Why I'm not Answering: Understanding Determinants of Classification of an Abstaining Classifier for Cancer Pathology Reports
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Louisiana Tumor Registry（路易斯安那州肿瘤登记处）；Kentucky Cancer Registry（肯塔基州癌症登记处）；Utah Cancer Registry（犹他州癌症登记处）；New Jersey State Cancer Registry（新泽西州癌症登记处）；Oak Ridge National Laboratory（橡树岭国家实验室）；Information Management Services Inc.（信息管理服务公司）；National Cancer Institute（美国国家癌症研究所）
Sayera Dhaubhadel, Jamaludin Mohd-Yusof, Kumkum Ganguly, Gopinath Chennupati, Sunil Thulasidasan, Nicolas W. Hengartner, Brent J. Mumphrey, Eric B. Durbin, Jenn… 展开作者
Sayera Dhaubhadel, Jamaludin Mohd-Yusof, Kumkum Ganguly, Gopinath Chennupati, Sunil Thulasidasan, Nicolas W. Hengartner, Brent J. Mumphrey, Eric B. Durbin, Jennifer A. Doherty, Mireille Lemieux, Noah Schaefferkoetter, Georgia Tourassi, Linda Coyle, Lynne Penberthy, Benjamin H. McMahon, Tanmoy Bhattacharya
Safe deployment of deep learning systems in critical real world applications requires models to make very few mistakes, and only under predictable circumstances. In this work, we address this problem using an abstaining classifier that is tuned to have $>$95% accuracy, and then identify the determinants of abstention using LIME. Essentially, we are training our model to learn the attributes of pathology reports that are likely to lead to incorrect classifications, albeit at the cost of reduced sensitivity. We demonstrate an abstaining classifier in a multitask setting for classifying cancer pathology reports from the NCI SEER cancer registries on six tasks of interest. For these tasks, we reduce the classification error rate by factors of 2--5 by abstaining on 25--45% of the reports. For the specific task of classifying cancer site, we are able to identify metastasis, reports involving lymph nodes, and discussion of multiple cancer sites as responsible for many of the classification mistakes, and observe that the extent and types of mistakes vary systematically with cancer site (e.g., breast, lung, and prostate). When combining across three of the tasks, our model classifies 50% of the reports with an accuracy greater than 95% for three of the six tasks\edit, and greater than 85% for all six tasks on the retained samples. Furthermore, we show that LIME provides a better determinant of classification than measures of word occurrence alone. By combining a deep abstaining classifier with feature identification using LIME, we are able to identify concepts responsible for both correctness and abstention when classifying cancer sites from pathology reports. The improvement of LIME over keyword searches is statistically significant, presumably because words are assessed in context and have been identified as a local determinant of classification.
Global explainability of a deep abstaining classifier
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；University of New Mexico（新墨西哥大学）；Oak Ridge National Laboratory（橡树岭国家实验室）；Louisiana Tumor Registry（路易斯安那肿瘤登记处）；Kentucky Cancer Registry（肯塔基癌症登记处）
Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction
Department of Medical Epidemiology and Biostatistics, Karolinska Institutet（卡罗林斯卡研究所医学流行病学与生物统计学系）；Department of Engineering Science, University of Oxford（牛津大学工程科学系）；Division of Oncology, Department of Clinical Sciences Lund, Lund University（卢德大学临床科学系肿瘤学系）；Oxford Suzhou Centre for Advanced Research, University of Oxford（牛津大学苏州先进研究中心）
Evaluating Computational Pathology Foundation Models for Prostate Cancer Grading under Distribution Shifts
