Lun M Wong¹, Qi-Yong H Ai^1,2, Tiffany Y So¹, Jacky WK Lam^3,4, and Ann D King^1
1Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong, Hong Kong, ²Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, Hong Kong, ³Department of Chemical Pathology, The Chinese University of Hong Kong, Hong Kong, Hong Kong, ⁴State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong, Hong Kong

Keywords: Machine Learning/Artificial Intelligence, Screening, XAI, explainability, deep learning

In this study, we propose a simple method to improve the explainability of artificial intelligence, specifically convolutional neural networks (CNNs), for the automatic detection of early nasopharyngeal carcinoma (NPC) on magnetic resonance imaging (MRI). We show a long-short-term-memory (LSTM) unit can be introduced into a CNN to read 3-dimensional medical image series. A risk curve can be extracted from the LSTM to visualize the “thought process” of the network when it reads through the input MRI slice-by-slice. This modification improves the explainability of the network without reducing performance for the early NPC detections of the original CNN.

View Presentation Video

Wenqi Zhou^1,2, Xinzhou Li^1,2, Fatemeh Zabihollahy¹, David S. Lu¹, and Holden H. Wu^1,2
1Department of Radiological Sciences, UCLA, Los Angeles, CA, United States, ²Department of Bioengineering, UCLA, Los Angeles, CA, United States

Keywords: Machine Learning/Artificial Intelligence, MR-Guided Interventions

Needle localization in 3D images during MRI-guided interventions is challenging due to the complex structure of biological tissue and the variability in the appearance of needle features in in-vivo MR images. Deep learning networks such as the Mask Regional Convolutional Neural Network (R-CNN) could address this challenge by providing accurate needle feature segmentation in intra-procedural MR images. This work developed an automatic coarse-to-fine pipeline that combines 2.5D and 2D Mask R-CNN to leverage inter-slice information and localize the needle tip and axis in in-vivo intra-procedural 3D MR images.

Apoorva Agarwal¹, Chitresh Bhushan², Desmond T.B. Yeo², Thomas Foo², Dawei Gui³, Deepa Anand¹, Maggie Fung⁴, Trevor Kolupar³, Tisha Abraham¹, Sanjay NT¹, Kameswari Padmanabhan¹, Uday Patil¹, and Dattesh Shanbhag^1
1GE Healthcare, Bengaluru, India, ²GE Global Research, Niskayuna, NY, United States, ³GE Healthcare, Waukesha, WI, United States, ⁴GE Healthcare, New York City, NY, United States

Keywords: Machine Learning/Artificial Intelligence, MSK

In clinical practice, oblique coronal and sagittal scans have been shown to be superior for visualization of ACL and assessment of ACL tears. In this work, we demonstrate a Deep Learning based method to obtain these complex scan planes (Coronal ACL and Coronal Blumensaat) directly from standard 2D tri-planar Localizers. Results on 487 test volumes show <0.6mm mean error for both planes, indicating suitability for clinical usage.

View Presentation Video

Chen Qian¹, Yiting Sun¹, Zi Wang¹, Xinlin Zhang¹, Qinrui Cai¹, Taishan Kang², Boyu Jiang³, Ran Tao³, Zhigang Wu⁴, Di Guo⁵, and Xiaobo Qu^1
1Department of Electronic Science, Biomedical Intelligent Cloud R&D Center, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China, ²Department of Radiology, Zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, China, ³United Imaging Healthcare, Shanghai, China, ⁴Philips, Beijing, China, ⁵School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China

Keywords: Machine Learning/Artificial Intelligence, Brain, Diffusion MR, Physics-informed

Deep learning is widely employed in biomedical magnetic resonance image (MRI) reconstructions. However, accurate training data are unavailable in multi-shot interleaved echo planer imaging (Ms-iEPI) diffusion MRI (DWI) due to inter-shot motion. In this work, we propose a Physics-Informed Deep DWI reconstruction method (PIDD). For Ms-iEPI DWI data synthesis, a simplified physical motion model for motion-induced phase synthesis is proposed. Then, lots of synthetic phases are combined with a few real data to generate efficient training data. Extensive results show that, PIDD trained on synthetic data enables sub-second, ultra-fast, high-quality, and robust reconstruction with different b-values and undersampling patterns.

