Detecting mass in mammogram is significant due to the high occurrence and mortality of breast cancer. In mammogram mass detection, modeling pairwise lesion correspondence explicitly is particularly important. However, most of the existing methods build relatively coarse correspondence and have not utilized correspondence supervision. In this paper, we propose a new transformer-based framework CL-Net to learn lesion detection and pairwise correspondence in an end-to-end manner. In CL-Net, View-Interactive Lesion Detector is proposed to achieve dynamic interaction across candidates of cross views, while Lesion Linker employs the correspondence supervision to guide the interaction process more accurately. The combination of these two designs accomplishes precise understanding of pairwise lesion correspondence for mammograms. Experiments show that CL-Net yields state-of-the-art performance on the public DDSM dataset and our in-house dataset. Moreover, it outperforms previous methods by a large margin in low FPI regime.
MammoTracker: Mask-Guided Lesion Tracking in Temporal Mammograms
Department of Electrical and Computer Engineering, Duke University, Durham, NC（电气与计算机工程系，杜克大学）；Department of Biomedical Engineering, Duke University, Durham, NC（生物医学工程系，杜克大学）；Department of Radiology, Duke University School of Medicine, Durham,NC（放射学系，杜克大学医学学院）；Departments Population Health Science and Mathematics, Duke University School of Medicine, Durham,NC（流行病学与数学系，杜克大学医学学院）
Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification
Center for Data Science, Peking University（北京大学数据科学中心）；Deepwise AI lab（Deepwise AI实验室）；Dept. of Computer Science, Peking University（北京大学计算机科学系）；Microsoft Research Asia（微软亚洲研究院）；Center on Frontiers of Computing Studies, Dept. of Computer Science, Peking University（北京大学计算机科学系前沿计算研究中心）
Semi- and Weakly-Supervised Learning for Mammogram Mass Segmentation with Limited Annotations
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Computer Science, Peking University（北京大学计算机科学学院）；School of Future Technology, Tianjin University（天津大学未来技术学院）；Research Institute, Sun Yat-sen University（中山大学研究学院）
BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations
Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；St Vincent’s Institute of Medical Research（圣文森特医学研究所）；St Vincent’s Hospital Melbourne（墨尔本圣文森特医院）；Melbourne Integrative Genomics, The University of Melbourne（墨尔本大学墨尔本整合基因组学研究所）
MammoMix: Leveraging Mixture of Experts for Robust Mammogram Breast Detection
School of Biomedical Engineering, University of Technology Sydney（悉尼科技大学生物医学工程学院）；School of Computer Science, University of Technology Sydney（悉尼科技大学计算机科学学院）；School of Electrical and Data Engineering, University of Technology Sydney（悉尼科技大学电气与数据工程学院）
MammoGANesis: Controlled Generation of High-Resolution Mammograms for Radiology Education
Faculty of Medicine, American University of Beirut（贝鲁特美国大学医学院）；American University of Beirut Medical Center（贝鲁特美国大学医学中心）；Department of Diagnostic Radiology, American University of Beirut Medical Center（贝鲁特美国大学医学中心诊断放射科）
在他们的成长期，放射学实习生被要求每月解读数百张乳房X光片，目的是能够辨别出区分良性和恶性病变的细微模式。不幸的是，医学法律和技术障碍使得难以访问和查询用于训练的医学图像。在本文中，我们训练一个生成对抗网络（GAN）来合成512 x 512的高分辨率乳房X线照片。所得到的模型导致高级别特征（例如，标准乳房X线摄影视图和乳房病变的性质）的无监督分离，在所生成的图像中具有随机变化（例如，乳房脂肪组织、钙化），从而实现合成图像的用户控制的全局和局部属性编辑。我们证明了该模型的能力，以生成解剖学和医学相关的乳房X线照片，实现了0.54的平均AUC在双盲研究中的四个专家乳房X线摄影放射科医生，以区分生成的和真实的图像，归因于高视觉质量的合成和编辑的乳房X线照片，并在推进和促进医学教育的潜在用途。
A Versatile Foundation Model for AI-enabled Mammogram Interpretation
Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre（广东省恶性肿瘤表观遗传与基因调控重点实验室，粤港澳RNA医学联合实验室，医学肿瘤科，乳腺肿瘤中心，I期临床试验中心）；Guangdong Provincial Key Laboratory of Cancer Pathogenesis and Precision Diagnosis and Treatment, AI Big Data Laboratory, Department of Medical Oncology（广东省肿瘤发生与精准诊断与治疗重点实验室，人工智能大数据实验室，医学肿瘤科）；Chongqing Key Laboratory of Bio-perception（重庆生物感知重点实验室）
Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection
Deepwise Healthcare（深睿医疗）；Peking University（北京大学）；Advanced Institute of Information Technology, Peking University（北京大学先进信息技术研究院）；The University of Hong Kong（香港大学）
Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
Center for Data Science, New York University（纽约大学数据科学中心）；Department of Radiology, New York University School of Medicine（纽约大学医学院放射科）；Perlmutter Cancer Center, NYU Langone Health（纽约大学朗格尼医学中心珀尔马特癌症中心）；Center for Advanced Imaging Innovation and Research, NYU Langone Health（纽约大学朗格尼医学中心先进成像创新与研究中心）；Department of Computer Science, Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所计算机科学系）
TransReg: Cross-transformer as auto-registration module for multi-view mammogram mass detection
VinUni-Illinois Smart Health Center, VinUniversity（VinUni-Illinois智慧健康中心，VinUniversity）；College of Engineering and Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）
MAMBO: High-Resolution Generative Approach for Mammography Images
The Institute for Artificial Intelligence Research and Development of Serbia（塞尔维亚人工智能研究与开发研究所）；University of Trento（特伦托大学）；Faculty of Technical Sciences, University of Novi Sad（诺维萨大学技术科学学院）；University of Pisa（比萨大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Verona（威尼斯大学）
Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning
Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司）；Shanghai Jiao Tong University（上海交通大学）；The University of Hong Kong（香港大学）；Yale University（耶鲁大学）；ShanghaiTech University（上海科技大学）
