The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data
School of Biomedical Engineering and Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与影像科学学院）；BioMedIA, Department of Computing, Imperial College London（帝国理工学院计算系生物医学影像与数据分析中心）；Department of Radiology, University College London（伦敦大学学院放射学系）；The Royal Brompton & Harefield NHS Foundation Trust（皇家布朗普顿和哈菲尔德英国国民保健信托基金会）；Technical University of Munich（慕尼黑工业大学）；Helmholtz Center Munich（亥姆霍兹慕尼黑中心）
Vasileios Baltatzis, Loic Le Folgoc, Sam Ellis, Octavio E. Martinez Manzanera, Kyriaki-Margarita Bintsi, Arjun Nair, Sujal Desai, Ben Glocker, Julia A. Schnabel
Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging. While most studies deploy cross-entropy as the loss function in such tasks, a growing number of approaches have turned to a family of contrastive learning-based losses. Even though performance metrics such as accuracy, sensitivity and specificity are regularly used for the evaluation of CNN classifiers, the features that these classifiers actually learn are rarely identified and their effect on the classification performance on out-of-distribution test samples is insufficiently explored. In this paper, motivated by the real-world task of lung nodule classification, we investigate the features that a CNN learns when trained and tested on different distributions of a synthetic dataset with controlled modes of variation. We show that different loss functions lead to different features being learned and consequently affect the generalization ability of the classifier on unseen data. This study provides some important insights into the design of deep learning solutions for medical imaging tasks.
Highly accurate model for prediction of lung nodule malignancy with CT scans
Arkansas State University（阿肯色州立大学）；University of Minnesota（明尼苏达大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai University of Finance and Economics（上海财经大学）；Washington University（华盛顿大学）；University of Arkansas for Medical Sciences（阿肯色大学医学科学校区）
MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan
Department of Computer Science and Engineering, Seoul National University（计算机科学与工程系，首尔国立大学）；Center for Artificial Intelligence in Medicine and Imaging, HealthHub Co. Ltd.（医学与影像人工智能中心，HealthHub公司）；Department of Electrical and Computer Engineering, The University of Alabama（电气与计算机工程系，阿拉巴马大学）；Department of Electrical Engineering, COMSATS University Islamabad（电气工程系，COMSATS大学伊斯兰堡分校）
Siamese Encoder-based Spatial-Temporal Mixer for Growth Trend Prediction of Lung Nodules on CT Scans
Harbin Institute of Technology（哈尔滨工业大学）；CVTE Research（视源股份研究院）；Southern University of Science and Technology（南方科技大学）；Guangdong University of Technology（广东工业大学）；CVTE（视源股份）
NoduLoCC2026: Lung Nodule Localization and Classification Contest from Chest X-Ray Images
Université de Haute-Alsace, IRIMAS（上阿尔萨斯大学，IRIMAS实验室）；IMT Nord Europe, Institut Mines-Télécom, Université de Lille, Center for Digital Systems（IMT北欧洲，矿业电信学院，里尔大学，数字系统中心）；Université de Rouen Normandie, ESIGELEC, IRSEEM（鲁昂诺曼底大学，ESIGELEC工程师学院，IRSEEM研究所）；Universidade Estadual de Campinas（坎皮纳斯州立大学）；Université du Québec à Chicoutimi（魁北克大学希库蒂米分校）；Università Politecnica delle Marche（马尔凯理工大学）；Université de Bejaia, Faculté des Sciences Exactes, Laboratoire d’Informatique Médicale et des Environnements Dynamiques et Intelligents (LIMED)（贝贾亚大学，精密科学学院，医学信息与动态智能环境实验室）；Université de Bretagne Occidentale（西布列塔尼大学）；University of Derby（德比大学）
Automatic Pulmonary Nodule Detection in CT Scans Using Convolutional Neural Networks Based on Maximum Intensity Projection
University of Groningen, University Medical Center Groningen（格罗宁根大学医学中心）；Tianjin Medical University Cancer Institute and Hospital（天津医科大学肿瘤医院）；University of Twente（特温特大学）
A Lung Nodule Dataset with Histopathology-based Cancer Type Annotation
School of Computer Science and Technology, Shandong University of Finance and Economics（山东财经大学计算机科学与技术学院）；School of Information Science and Technology, Linyi University（临沂大学信息科学与技术学院）；Thoracic Surgery Department of Linyi Central Hospital（临沂市中心医院胸外科）；Personnel Department of Linyi Central Hospital（临沂市中心医院人事科）
LNDb: A Lung Nodule Database on Computed Tomography
Institute for Systems and Computer Engineering, Technology and Science (INESC TEC)（系统与计算机工程、技术与科学研究所（INESC TEC））；Faculty of Engineering of the University of Porto (FEUP)（波尔图大学工程学院（FEUP））；University of Trás-os-Montes e Alto Douro (UTAD)（山后-上杜罗大学（UTAD））；Centro Hospitalar e Universitário de S. João（圣若昂大学医院中心）；Faculty of Medicine of the University of Porto (FMUP)（波尔图大学医学院（FMUP））
