Weiting Huang¹, GuoRui Hou ², Chen Wang³, and Kai Ai^4
1Department of Magnetic Resonance, Lanzhou University Second Hospital, Lanzhou, China, ²Department of Magnetic Resonance, Xijing Hospital, Xi'an, China, ³Department of Radiology, Xijing Hospital, Xi'an, China, ⁴Philips Healthcare, Xi’an, China

Keywords: Prostate, Machine Learning/Artificial Intelligence, Spatial Transformer Network, Transfer learning

In this study, we propose a method to predict clinically significant state cancer based on MRI points of interest (POI) and classification network with multi-mode and multi-scale. Instead of the traditional method of manual delineation region-of-interest (ROI) to assist prediction, our method utilizes multi-scale input combined with Spatial Transformer Network (STN) to automatically adjust the adjust the scale of interest. This work also explored the possibility of predicting the grade of prostate cancer in a small amount of data using the method of transfer learning. Experiments show that this method has high prediction performance.

View Presentation Video

Vick Lau^1,2, Christopher Man^1,2, Shi Su^1,2, Ye Ding^1,2, Jiahao Hu^1,2, Junhao Zhang^1,2, Yujiao Zhao^1,2, Alex T. L. Leong^1,2, and Ed X. Wu^1,2
1Laboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, Hong Kong SAR, China, ²Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

Predicting brain age from structural MRI (sMRI) is potentially valuable as the deviation of predicted age from chronological age can be a biomarker for characterising brain health conditions. Currently, extensive pre-processing of sMRI data is required for most deep learning methods. This study presents a multi-task contrastive learning framework for simultaneous brain age prediction and gender classification from minimally processed, noisy 3D T1-weighted images. By including gender classification task and supervised contrastive learning, we demonstrate that leveraging gender information in training and better representation learning can boost age prediction accuracy for both in-domain and out-of-domain datasets.

View Presentation Video

Yifeng Gao¹, Zhen Zhou¹, Bing Zhang², Saidi Guo², Kairui Bo¹, Shuang Li¹, Nan Zhang¹, Hui Wang¹, Yang Guang³, Heye Zhang², Tong Liu⁴, Jianxiu Lian⁵, and Lei Xu^1
1Department of Radiology, Beijing Anzhen Hospital, Beijing, China, ²School of Biomedical Engineering, Sun Yat-Sen University, Guangzhou, China, ³National Heart and Lung Institute, Imperial College London, London, United Kingdom, ⁴Department of Cardiology, Beijing Anzhen Hospital, Beijing, China, ⁵Philips Healthcare, Beijing, China

Keywords: Machine Learning/Artificial Intelligence, Heart, Deep Learning; Heart Failure

We proposed a multi-source deep-learning model including traditional functional parameters and myocardial strain derived from cardiovascular magnetic resonance, as well as clinical features such as laboratory tests, electrocardiograms, and echocardiography. Meanwhile, we innovatively integrated cardiac motion characteristics through deep learning algorithms and fast neural convolution networks to construct deep learning heart failure prediction model. The results showed that compared with the traditional cox model, the deep learning model had higher efficacy for prognosis evaluation in patients with heart failure and could provide risk stratification in patients with heart failure, which may further guide clinical decision-making.

View Presentation Video

Chaojie Zhang¹, Shengjia Chen¹, Haoxu Huang², Haresh Rengaraj Rajamohan³, Jungkyu Park¹, Noah Kasmanoff¹, Kyunghyun Cho³, Gregory Chang¹, Richard Kijowski¹, and Cem M. Deniz^1
1Department of Radiology, New York University Langone Health, New York, NY, United States, ²Courant Institute of Mathematical Sciences, New York University, New York, NY, United States, ³Center for Data Science, New York University, New York, NY, United States

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

Our study implemented the self-supervised learning method, Twin Class Distribution Estimation, with unlabeled knee MR images. The self-supervised pretraining improves the downstream analysis in predicting total knee replacement within 9 years using labeled knee MR images. The self-supervised features are shown to be efficient classifiers in TKR prediction.