Department of Medical Epidemiology and Biostatistics, Karolinska Institutet（卡罗林斯卡研究所医学流行病学与生物统计学系）；Department of Engineering Science, University of Oxford（牛津大学工程科学系）
DPSeq: A Novel and Efficient Digital Pathology Classifier for Predicting Cancer Biomarkers using Sequencer Architecture
School of Data Science, University of Science and Technology of China（中国科学技术大学数据科学学院）；School of Management, University of Science and Technology of China（中国科学技术大学管理学院）；School of Population Health, UNSW Sydney（新南威尔士大学悉尼分校人口健康学院）；Genmab Inc.（杰特贝公司）
Learning with Less Labels in Digital Pathology via Scribble Supervision from Natural Images
University of Guelph（圭尔夫大学）；Vector Institute（向量研究所）
在数字病理学（DP）领域训练深度学习模型的一个关键挑战是医学专家的高注释成本。解决这个问题的单向式方法是通过自然图像域（NI）的迁移学习，其中注释成本相当便宜。通过类标签，从NI到DP的跨域迁移学习是成功的。依赖类标签的一个潜在弱点是缺乏空间信息，空间信息可以从空间标签（如全像素分割标签和涂鸦标签）中获得。我们证明了NI域的涂鸦标签可以提高DP模型在两个癌症分类数据集（Patch Camelyon Breast Cancer和Colorectal Cancer数据集）上的性能。此外，我们表明，使用涂鸦标签训练的模型与完整的像素分割标签具有相同的性能提升，尽管收集起来更容易和更快。
Automatic Classification of Pathology Reports using TF-IDF Features
Kimia Lab, University of Waterloo（滑铁卢大学Kimia实验室）；University of Waterloo（滑铁卢大学）；Kimia Lab（Kimia实验室）；Canada（加拿大）；Kimia Lab, University of Waterloo, Canada（滑铁卢大学Kimia实验室，加拿大）
病理报告可以说是医学中最重要的文件之一，其中包含有关患者活检样本视觉发现的解释信息。每份病理学报告在患者治疗后的保存期最长可达20年。癌症登记处处理和编码大量的自由文本病理报告，用于监测世界各地的癌症和肿瘤疾病。尽管它们拥有极其宝贵的信息，但病理学报告并没有以任何系统的方式用于促进计算病理学。因此，在这项研究中，我们研究了自动化机器学习技术，以识别/预测病理报告的主要诊断（基于ICD-0代码）。我们进行了实验，从报告中提取TF-IDF特征，并使用三种不同的方法进行分类-SVM，XGBoost和Logistic回归。我们构建了一个新的数据集，其中包含1，949份病理学报告，分为37个ICD-0类别，收集自四个不同的主要部位，即肺，肾，胸腺和睾丸。这些报告在从NCI Genomic Data Commons公共数据集收集PDF文件后手动转录成文本格式。我们随后通过删除OCR软件产生的不相关文本工件来预处理报告。在TF-IDF特征向量上，XGBoost分类器的最高分类准确率为92%，线性SVM的最高分类准确率为87%。此外，研究表明，TF-IDF向量适合突出显示报告中的重要关键词，这有助于癌症研究和诊断工作流程。结果令人鼓舞地证明了机器学习方法用于病理报告分类和编码的潜力。
Machine learning-based multimodal prognostic models integrating pathology images and high-throughput omic data for overall survival prediction in cancer: a systematic review
Leeds Teaching Hospitals NHS Trust（利兹教学医院国民医疗服务信托）；University of Leeds（利兹大学）；Linköping University（林雪平大学）
Virchow: A Million-Slide Digital Pathology Foundation Model
Paige；Microsoft Research（微软研究院）；NSW Health Pathology（新南威尔士州卫生病理学）；St George Hospital（圣乔治医院）；Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）；University of Rochester（罗切斯特大学）
Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation
Imperial College London（帝国理工学院）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Latvia（拉脱维亚大学）；Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência（系统与计算机工程、技术与科学研究所）；Universidade do Porto（波尔图大学）；StratejAI（斯特拉泰人工智能公司）；Portuguese Oncology Institute of Porto (IPO Porto)（波尔图葡萄牙肿瘤研究所）；Instituto Investigación Sanitaria INCLIVA（INCLIVA卫生研究所）；Hospital Clínico Universitario de Valencia（瓦伦西亚大学临床医院）；Yale University（耶鲁大学）
Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unlabeled, unannotated pathology slides
University of Glasgow（格拉斯哥大学）；New York University School of Medicine（纽约大学医学院）；New York University Langone Health（纽约大学朗格尼医学中心）；Karolinska Institutet（卡罗林斯卡学院）；University College London Hospital（伦敦大学学院医院）
Pan-Cancer Diagnostic Consensus Through Searching Archival Histopathology Images Using Artificial Intelligence
Huron Digital Pathology（休伦数字病理学公司）；University of Waterloo（滑铁卢大学）；Vector Institute（矢量研究所）；McMaster University（麦克马斯特大学）；University of Pittsburgh Medical Center（匹兹堡大学医学中心）
LUCAID: Agentic Multimodal AI for Lung Cancer Precision Pathology