Gated-Dilated Networks for Lung Nodule Classification in CT scans
Monash University Malaysia（莫纳什大学马来西亚分校）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；CNRS（法国国家科学研究中心）；Singapore Eye Research Institute（新加坡眼科研究所）；University of Oklahoma（俄克拉荷马大学）
Lung nodule classification on CT scan patches using 3D convolutional neural networks
Institute for Applied System Analysis of National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”（乌克兰国立技术大学“伊戈尔·西科尔斯基基辅理工学院”应用系统分析研究所）
Full-resolution Lung Nodule Segmentation from Chest X-ray Images using Residual Encoder-Decoder Networks
University of Technology Sydney（悉尼科技大学）；IBM Australia Limited（IBM澳大利亚有限公司）；University of New England（新英格兰大学）；Universiti Kebangsaan Malaysia（马来西亚国民大学）；Charles Sturt University（查尔斯斯特大学）；Westmead Hospital（韦斯特米德医院）；Cogninet Australia（科尼尼特澳大利亚公司）；University of Southern Queensland（南昆士兰大学）；Data Science Institute, University of Technology Sydney（悉尼科技大学数据科学学院）
Interpretative Computer-aided Lung Cancer Diagnosis: from Radiology Analysis to Malignancy Evaluation
College of Physics and Information Engineering, Fuzhou University（福州大学物理与信息工程学院）；Thoracic Department, Fujian Medical University Union Hospital（福建医科大学附属协和医院胸外科）
LMLCC-Net: A Semi-Supervised Deep Learning Model for Lung Nodule Malignancy Prediction from CT Scans using a Novel Hounsfield Unit-Based Intensity Filtering
mHealth Lab, Department of Biomedical Engineering, Bangladesh University of Engineering and Technology（孟加拉国工程与技术大学生物医学工程系mHealth实验室）
A 3D Probabilistic Deep Learning System for Detection and Diagnosis of Lung Cancer Using Low-Dose CT Scans
Draper（德雷珀实验室）；Google（谷歌）
我们介绍了一种新的计算机辅助检测和诊断系统，肺癌筛查与低剂量CT扫描，产生有意义的概率评估。我们的系统完全基于3D卷积神经网络，并在公开的LUNA16和Kaggle Data Science Bowl挑战赛上实现了肺结节检测和恶性肿瘤分类任务的最新性能。虽然结节检测系统通常是自行设计和优化的，但我们发现，考虑检测和诊断组件之间的耦合是很重要的。利用这种耦合使我们能够开发一种端到端系统，该系统具有更高和更强大的性能，并消除了对结节检测假阳性减少阶段的需要。此外，我们在我们的深度学习系统中描述了模型的不确定性，这是肺部CT分析的第一个，并表明我们可以使用它来为结节检测和患者恶性肿瘤诊断提供校准良好的分类概率。这些由模型不确定性提供信息的校准概率可用于后续基于风险的诊断干预或疾病治疗决策，正如我们使用基于概率的患者转诊策略进一步改善我们的结果所证明的那样。
CAE-Transformer: Transformer-based Model to Predict Invasiveness of Lung Adenocarcinoma Subsolid Nodules from Non-thin Section 3D CT Scans
Concordia University（康考迪亚大学）；Concordia Institute for Information Systems Engineering（康考迪亚信息系统工程研究所）；Sunnybrook Health Sciences Centre（桑尼布鲁克健康科学中心）；University of Toronto（多伦多大学）
End-to-end Lung Nodule Detection in Computed Tomography
Gordon Center for Medical Imaging, Massachusetts General Hospital（麻省总医院戈登医学成像中心）；Harvard Medical School（哈佛医学院）；Beijing International Center for Mathematical Research, Peking University（北京大学北京国际数学研究中心）
High-risk Factor Prediction in Lung Cancer Using Thin CT Scans: An Attention-Enhanced Graph Convolutional Network Approach
Renmin University of China（中国人民大学）；Capital Medical University（首都医科大学）；Beijing Chao-Yang Hospital（北京朝阳医院）；Beijing Institute of Respiratory Medicine（北京呼吸疾病研究所）
Medical Artificial Intelligence for Early Detection of Lung Cancer: A Survey
College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, 610225, China（计算机科学与人工智能学院，西南民族大学）；The Australian National University, Canberra ACT 2601, Australia（澳大利亚国立大学）；School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China（计算机科学与技术学校，北京交通大学）；Hunan university of technology, Zhuzhou, 410072, China（湖南理工大学）；University of Adelaide, Adelaide, South Australia 5005, Australia（阿德莱德大学）；La Trobe University, Melbourne, Victoria 3086, Australia（拉筹伯大学）
Deep Mining Generation of Lung Cancer Malignancy Models from Chest X-ray Images
University of Technology Sydney（悉尼科技大学）；IBM Australia Limited（IBM澳大利亚有限公司）；Sejong University（世宗大学）；Universiti Kebangsaan Malaysia（马来西亚国民大学）；Charles Sturt University（查尔斯特大学）
Lung cancer screening with low-dose CT scans using a deep learning approach
Arkansas State University（阿肯色州立大学）；University of Michigan（密歇根大学）；Ann Arbor Algorithm（安阿伯算法公司）；University of Arkansas at Pine Bluff（阿肯色大学松崖分校）；University of Arkansas for Medical Sciences（阿肯色大学医学院）
Acquisition state behaves as a structured, measurable variable governing lung-nodule AI: kernel-driven measurement instability and noise-driven detection fragility, invisible to DICOM metadata
MIXCAPS: A Capsule Network-based Mixture of Experts for Lung Nodule Malignancy Prediction
Concordia Institute for Information Systems Engineering, Concordia University（康考迪亚大学信息系统工程研究所）；Sunnybrook Health Sciences Centre, University of Toronto（多伦多大学桑尼布鲁克健康科学中心）；McGill University Health Center- Research Institute（麦吉尔大学健康中心研究所）；Babak Imaging Center（巴布克影像中心）；Department of Electrical and Computer Engineering, University of Toronto（多伦多大学电气与计算机工程系）