View Presentation Video

Walter Zhao¹, Xiaofeng Wang², Charit Tippareddy³, Hamed Akbari^4,5, Anahita Fathi Kazerooni^4,5, Christos Davatzikos^4,5, Marta Couce⁶, Andrew E. Sloan^6,7,8,9, Chaitra Badve³, and Dan Ma^1
1Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States, ²Department of Quantitative Health Sciences, Cleveland Clinic, Cleveland, OH, United States, ³Department of Radiology, Case Western Reserve University and University Hospitals Cleveland Medical Center, Cleveland, OH, United States, ⁴Center for Biomedical Image Computing and Analytics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States, ⁵Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States, ⁶Department of Pathology, Case Western Reserve University and University Hospitals Cleveland Medical Center, Cleveland, OH, United States, ⁷Department of Neurosurgery, Case Western Reserve University and University Hospitals Cleveland Medical Center, Cleveland, OH, United States, ⁸Seidman Cancer Center and Case Comprehensive Cancer Center, Cleveland, OH, United States, ⁹Piedmont Health, Atlanta, GA, United States

Keywords: Machine Learning/Artificial Intelligence, Cancer

Existing glioblastoma (GB) infiltration models are often limited by lack of true infiltration labels and employ the assumption that edema closer to tumor has higher infiltrative potential relative to distant edema. Here, we propose a semi-supervised learning scheme that incorporates pretraining on the near-far heuristic and spatial pseudo labeling using true infiltration labels for voxel-wise tumor infiltration prediction. Our results show improved classification performance following finetuning on labeled infiltration data compared to training on the near-far heuristic alone and indicate the potential in employing MR fingerprinting-based models to guide GB diagnosis and treatment.

View Presentation Video

Mohammed R. S. Sunoqrot^1,2, Rebecca Segre^1,3, Gabriel A. Nketiah^1,2, Alexandros Patsanis¹, Tone F. Bathen^1,2, and Mattijs Elschot^1,2
1Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU), Trondheim, Norway, ²Department of Radiology and Nuclear Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway, ³Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Torino, Italy

Keywords: Machine Learning/Artificial Intelligence, Prostate

Biparametric MRI (bpMRI) is a valuable tool for the diagnosis of prostate cancer (PCa). Computer-aided detection and diagnosis (CAD) systems have the potential to improve the robustness and efficiency of PCa detection) compared with conventional radiological reading. This work explores the combination of the results of two PCa CAD systems as input to a new classification model. We show that this is promising approach that can potentially improve the final detection of PCa.

Xiaohua Chen¹, Zhiqiang Chen², Zhuo Wang¹, Shaoru Zhang¹, Yunshu Zhou¹, Shili Liu¹, Ruodi Zhang¹, Yuhui Xiong³, and Aijun Wang^4
1Clinical medicine school of Ningxia Medical University, Yinchuan, China, ²Department of Radiology ,the First Hospital Affiliated to Hainan Medical College, Haikou, China, ³GE Healthcare MR Research, Beijing, China, ⁴Department of Radiology, General Hospital of Ningxia Medical University, Yinchuan, China

Keywords: Machine Learning/Artificial Intelligence, Brain

Using an automated method of convolutional neural networks (CNNs), we aimed to predict the IDH mutation status of gliomas from conventional preoperative MRI in this study. We conclude that the Markov Random Field-U-Net network can accurately segment the tumor region. Using a modified  34-layer Resnet network, we were subsequently able to predict IDH mutation status effectively. Consequently, the model has the potential to be utilized more broadly as a practical tool with reproducibility, this model has the potential to be a practical tool for the non-invasive characterization of gliomas to help the individualized treatment planning.

View Presentation Video

Vivian S. Nguyen^1,2, Adam J. Hasse³, Emily Tao¹, Jihye Jang⁴, Adil Javed⁵, Timothy J. Carroll³, and Keigo Kawaji^1,2
1Biomedical Engineering, Illinois Institute of Technology, Chicago, IL, United States, ²Medicine - Cardiology, University of Chicago Medical Center, Chicago, IL, United States, ³Radiology, University of Chicago Medical Center, Chicago, IL, United States, ⁴Philips Healthcare, Gainesville, FL, United States, ⁵Neurology, University of Chicago Medical Center, Chicago, IL, United States

Keywords: Machine Learning/Artificial Intelligence, Multiple Sclerosis

Multiple Sclerosis is a neuroinflammatory disease in which the immune system attacks nerve fibers and myelin sheaths, leading to the formation of lesions through white matter. Gadolinium-enhanced MRI is used to diagnose and track the progression of MS. Active MS lesions enhance with gadolinium, but there is an interest in prediction of lesion enhancement based on lesion features. In this study, we examined first-order features derived from T1w pre-contrast MS lesions acquired on multiple 3T imagers at a single center to train a logistic regression classifier to classify lesions as active or inactive.

