Purpose: AI in radiology is hindered chiefly by: 1) Requiring large annotated data sets. 2) Non-generalizability that limits deployment to new scanners / institutions. And 3) Inadequate explainability and interpretability. We believe that reinforcement learning can address all three shortcomings, with robust and intuitive algorithms trainable on small datasets. To the best of our knowledge, reinforcement learning has not been directly applied to computer vision tasks for radiological images. In this proof-of-principle work, we train a deep reinforcement learning network to predict brain tumor location.
Materials and Methods: Using the BraTS brain tumor imaging database, we trained a deep Q network on 70 post-contrast T1-weighted 2D image slices. We did so in concert with image exploration, with rewards and punishments designed to localize lesions. To compare with supervised deep learning, we trained a keypoint detection convolutional neural network on the same 70 images. We applied both approaches to a separate 30 image testing set.
Results: Reinforcement learning predictions consistently improved during training, whereas those of supervised deep learning quickly diverged. Reinforcement learning predicted testing set lesion locations with 85% accuracy, compared to roughly 7% accuracy for the supervised deep network.
Conclusion: Reinforcement learning predicted lesions with high accuracy, which is unprecedented for such a small training set. We believe that reinforcement learning can propel radiology AI well past the inherent limitations of supervised deep learning, with more clinician-driven research and finally toward true clinical applicability.
Memorial Sloan Kettering Cancer Center（纪念斯隆-凯特琳癌症中心）；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）
Purpose: Lesion segmentation in medical imaging is key to evaluating treatment response. We have recently shown that reinforcement learning can be applied to radiological images for lesion localization. Furthermore, we demonstrated that reinforcement learning addresses important limitations of supervised deep learning; namely, it can eliminate the requirement for large amounts of annotated training data and can provide valuable intuition lacking in supervised approaches. However, we did not address the fundamental task of lesion/structure-of-interest segmentation. Here we introduce a method co…
LesiOnTime -- Joint Temporal and Clinical Modeling for Small Breast Lesion Segmentation in Longitudinal DCE-MRI
Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Austria（医学影像研究实验室，生物医学影像与影像引导治疗系，维也纳医科大学）；Comprehensive Center for AI in Medicine, Medical University of Vienna, Austria（医学人工智能综合中心，维也纳医科大学）；Breast Health Center, Privatklinik Döbling, Austria（乳腺健康中心，多克林根私人诊所）；Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Austria（生物医学影像与影像引导治疗系，维也纳医科大学）；Department of Obstetrics and Gynecology, Medical University of Vienna, Austria（妇产科系，维也纳医科大学）；Department of Pathology, Medical University of Vienna, Austria（病理学系，维也纳医科大学）；Comprehensive Cancer Center, Medical University of Vienna, Austria（综合癌症中心，维也纳医科大学）
Amirkabir University of Technology (Tehran Polytechnic)（阿米尔卡比尔理工大学（德黑兰理工学院））；South Tehran Branch Islamic Azad University (IAU)（伊斯兰阿扎德大学南德黑兰分校）；Arak University of Medical Sciences（阿拉克医科大学）
Magnetic resonance images (MRI) play an important role in supporting and substituting clinical information in the diagnosis of multiple sclerosis (MS) disease by presenting lesion in brain MR images. In this paper, an algorithm for MS lesion segmentation from Brain MR Images has been presented. We revisit the modification of properties of fuzzy -c means algorithms and the canny edge detection. By changing and reformed fuzzy c-means clustering algorithms, and applying canny contraction principle, a relationship between MS lesions and edge detection is established. For the special case of FCM, w…
Dual-Encoder Transformer-Based Multimodal Learning for Ischemic Stroke Lesion Segmentation Using Diffusion MRI
Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University（麻醉学、围术期与疼痛医学系，斯坦福大学）；Department of Biomedical Sciences, Seoul National University（生物医学科学系，首尔国立大学）；Department of Computer Engineering, National University of Sciences and Technology (NUST)（计算机工程系，国立科学与技术大学（NUST））；Department of Computer Science, The University of Alabama（计算机科学系，阿拉巴马大学）；Department of Computer Science, Hanyang University（计算机科学系，翰阳大学）
Technical University of Munich（慕尼黑工业大学）；LMU Hospital Grosshadern（路德维希-马克西米利安-慕尼黑大学格罗斯哈德恩医院）
Automatic segmentation of the liver and hepatic lesions is an important step towards deriving quantitative biomarkers for accurate clinical diagnosis and computer-aided decision support systems. This paper presents a method to automatically segment liver and lesions in CT and MRI abdomen images using cascaded fully convolutional neural networks (CFCNs) enabling the segmentation of a large-scale medical trial or quantitative image analysis. We train and cascade two FCNs for a combined segmentation of the liver and its lesions. In the first step, we train a FCN to segment the liver as ROI input …
