem as expected, due to the lack of perfusion, but did not reach 0. The lower fIVIM area was well correlated with the CD31-negative non-brownish area (arrow).
    Figure1. Box-whisker plots and line graphs of fIVIM values with different diffusion times in vivo and post-mortem.
  • Evaluation of CEST-mDixon imaging for breast malignancy characterization and staging: correlation with histopathology
    Ioannis Papadopoulos1, Ivan Dimitrov2, Jochen Keupp3, Durga Udayakumar1,4, Stephen Seiler1, Sunati Sahoo5, Yin Xi1, Emily Knippa1, Robert Lenkinski1,4, Ananth Madhuranthakam1,4, Shu Zhang6, and Elena Vinogradov1,4
    1Radiology, University of Texas Southwestern Medical Center, Dallas, TX, United States, 2Philips Healthcare, Gainesville, FL, United States, 3Philips Research, Hamburg, Germany, 4Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, TX, United States, 5Pathology, University of Texas Southwestern Medical Center, Dallas, TX, United States, 6Cancer Systems Imaging, University of Texas MD Anderson Cancer Center, Houston, TX, United States
    CEST-mDixon using MTRasym at 1ppm and 2ppm, shows significant potential in breast tumor aggressiveness differentiation. Ki-67 correlation is confirmed and, for the first time, a negative linear correlation with the percentage of cells positive for nuclear expression of the PR is found.
    CEST-mDixon result. Left: MTRasym maps for 1ppm, 2ppm and 3.5ppm for 3 slices. Right: Z-spectrum from the ROI placed over the suspicious lesion.
    Left to right: ROI averaged MTRasym­(1ppm), MTRasym­(2ppm) and MTRasym­(3.5ppm) compared to the Ki-67 histopathological index. A moderate positive correlation is observed for hydroxyls (1ppm) and amines (2 ppm).
  • Electric properties tomography (EPT) of breast tissue using High Spectral and Spatial resolution (HiSS) MRI
    Milica Medved1, Ulrich Katscher2, Hiroyuki Abe1, and Gregory S Karczmar1
    1Department of Radiology, The University of Chicago, Chicago, IL, United States, 2Philips Research, Hamburg, Germany
    We demonstrate feasibility of EPT analysis as applied to HiSS MRI data, which could simplify the process of lesion delineation relative to the current method and may thus improve the diagnostic accuracy of non-contrast breast MRI.
    Figure 1: A slice through the center of two invasive ductal carcinomas is shown in Fig. 1, for T2W-VISTA (a) and HiSS MRI water peak height (b) images. (c) and (d) show conductivity maps derived from (a) and (b), respectively, using EPT.