View Presentation Video

Zhou Huang¹, Xue Chen², Nan Jiang¹, Su Hu¹, and Chunhong Hu^1
1Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China, ²Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou, China

Keywords: Machine Learning/Artificial Intelligence, Breast

To predict ductal carcinoma in situ with microinvasion (DCISMI) based on clinicopathologic, conventional breast magnetic resonance imaging (MRI), and dynamic contrast enhanced MRI (DCE-MRI) radiomics signatures in women with biopsy-confirmed ductal carcinoma in situ (DCIS) to choose high-risk women who may benefit from sentinel lymph node biopsy at initial surgery. The mixed model showed better AUC values than both clinicopathological and DCE-MRI radiomics models in both training/test sets with heterogeneous enhancement and radiomics scores as significant independent predict factors. The mixed model showed the greatest overall net benefit for upstaging and the second was the combine model.

View Presentation Video

Lidi Ma¹, Congrui Li², Haixia Li³, Kan Deng³, Cheng Zhang¹, Weijing Zhang¹, and Chuanmiao Xie^1
1Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, China, ²Department of Diagnostic Radiology, Hunan Cancer Hospital, Central South University, Changsha, China, ³Philips Healthcare, Guangzhou, China

Keywords: Machine Learning/Artificial Intelligence, Liver

In this study, we developed a deep learning model based on GD-DTPA-enhanced MRI data to predict the overall survival (OS) of patients with HCC. Our results showed that 3D-CNN model based on GD-DTPA-enhanced MRI can non-invasively predict the OS of patients with HCC. The combined model integrating the deep learning score and clinical factors showed a higher predictive value than the clinical and 3D-CNN models and may be more useful in guiding clinical treatment decisions to improve the prognosis of patients with HCC. 

Linkun Cai¹, Haijun Niu¹, Erwei Zhao², Yawen Liu¹, Tingting Zhang¹, Dong Liu³, Penggang Qiao⁴, Pengling Ren⁴, Wei Zheng², and Zhenchang Wang^4
1School of Biological Science and Medical Engineering,Beihang University, Beijing, China, ²National Space Science Center,Chinese Academy of Sciences, Beijing, China, ³Department of Ultrasound, Beijing Friendship Hospital, Beijing, China, ⁴Department of Radiology, Beijing Friendship Hospital, Beijing, China

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

The diagnosis and evaluation of cerebral perfusion status are crucial for the management of brain diseases. However, the detection method of cerebral perfusion status is complicated. Considering that CBF is mainly supplied by the internal carotid artery (ICA), this paper proposes a novel cerebral perfusion status prediction model, which can automatically quantify the cerebral perfusion level of patients by modeling the association between ICA blood flow and cerebral perfusion. The experimental results on a real-world dataset using machine learning methods can achieve satisfactory performance. Thus, it can be used as an effective adjuvant tool for determining the cerebral perfusion status.

View Presentation Video

Matteo Ferrante¹, Tommaso Boccato², Marianna Inglese², and Nicola Toschi^3,4
1Biomedicine and prevention, University of Rome Tor Vergata, Roma, Italy, ²Biomedicine and prevention, University of Rome Tor Vergata, Rome, Italy, ³BioMedicine and prevention, University of Rome Tor Vergata, Rome, Italy, ⁴Department of Radiology,, Athinoula A. Martinos Center for Biomedical Imaging and Harvard Medical school, Boston, MA, USA, Boston, MA, United States

Keywords: Machine Learning/Artificial Intelligence, Alzheimer's Disease

The willingness to trust predictions formulated by automatic algorithms is key in a vast number of domains. We propose converting a standard neural network into a Bayesian neural network and estimating the variability of predictions by sampling different networks at inference time. We use a rejection-based approach to increase classification accuracy from 0.86 to 0.95 while retaining 75% of the test set for Alzheimer disease classification from MRI morphometry images. Estimating uncertainty of a prediction and modulating the behavior of the network to a desirable degree of confidence, represents a crucial step in the direction of responsible and trustworthy AI.

