Qi Zhang¹, Caixia Fu², Qing Li³, and Yajie Li^4
1Department of Radiology, Huashan hospital, Fudan University, Shanghai, China, ²MR Application Development, Siemens Shenzhen Magnetic Resonance Ltd., Shenzhen, China, ³MR Collaborations, Siemens Healthineers Digital Technology (Shanghai) Co., Ltd., Shanghai, China, ⁴Fudan University, Shanghai, China

Keywords: Uterus, Molecular Imaging

In vivo, NPBCNs generated strong signal enhancement in endometriosis lesion in rat on T1-weighted images via MRI.

Yida Wang¹, He Zhang², Xiance Zhao³, and Guang Yang^1
1Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China, ²Department of Radiology, Obstetrics and Gynecology Hospital, Fudan University, Shanghai, China, ³Philips Healthcare, Shanghai, China

Keywords: Uterus, Cancer

We developed a multi-task deep learning model using multi-parametric MRI to simultaneously predict lymphatic nodes metastasis (LNM) and lymphatic vascular space invasion (LVSI) in patients with endometrial cancer. Cross-modality attention mechanism was integrated with the model to learn the within and cross modality-specific features which could enhance the performance of network. In this study, we also treated endometrial cancer regions as the anatomical prior knowledge to capture the discriminative information from the whole MR images. The results showed the proposed model predicted LNM and LVSI with a high accuracy in both internal and external test datasets.

Ma Changjun¹, Tian Shifeng¹, Song Qingling¹, Chen Lihua¹, Wang Nan², Lin Liangjie³, Wang Jiazheng⁴, and Liu Ailian^1
1Department of Radiology,, The First Affiliated Hospital of Dalian Medical University, Dalian, China, China, ²Department of Radiology, The First Affiliated Hospital of Dalian Medical University, Dalian, China, China, ³Clinical & Technical Support, Philips Healthcare, Beijing, China, China, ⁴Clinical & Technical Support, Philips Healthcare, Shanghai, China, China

Keywords: Pelvis, Quantitative Imaging

it is necessary to find a method for non-invasive monitoring of Her-2 status. MRI with characteristics of multi-direction, multi-parameter, multi-function, high soft-tissue resolution, and non-invasiveness, has become the preferred method for evaluation of uterine lesions.

Yiang Wang¹, Mengge He¹, Peng Cao¹, Chien-Yuan Lin², Weiyin Liu², Chia-Wei Lee², and Elaine Y.P. Lee^1
1Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, Hong Kong, ²GE Healthcare, Taipei, Taiwan

Keywords: Uterus, Cancer, Endometrial Cancer; Tumor Grade

Random forest models were constructed to predict tumor grade (grade 1-2 vs. grade 3) of endometrial cancer based on radiomics features extracted from quantitative T1, T2, proton density maps generated by synthetic MRI and apparent diffusion coefficient maps generated by diffusion-weighted imaging. The classification model based on features extracted from all the quantitative maps achieved the highest area under the curve of 0.804 compared to models constructed based on single quantitative map.

View Presentation Video

Keywords: Pelvis, Diffusion/other diffusion imaging techniques, image reconstruction

Multi-shot EPI is commonly used to compensate for geometric distortions and increase spatial resolution in body diffusion MRI, with a price tag of longer scan times. This work presents an alternative technique to k-space undersampling to accelerate the acquisition, which is based on reducing the number of repetitions at high b-value and denoising the resulting images using a convolutional neural network. The proposed deep learning denoising technique is demonstrated to accelerate the acquisition of multi-shot diffusion MRI acquisition of patients with rectal cancer and reduce the scan time beyond the duration of a single-shot diffusion MRI acquisition.

Yihe Gao¹, Ke Xue², Yongming Dai², and Jing Ye^1
1Northern Jiangsu People's Hospital, Yangzhou, Jiangsu Province, China, ²MR Collaboration, Central Research Institute, United Imaging Healthcare, Shanghai, China, Shanghai, China

Keywords: Uterus, Microstructure, multi dimension

Accurately staging squamous cell carcinoma (SCC) is of vital importance for determining the treatment plan, prognosis and outcome. Diffusion-relaxation correlation spectrum imaging (DR-CSI) can jointly encode diffusion and relaxation information and resolve information of tissue compartments and heterogeneity at a sub-voxel level. In this study we investigated the feasibility of DR-CSI in characterizing tissue microenvironment and staging SCC. The DR-CSI technique can non-invasively provide information on microscopic tissue compartments within voxels, reflecting intra-tissue heterogeneity. The diagnostic performance of DR-CSI in identifying early and advanced SCC was significantly superior to conventional ADC and T2. 