SCOPE-MRI: Bankart Lesion Detection as a Case Study in Data Curation and Deep Learning for Challenging Diagnoses
Pritzker School of Medicine, University of Chicago（芝加哥大学普ritzker医学学院）；University of Chicago（芝加哥大学）；Department of Computer Science, University of Chicago（芝加哥大学计算机科学系）；Department of Orthopaedic Surgery & Rehabilitation Medicine, UChicago Medicine（芝加哥医学中心骨科与康复医学系）
University of LAquila（拉奎拉大学）；Sapienza University of Rome（罗马第一大学）
To date, several automated strategies for identification/segmentation of Multiple Sclerosis (MS) lesions with the use of Magnetic Resonance Imaging (MRI) have been presented, but they are outperformed by human experts, from whom they act very differently. This is mainly due to: the ambiguity originated by MRI instabilities; peculiar variability of MS; non specificity of MRI regarding MS. Physicians partially manage the uncertainty generated by ambiguity relying on radiological/clinical/anatomical background and experience. To emulate human diagnosis, we present an automated framework for ident…
Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment
The University of Manchester（曼彻斯特大学）；City University of Hong Kong（香港城市大学）；The Hong Kong Polytechnic University（香港理工大学）；Institute of Automation, CAS（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Johns Hopkins University（约翰霍普金斯大学）
Comparative evaluation of training strategies using partially labelled datasets for segmentation of white matter hyperintensities and stroke lesions in FLAIR MRI
Modality-Agnostic Input Channels Enable Segmentation of Brain lesions in Multimodal MRI with Sequences Unavailable During Training
Department of Engineering Science, University of Oxford, Oxford, UK（工程科学系，牛津大学，牛津，英国）；Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK（牛津大学临床神经科学系，牛津，英国）
Universidad de Buenos Aires（布宜诺斯艾利斯大学）；CONICET（国家科学技术研究委员会）；Universidad Nacional del Litoral（滨海国立大学）
Brain lesion and anatomy segmentation in magnetic resonance images are fundamental tasks in neuroimaging research and clinical practice. Given enough training data, convolutional neuronal networks (CNN) proved to outperform all existent techniques in both tasks independently. However, to date, little work has been done regarding simultaneous learning of brain lesion and anatomy segmentation from disjoint datasets. In this work we focus on training a single CNN model to predict brain tissue and lesion segmentations using heterogeneous datasets labeled independently, according to only one of the…
BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning
University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；University of Pittsburgh（匹兹堡大学）；The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）；University of Dublin, Trinity College（都柏林大学圣三一学院）；Yale University（耶鲁大学）
Semi-Supervised Bone Marrow Lesion Detection from Knee MRI Segmentation Using Mask Inpainting Models
Gordon Center for Medical Imaging, Harvard Medical School and Massachusetts General Hospital（哈佛医学院与麻省总医院戈登医学成像中心）；Boston University（波士顿大学）；Seidenberg School of CSIS, Pace University（佩斯大学塞登伯格计算机科学与信息系统学院）；Ewha Womans University（梨花女子大学）
Imperial College London（帝国理工学院）；Cambridge University（剑桥大学）
We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation. The devised architecture is the result of an in-depth analysis of the limitations of current networks proposed for similar applications. To overcome the computational burden of processing 3D medical scans, we have devised an efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data. Further, we ana…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Chung-Ang University（中央大学）
We present a method to segment MRI scans of the human brain into ischemic stroke lesion and normal tissues. We propose a neural network architecture in the form of a standard encoder-decoder where predictions are guided by a spatial expansion embedding network. Our embedding network learns features that can resolve detailed structures in the brain without the need for high-resolution training images, which are often unavailable and expensive to acquire. Alternatively, the encoder-decoder learns global structures by means of striding and max pooling. Our embedding network complements the encode…
T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis
Department of Computer Science, Toronto Metropolitan University（计算机科学系，多伦多 Metropolitan 大学）；School of Biomedical Engineering, Western University（生物医学工程学院，西部大学）
BrainDINO: A Brain MRI Foundation Model for Generalizable Clinical Representation Learning
Department of Radiation Oncology and Winship Cancer Institute, Emory University（放射肿瘤科和Winship癌症研究所，埃默里大学）；Department of Radiation and Cellular Oncology, The University of Chicago（放射肿瘤学与细胞肿瘤学部，芝加哥大学）；Department of Electrical and Computer Engineering, Georgia Institute of Technology（电气与计算机工程系，佐治亚理工学院）；Department of Biomedical Engineering, Georgia Institute of Technology（生物医学工程系，佐治亚理工学院）；Department of Biomedical Informatics, Emory University（生物医学信息学系，埃默里大学）；Department of Medical Physics, Memorial Sloan Kettering Cancer Center（医学物理系，纪念斯隆凯特琳癌症中心）