View Presentation Video

Junru Zhong¹, Yongcheng Yao¹, Dόnal G. Cahill², Fan Xiao³, Siyue Li¹, Jack Lee⁴, Kevin Ki-Wai Ho⁵, Michael Tim-Yun Ong⁵, James F. Griffith², and Weitian Chen^1
1CU Lab for AI in Radiology (CLAIR), Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Sha Tin, NT, Hong Kong, ²Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Sha Tin, NT, Hong Kong, ³Department of Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China, ⁴Centre for Clinical Research and Biostatistics, The Chinese University of Hong Kong, Sha Tin, NT, Hong Kong, ⁵Department of Orthopaedics & Traumatology, The Chinese University of Hong Kong, Sha Tin, NT, Hong Kong

Keywords: Osteoarthritis, Osteoarthritis

We propose a knee osteoarthritis phenotype classification system using unsupervised domain adaptation (UDA). A convolutional neural network was initially trained on a large source dataset (Osteoarthritis Initiative, n=3116), then adapted to a small target dataset (n=50). We observed a significant performance improvement compared to the classifiers trained solely on the target dataset. We demonstrated the feasibility of applying UDA for medical image analysis in a small label-free dataset.

View Presentation Video

Haresh Rengaraj Rajamohan¹, Kyunghyun Cho¹, Richard Kijowski², and Cem M. Deniz^2
1New York University, NEW YORK, NY, United States, ²NYU Langone Health, NEW YORK, NY, United States

Keywords: Osteoarthritis, Machine Learning/Artificial Intelligence, Deep Learning

We propose a novel risk constraint to improve the performance of deep learning models on progressive disorders. On the Osteoarthritis Initiative (OAI) dataset, the proposed approach outperforms a baseline model trained with the standard cross-entropy loss on predicting total knee replacement (TKR) within 3 different time horizons- 1 year, 2 years and 4 years of the MRI date. It further generalizes better to the external Multicenter Osteoarthritis Study dataset.

View Presentation Video

Anthony A Gatti¹, Dave Van Veen², Garry E Gold¹, Scott L Delp³, and Akshay S Chaudhari^1
1Radiology, Stanford University, Stanford, CA, United States, ²Electrical Engineering, Stanford University, Stanford, CA, United States, ³Bioengineering, Stanford University, Stanford, CA, United States

Keywords: Osteoarthritis, Machine Learning/Artificial Intelligence

MRI-based statistical shape models can predict future disease and distinguish between patient groups. However, these models require thousands of matching points between bones which may introduce biases and their strictly linearly orthogonal features is a limitation. This study built continuous 3D shape representations of the femur using neural implicit representations and used the learned latent space to predict knee pain. The neural shape model can generate arbitrarily high resolution surfaces and predict pain with area under the receiver operating characteristic curve of 0.7 and sensitivity of 0.89, metrics comparable to deep learning methods trained on orders of magnitude more data.

View Presentation Video

Maysam Orouskhani¹, Shaojun Xia², Mahmud Mossa-Basha³, and Chengcheng Zhu^3
1University of Washington, SEATTLE, WA, United States, ²Peking University Cancer Hospitals & Institution, Beijing, China, ³Department of Radiology, University of Washington, Seattle, WA, United States

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence, Aneurysm detection, nnDetection, Aneurysm Localization

Intracranial aneurysms are relatively common life-threatening diseases with a prevalence of 3.2% in the general population. Therefore, detection is a vital task in aneurysm management. Lesion detection refers to simultaneously localizing and categorizing the lesions in medical images. In this study, we employed nnDetection framework, a self-configuring framework for 3D medical object detection, to detect and localize the 3D coordination of aneurysms. To capture and extract diverse features of aneurysms, two modalities including TOF-MRA, and structural MRI from ADAM dataset have been used. The performance of the proposed deep learning model was evaluated by free-response receiver operative characteristics

View Presentation Video

Eisa Hedayati¹, Haresh Rajamohan², Lily Zhou³, Kyunghyun Cho², Gregory Chang¹, Richard Kijowski¹, and Cem M Deniz^1
1Radiology, New York University Langone health, New York, NY, United States, ²Center for data Science, New York University, New York, NY, United States, ³Radiology & diagnostic Imaging, University of Alberta, Edmonton, AB, Canada

Keywords: Machine Learning/Artificial Intelligence, Osteoarthritis

"When do I need my knee replaced? " is a common question of patients with progressed osteoarthritis conditions. However, answering that question is not trivial, especially for cases that do not result in an immediate surgery. To help doctors addressing this question we employed neural networks to recommend an estimated subject-specific date for the total knee replacement (TKR).