View Presentation Video

Keywords: Uterus, Diffusion/other diffusion imaging techniques, amide proton transfer weighted imaging,cervical cancer,squamous cell carcinoma of the cervix

The pathological differentiation of cervical squamous cell carcinoma (CSCC) determines the therapy method and prognosis. APTw, DWI and IVIM sequences were performed for predicting pathological differentiation. 27 patients with well-moderately differentiation, 13 patients with poorly differentiation and 15 healthy volunteers were enrolled. APT SI, ADC, D*, D and f values were calculated for comparing among different groups. Results showed parameters except D* differed significantly between CSCC and normal. There were statistically significant differences in AUC of APT SI, D and f between well-moderately group and poorly differentiated group. APTw and IVIM can be used to identify pathological differentiation of CSCC.

View Presentation Video

Yibei Yu¹, Xiaolei Song², Lixue Wang¹, Dandan Zheng³, and Zhuozhao Zheng^1
1Radiology department, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China, ²Center for Biomedical Imaging Research, School of Medicine, Tsinghua University, Beijing, China, ³Clinical& Technical Support, Philips Healthcare, Beijing, China

Keywords: Pelvis, CEST & MT

The therapies for ovarian cystadenoma and cystadenocarcinoma are different, thus the differential diagnosis of ovarian lesions is critical. The diagnostic efficacy increased with the use of DWI and DCE-MRI, but the differential diagnosis of cystic ovarian lesions is still a challenge. This study evaluates the diagnostic efficacy of 3D APTw MRI in the differentiation between cystadenoma and cystadenocarcinoma based on the analysis of the cystic regions. The results showed that APTw SIs had better diagnostic performance than ADC values and may be used as a noninvasive tool for differential diagnosis and therapy guidance.

Yajie Li^1,2, Qi Zhang², Caixia Fu³, Qing Li⁴, and Robert Grimm^5
1Shanghai Institute of Medical Imaging, Shanghai, China, ²Department of Radiology, Huashan Hospital, Shanghai, China, ³MR Application Development, Siemens Shenzhen Magnetic Resonance Ltd., Shenzhen, China, ⁴MR Collaborations, Siemens Healthineers Digital Technology (Shanghai) Co., Ltd., Shanghai, China, ⁵MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany

Keywords: Uterus, Diffusion/other diffusion imaging techniques, Intravoxel incoherent motion, Microcirculation, Perfusion

Purpose: To assess the feasibility of intravoxel incoherent motion MRI on detecting the microcirculatory changes in the uterus of women during the menstrual cycle.

Methods: Volunteers underwent MRI scans by using IVIM. The changes of D value, D* and f value of three layers of uterine structure during menstrual cycle were analyzed quantitatively.

Results: During menstrual cycle, the D values of junctional zone were significantly lower than in myometrium. Meanwhile, the f values of the three zones structure of uterus were significantly different.

Conclusion: IVIM can be used for noninvasive and quantitative evaluation of uterine blood microcirculation changes.

View Presentation Video

Paddy J. Slator¹, Jana Hutter ^2,3, Raphael Tomi Tricot^2,3,4, Jordina Aviles Verdera^2,3, Joseph V. Hajnal^2,3, and Daniel C. Alexander^1
1Centre for Medical Image Computing and Department of Computer Science, University College London, London, United Kingdom, ²Centre for the Developing Brain, School of Biomedicial Engineering and Imaging Sciences, King's College London, London, United Kingdom, ³Biomedical Engineering Department, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, ⁴MR Research Collaborations, Siemens Healthcare Limited, Frimley, United Kingdom

Keywords: Placenta, Low-Field MRI

Placental MRI is emerging as a promising adjunct to ultrasound during pregnancy. Low field MRI is appealing for multiple reasons and can support the widespread roll out of placental MRI. Here we provide a proof-of-concept that a quantitative placental imaging technique that has been demonstrated at high-field (1.5T / 3T) – combined T2*-diffusion MRI – is also viable at low field (0.55T). We highlight similarities and differences in low-field maps compared to the current state-of-the-art high-field maps and highlight key areas for future work to realise the potential of low-field placental quantitative MRI during pregnancy.

View Presentation Video

Daniel Cromb^1,2, Paddy J Slator³, Anthony Price^1,2, Miguel De La Fuente¹, Alexia Egloff-Collado¹, Mary Rutherford^1,4, Serena J Counsell^1,2, and Jana J Hutter^1,2
1Centre for the Developing Brain, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, ²Biomedical Engineering Department, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, ³Centre for Medical Image Computing, Department of Computer Science, University College London, London, United Kingdom, ⁴MRC Centre for Neurodevelopmental Disorders, King's College London, London, United Kingdom

Keywords: Placenta, Placenta

This study provides unique data on the evolution of quantitative multi-modal placenta MRl measures over gestation, including, crucially, within-subject results. A multi-compartmental T2*-IVIM model was employed, suited to the complex physiology of the human placenta, and matched to the deployed multi-parametric acquisition technique.