View Presentation Video

Grant Nikseresht¹, Arnold M. Evia², David A. Bennett², Julie A. Schneider², Gady Agam¹, and Konstantinos Arfanakis^2,3
1Computer Science, Illinois Institute of Technology, Chicago, IL, United States, ²Rush Alzheimer's Disease Center, Rush University Medical Center, Chicago, IL, United States, ³Biomedical Engineering, Illinois Institute of Technology, Chicago, IL, United States

Keywords: Machine Learning/Artificial Intelligence, Aging, Ex-Viov Applications, Neuro (Microbleeds)

Detection of cerebral microbleeds (CMBs) on ex-vivo gradient echo MR images is an important task in MRI-pathology studies in older adults. The goal of this study was to develop a confidence-aware ex-vivo CMB detection algorithm that outputs interpretable probabilities and ranking of CMB candidates on brain MRI scans of community-based older adults.  The present study demonstrates that training an ex-vivo CMB detection model with confidence-aware deep learning, a technique for improving confidence estimation and ordinal ranking of examples in classification models, improves detection performance and prediction interpretability.

View Presentation Video

Yue Guan¹, Yudu Li^2,3, Ruihao Liu^1,2, Ziyu Meng¹, Yao Li¹, Yiping P. Du¹, and Zhi-Pei Liang^2,4
1School of Biomedical Engineering, Institute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China, ²Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, United States, ³National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign, Urbana, IL, United States, ⁴Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, United States

Keywords: Machine Learning/Artificial Intelligence, Image Reconstruction

Deep learning-based image reconstruction has two known practical issues: (a) sensitivity to data perturbations, and (b) poor generalization. An approach to addressing these issues is to use classical signal models to assist/constrain deep learning. This paper performs a systematic analysis of the role   of signal models in model-assisted deep learning-based reconstruction. Our results show that signal models (e.g., subspace model or sparse model) can substantially reduce the sensitivity of deep learning-based reconstruction to data perturbations; they can also help improve generalization capability.

View Presentation Video

Ke Fang¹, Zejun Wang², Zhaowei Cheng¹, Bao Wang³, Xinyu Jin¹, Yingchao Liu⁴, and Ruiliang Bai^5
1College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China, ²Key Laboratory of Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China, ³Department of Radiology, Qilu Hospital of Shandong University, Jinan, China, ⁴Department of Neurosurgery, Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China, ⁵School of Medicine, Zhejiang University, Hangzhou, China

Keywords: Machine Learning/Artificial Intelligence, Data Analysis

The pharmacokinetic (PK) parameters extracted from the DCE-MRI provide valuable information but suffer from many sources of variability. Thus, the efficient and fast estimation of the distributions of these ambiguous PK parameters caused by variabilities could significantly improve the robustness and repeatability of DCE-MRI. The estimation of the PK parameters’ distributions provides a way to quantify the PK parameters’ values and variabilities simultaneously. In this study, we demonstrated the feasibility of the normalizing flow-based distribution estimation network (FPDEN) for PK parameters’ distribution estimation in DCE-MRI.

View Presentation Video

Zhiyuan Li^1,2, Hailong Li¹, Nehal Parikh³, Jonathan Dillman¹, Anca Ralescu², and Lili He^1
1Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, ²Department of Computer Science, University of Cincinnati, Cincinnati, OH, United States, ³The Perinatal Institute, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States

Keywords: Machine Learning/Artificial Intelligence, Brain Connectivity, Contrastive Learning, Cognitive Deficits

Deep learning has shown promising results in early predicting cognitive deficits in very preterm infants using multimodal brain MRI data, acquired soon after birth. Prior methods focus on the feature fusion of different modalities but ignore the latent high-order feature similarity information. In this study, we propose a novel deep multimodal contrastive network using T2-weighted structural MRI (sMRI), diffusion tensor imaging (DTI), resting-state functional MRI (rsfMRI), and clinical data to predict later cognitive deficits. Our proposed model significantly improved predictive power compared to other peer models for early diagnosis of cognitive deficits.

View Presentation Video

Keywords: Machine Learning/Artificial Intelligence, Low-Field MRI, super-resolution, Hyperfine

Computer vision methods can be used for image quality transfer (IQT) to address the poor contrast, decreased resolution and increased noise observed in MR images acquired at ultra-low magnetic fields. Current methods have been shown to produce high-quality synthetic outputs for low-field (~0.5T) but not ultra-low-field (~0.05T) field images. Moreover, these methods do not adapt well to the presence of abnormal morphology (e.g. lesions). Here we introduce a new approach to ultra-low field IQT that improves on previous methods and is adaptive to the presence of synthetic lesions.