Institute of Pathology, Charité – Universitätsmedizin Berlin（柏林夏里特医学院病理学研究所）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Berlin Institute of Health at Charité – Universitätsmedizin Berlin（柏林夏里特医学院柏林卫生研究所）；Aignostics GmbH（Aignostics有限公司）；Machine Learning Group, Technical University of Berlin（柏林工业大学机器学习组）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（BIFOLD——柏林学习与数据基础研究所）；MVZ HPH Institut für Pathologie und Hämatopathologie GmbH（HPH病理及血液病理诊断中心有限公司）
Pathology-genomic fusion via biologically informed cross-modality graph learning for survival analysis
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Beijing Tiantan Hospital, Capital Medical University（首都医科大学附属北京天坛医院）；First Affiliated Hospital of Zhengzhou University（郑州大学第一附属医院）
Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary
Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；Broad Institute of Harvard and MIT（哈佛-麻省理工学院博德研究所）；Dana-Farber Cancer Institute（丹娜-法伯癌症研究所）
A comparative study of zero-shot inference with large language models and supervised modeling in breast cancer pathology classification
Bakar Computational Health Sciences Institute, University of California, San Francisco（加州大学旧金山分校巴卡尔计算健康科学研究所）；Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco（加州大学旧金山分校海伦·迪勒家族综合癌症中心）；University of California, Berkeley（加州大学伯克利分校）；Center for Data-driven Insights and Innovation, University of California, Office of the President（加州大学校长办公室数据驱动洞察与创新中心）；Department of Pediatrics, University of California, San Francisco（加州大学旧金山分校儿科系）
ConvPath: A Software Tool for Lung Adenocarcinoma Digital Pathological Image Analysis Aided by Convolutional Neural Network
University of Texas Southwestern Medical Center（德克萨斯大学西南医学中心）；National Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences（中国医学科学院国家癌症中心/肿瘤医院）；University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）
Implementing Trust in Non-Small Cell Lung Cancer Diagnosis with a Conformalized Uncertainty-Aware AI Framework in Whole-Slide Images
The Hong Kong Polytechnic University（香港理工大学）；Vanderbilt University Medical Center（范德堡大学医学中心）；Hong Kong Baptist University（香港浸会大学）；Vanderbilt University（范德堡大学）
Stanford University School of Medicine（斯坦福大学医学院）；Stanford University（斯坦福大学）；Bonn University Hospital（波恩大学医院）；Institute for Pathology and Cytology（病理与细胞学研究所）；University Hospital Muenster（明斯特大学医院）
Augmenting the Pathology Lab: An Intelligent Whole Slide Image Classification System for the Real World
Proscia Inc.（Proscia 公司）；Boonshoft School of Medicine, Wright State University School of Medicine（莱特州立大学医学院布恩肖夫特医学院）；Dermatopathology Laboratory of Central States（中部各州皮肤病理学实验室）；University of Florida College of Medicine（佛罗里达大学医学院）；Cockerell Dermatopathology（科克雷尔皮肤病理学机构）；Sidney Kimmel Medical College at Thomas Jefferson University（托马斯杰斐逊大学西德尼·金梅尔医学院）
Multimodal Whole Slide Foundation Model for Pathology
Mass General Brigham, Harvard Medical School（哈佛医学院，麻省总医院布里格姆医疗系统）；Dana-Farber Cancer Institute（丹娜法伯癌症研究院）；Broad Institute of Harvard and MIT（哈佛与麻省理工学院博德研究所）；John A. Paulson School of Engineering and Applied Sciences, Harvard University（哈佛大学约翰·A·保尔森工程与应用科学学院）；Helmholtz Munich – German Research Center for Environment and Health（亥姆霍兹慕尼黑中心——德国环境与健康研究中心）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology（麻省理工学院电气工程与计算机科学系）；Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology（麻省理工学院哈佛-麻省卫生科学与技术分部）；Department of Pathology, Pusan National University（釜山大学病理学系）；Department of Pathology and Laboratory Medicine, Emory University School of Medicine（埃默里大学医学院病理学与检验医学系）；Harvard Data Science Initiative, Harvard University（哈佛大学哈佛数据科学计划）；Department of Systems Biology, Harvard Medical School（哈佛医学院系统生物学系）；Department of Preventive Medicine, Graduate School of Medicine, The University of Tokyo（东京大学医学部预防医学系）