View Presentation Video

George Hutchinson¹, Adam Blakey², Neele Dellschaft¹, Nia Jones³, Reuben O'Dea², Lopa Leach⁴, Matthew Hubbard², Paul Houston², and Penny Gowland^1
1The Sir Peter Mansfield Imaging Centre, The University of Nottingham, Nottingham, United Kingdom, ²Mathematical Sciences, The University of Nottingham, Nottingham, United Kingdom, ³Medicine, The University of Nottingham, Nottingham, United Kingdom, ⁴Life Sciences, The University of Nottingham, Nottingham, United Kingdom

Keywords: Placenta, Diffusion/other diffusion imaging techniques

Placental diffusion imaging data is assumed to be driven by a combination of slow diffusive processes, as well as faster incoherent terms. How these faster incoherent terms combine within a voxel is not obvious, and here we investigate this further by comparing a mathematical simulation of maternal flow through a single placentone to data collected in utero. We observe maternal flows can cause IVIM like effects, with slow exponential decays, but also regions of fast IVIM similar to those observed in the placenta, as well as 'rebounding' of signal. 

View Presentation Video

Daniel Cromb^1,2, Paddy J Slator³, Anthony Price^1,2, Megan Hall^1,2, Daniel Alexander³, Joseph V Hajnal^1,2, Mary Rutherford^1,4, Jana Hutter^1,2, and Serena J Counsell^1,2
1Centre for the Developing Brain, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, ²Biomedical Engineering Department, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, ³Centre for Medical Image Computing, Department of Computer Science, University College London, London, United Kingdom, ⁴MRC Centre for Neurodevelopmental Disorders, King's College London, London, United Kingdom

Keywords: Placenta, Placenta, Diffusion, Microstructure

Congenital heart disease (CHD) is common and associated with abnormal placental development. We used novel diffusion MRI acquisition and analysis techniques to inspect placental microstructure in pregnancies affected by congenital heart disease (CHD), highlighting the potential value of this approach for in-utero identification of how placental development may deviate from normal in CHD.

View Presentation Video

Haijie Wang¹, Yida Wang¹, Chenglong Wang¹, He Zhang², Hao Zhu³, Yuanyuan Lu⁴, Yang Song⁵, and Guang Yang^1
1Shanghai key lab of magnetic resonance, East China Normal University, Shanghai, China, ²Department of Radiology, Obstetrics and Gynecology Hospital of Fudan University, Shanghai, China, ³Department of Obstetrics, Obstetrics and Gynecology Hospital of Fudan University, Shanghai, China, ⁴Department of Radiology, Shanghai First Maternity and Infant Health Hospital, Shanghai, China, ⁵MR Scientific Marketing, Siemens Healthcare, Shanghai, China

Keywords: Placenta, Placenta

Placenta accreta spectrum (PAS) is a pathologic condition of placentation associated with significant maternal morbidity and mortality. We enrolled 540 patients from two institutions to build an automatic pipeline for early diagnosis of PAS based on T2W images. An nnU-Net model was trained for automatic segmentation of the placenta, then an image stripe was created, in which utero-placental borderline (UPB) was straightened and centered. The UPB image was fed into a DenseNet-based network together with placental position for PAS diagnosis. The pipeline achieved good performance with AUCs of 0.860 and 0.897 in internal and external test cohorts, respectively.

View Presentation Video

Ruiming Chen¹, Daniel Seiter¹, Logan T. Keding^2,3, Jessica Vazquez^2,3, Kathleen Antony⁴, Heather A. Simmons^2,3, Kevin M. Johnson^1,5,6, Aleksandar K. Stanic⁴, Ruo-Yu Liu¹, Dinesh Shah⁴, Thaddus G. Golos^2,3, and Oliver Wieben^1,5,6
1Medical Physics, University of Wisconsin - Madison, Madison, WI, United States, ²Wisconsin National Primate Research Center, University of Wisconsin - Madison, Madison, WI, United States, ³Comparative Biosciences, University of Wisconsin - Madison, Madison, WI, United States, ⁴Obstetrics & Gynecology, University of Wisconsin - Madison, Madison, WI, United States, ⁵Radiology, University of Wisconsin - Madison, Madison, WI, United States, ⁶Biomedical Engineering, University of Wisconsin - Madison, Madison, WI, United States

Keywords: Placenta, DSC & DCE Perfusion

Placental blood flow is a marker that reflects the health of the utero-placental vasculature. Dynamic contrast-enhanced (DCE) MRI is more robust than arterial spin labeling and can be utilized in animal models to provide cotyledon-specific blood flow and blood volume measurements in vivo throughout gestation.  This study investigated the distribution of blood flow to the placental at a cotyledon level in pregnant rhesus monkeys before and following the injection of Tisseel (a fibrin sealant) and MCP1 (an inflammatory response inducer) to assess the predictabilities of flow for placental injury.