View Presentation Video

Chenghao Zhang¹, Mikhail Morgan¹, Yanting Yang¹, Ye Tian¹, and Jia Guo^1
1Columbia University, New York, NY, United States

Keywords: Machine Learning/Artificial Intelligence, Brain

Image registration is currently employed to assist with diagnostic tasks such as neurodegenerative disease diagnosis. Aging also affects the brain, and our knowledge of age-related brain diseases is currently encumbered by age-induced bias; understanding the mechanisms of neurodegenerative diseases requires a deeper understanding of aging. Thus we have devised a pipeline for generating age-specific templates using a novel deep-learning algorithm detailed in a separate report. Our results show qualitative changes in brain morphology across age groups, and tissue segmentation was performed on each template to calculate volumetric changes in brain matter across time.

View Presentation Video

Maëliss Jallais^1,2 and Marco Palombo^1,2
1Cardiff University Brain Research Imaging Centre, Cardiff University, Cardiff, United Kingdom, ²School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom

Keywords: Signal Modeling, Microstructure, dMRI

This work proposes µGUIDE: a general Bayesian framework to estimate posterior distributions of tissue microstructure parameters from any given biophysical model or MRI signal representation, with exemplar demonstration in diffusion-weighted MRI. Harnessing a new deep learning architecture for automatic signal feature selection combined with simulation-based inference and efficient sampling of the posterior distributions, µGUIDE bypasses the high computational and time cost of conventional Bayesian approaches and does not rely on acquisition constraints to define model-specific summary statistics. The obtained posterior distributions allow to highlight degeneracies present in the model definition and quantify the uncertainty and ambiguity of the estimated parameters.

View Presentation Video

Guanxiong Luo¹, Martin Heide¹, Moritz Blumenthal¹, and Martin Uecker^1,2,3,4
1University Medical Center Göttingen, Göttingen, Germany, ²Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria, ³German Centre for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany, ⁴Cluster of Excellence "Multiscale Bioimaging: from Molecular Machines to Networks of Excitable Cells'' (MBExC), University of Göttingen, Göttingen, Germany

Keywords: Machine Learning/Artificial Intelligence, Image Reconstruction

The application of generative models in MRI reconstruction is shifting researchers’ attention from the unrolled reconstruction networks to the probabilistically tractable iterations and permits an unsupervised fashion for medical image reconstruction.

View Presentation Video

Keywords: System Imperfections: Measurement & Correction, New Signal Preparation Schemes

MRI scans are commonly performed inside a fully-enclosed RF shielding room, posing stringent installation requirement and unnecessary patient discomfort. This study develops a strategy of active EMI sensing and deep learning MR signal prediction using residual U-Net for RF shielding-free MRI. We implemented it on an ultra-low-field 0.055T head MRI scanner. Our experimental results demonstrated that this strategy could directly and accurately predict EMI-free MRI signals from the signals acquired by MRI receive coil and EMI sensing coils. It worked robustly with strong and dynamically varying EMI sources, yielding significantly improved brain image quality.

View Presentation Video

Hongjun An¹, Jiye Kim¹, and Jongho Lee^1
1Seoul National University, Seoul, Korea, Republic of

Keywords: Machine Learning/Artificial Intelligence, MR Fingerprinting

View Presentation Video

Keywords: Osteoarthritis, MSK, statistical shape modeling, cartilage thickness, cartilage T2, meniscus

While the Osteoarthritis Initiative data has been explored in independent studies, to our knowledge, never has such a comprehensive analysis been completed, investigating morphology of femur, patella, tibia, menisci, for biomarkers: cartilage thickness, cartilage T2, bone shape, and meniscus shape. With 4,796 subjects from the OAI, this study utilizes an automatic statistical shape modeling technique to create a 100D interpretable space of biomarker-tissue PC modes, which can be disseminated using an innovative opensource app. In combination with Image Twin and Clinical Twin analyses, variations in morphology, as well as clinical metadata, were identified as being significantly associated with osteoarthritis incidence.