View Presentation Video

Po-Jui Lu^1,2,3, Benjamin Odry⁴, Muhamed Barakovic^1,2,3, Matthias Weigel^1,2,3,5, Robin Sandkühler⁶, Reza Rahmanzadeh⁷, Xinjie Chen^1,2,3, Mario Ocampo-Pineda^1,2,3, Jens Kuhle^2,3, Ludwig Kappos^2,3, Philippe Cattin⁶, and Cristina Granziera^1,2,3
1Translational Imaging in Neurology (ThINk) Basel, Department of Medicine and Biomedical Engineering, University Hospital Basel and University of Basel, Basel, Switzerland, ²Department of Neurology, University Hospital Basel, Basel, Switzerland, ³Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland, ⁴AI for Clinical Analytics, Covera Health, New York, NY, United States, ⁵Division of Radiological Physics, Department of Radiology, University Hospital Basel, Basel, Switzerland, ⁶Center for medical Image Analysis & Navigation, Department of Biomedical Engineering, University of Basel, Allschwil, Switzerland, ⁷Neuroradiology Department, Inselspital, Bern, Switzerland

Keywords: Machine Learning/Artificial Intelligence, Multiple Sclerosis

The decision process of artificial intelligence is elusive. We proposed a new method that by combining an attention-based convolutional neural network (GAMER-MRI) with the modified Layer-wise Relevance Propagation could reveal relevant regions on quantitative imaging maps in differentiating multiple sclerosis patients with mild-moderate and severe disabilities. The assessment of the relevant regions included the impact of inverting values within the regions and the heatmap on the MNI152 template. Our results show good network performance and identify brain regions relevant to the corticospinal tract. The proposed method might be useful to further explore patterns of brain microstructural alterations associated with disability.

View Presentation Video

Vlora Riberdy¹, Alessandro Guida^2,3, James Rioux^1,2,3, and Kimberly Brewer^1,2,3,4,5
1Physics and Atmospheric Science, Dalhousie University, Halifax, NS, Canada, ²Diagnostic Radiology, Dalhousie University, Halifax, NS, Canada, ³Biomedical MRI Research Laboratory, Nova Scotia Health Authority, Halifax, NS, Canada, ⁴School of Biomedical Engineering, Dalhousie University, Halifax, NS, Canada, ⁵Microbiology & Immunology, Dalhousie University, Halifax, NS, Canada

Keywords: Molecular Imaging, Radiomics

Molecular MRI allows for immunotherapy treatment monitoring of glioblastoma, but analysis of multi-parametric data is complex.  Machine learning algorithms can be applied to quantitative maps, to identify correlations between radiomic features and treatment outcomes. Feature selection is key when dealing with longitudinal preclinical data with multiple contrasts and small group numbers. We evaluated three feature selection methods in terms of their ability to produce predictive models of survival.  The best performance was seen using recursive feature elimination applied to features from iron concentration maps of the tumor, which yielded an ROC AUC of 0.78 and an accuracy of 0.72.

View Presentation Video

Gelareh Valizadeh¹, Fereshteh Khodadadi Shoushtari², Soheila Koopaee¹, Hanieh Mobarak Salari¹, Mohammad Hossein Golezar³, Masomeh Gity⁴, and Hamidreza Saligheh Rad^1,5
1Quantitative MR Imaging and Spectroscopy Group, Tehran University of Medical Sciences, Tehran, Iran (Islamic Republic of), ²Shiraz University, Shiraz, Iran (Islamic Republic of), ³Shahed University, Tehran, Iran (Islamic Republic of), ⁴Tehran university, Tehran, Iran (Islamic Republic of), ⁵Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran (Islamic Republic of)

Keywords: Multimodal, Breast

This study aimed to assess added value of various combinations of different MRI protocols and artificial intelligence techniques in differentiation capability between malignant and benign breast lesions. 61 benign and 69 malignant lesions were recruited. Radiomics features were extracted from three proposed scenarios, including original images of ADC and T2W (scenario-I), original images of ADC, T2W, and DCE (scenario-II), and the joint of original and the pre-filtered images (using wavelet) from ADC, T2W and DCE (scenario-III). Ten most relevant features were utilized for training 11 machine learning algorithms. Finally, decision tree achieved the highest results of accuracy using scenario-III.