Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology
University of Chicago Medical Center（芝加哥大学医学中心）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）；DV Group, LLC（DV集团有限责任公司）；University of Chicago（芝加哥大学）；Mayo Clinic（梅奥诊所）；University of Wisconsin at Madison（威斯康星大学麦迪逊分校）
James M Dolezal, Andrew Srisuwananukorn, Dmitry Karpeyev, Siddhi Ramesh, Sara Kochanny, Brittany Cody, Aaron Mansfield, Sagar Rakshit, Radhika Bansa, Melanie Bo… 展开作者
James M Dolezal, Andrew Srisuwananukorn, Dmitry Karpeyev, Siddhi Ramesh, Sara Kochanny, Brittany Cody, Aaron Mansfield, Sagar Rakshit, Radhika Bansa, Melanie Bois, Aaron O Bungum, Jefree J Schulte, Everett E Vokes, Marina Chiara Garassino, Aliya N Husain, Alexander T Pearson
A model's ability to express its own predictive uncertainty is an essential attribute for maintaining clinical user confidence as computational biomarkers are deployed into real-world medical settings. In the domain of cancer digital histopathology, we describe a novel, clinically-oriented approach to uncertainty quantification (UQ) for whole-slide images, estimating uncertainty using dropout and calculating thresholds on training data to establish cutoffs for low- and high-confidence predictions. We train models to identify lung adenocarcinoma vs. squamous cell carcinoma and show that high-confidence predictions outperform predictions without UQ, in both cross-validation and testing on two large external datasets spanning multiple institutions. Our testing strategy closely approximates real-world application, with predictions generated on unsupervised, unannotated slides using predetermined thresholds. Furthermore, we show that UQ thresholding remains reliable in the setting of domain shift, with accurate high-confidence predictions of adenocarcinoma vs. squamous cell carcinoma for out-of-distribution, non-lung cancer cohorts.
Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images
Dept. of Computer Science（计算机科学系）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；School of Information（信息学院）；Dell Children's Medical Center（德尔儿童医学中心）；Dept. of OREI（OREI部门）；University of Nevada, Reno（内华达大学里诺分校）
CoDiR: Confidence-Guided Diffusion Refinement for Semi-Supervised Histopathology Segmentation
AI VIETNAM Lab（AI VIETNAM实验室）；Portland Community College（波特兰社区学院）；University of Science, VNU-HCM（胡志明市国家大学科学大学）；Hanoi University of Science and Technology（河内科技大学）；Jeonbuk National University（全北国立大学）；Washington University School of Medicine（华盛顿大学医学院）；Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）
Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
The Pennsylvania State University（宾夕法尼亚州立大学）；Lister Hill National Center for Biomedical Communications（利斯特希尔国家生物医学通信中心）；National Library of Medicine（国家医学图书馆）；Penn State Health Milton S. Hershey Medical Center（宾夕法尼亚州立大学健康米尔顿·S·赫尔希医学中心）；Penn State College Of Medicine（宾夕法尼亚州立大学医学院）
Learning from the Right Patches: A Two-Stage Wavelet-Driven Masked Autoencoder for Histopathology Representation Learning
PLRI Medical Informatics Institute（PLRI医学信息学研究所）；CAIMed Reserch Center（CAIMed研究中心）；Hannover Medical School（汉诺威医学院）；Computer Science Institute（计算机科学研究所）；Leibniz University Hannover（莱比锡大学汉诺威分校）；Sanford Burnham Prebys Medical Discovery Institute（桑福医疗发现研究所）；Rady Children’s Institute for Genomic Medicine（拉迪儿童基因医学研究所）；University of California San Diego（加州大学圣地亚哥分校）
Retrieval-Guided Generation for Safer Histopathology Image Captioning
Kimia Lab, Department of Artificial Intelligence \& Informatics, Mayo Clinic, Rochester, MN, USA；Department of Biomedical Informatics, University of Arkansas for Medical Sciences, Little Rock, AR, USA；Lane Department of Computer Science；Electrical Engineering, West Virginia University, Morgantown, WV, USA；Department of Computer Science；Engineering, Princeton University, Princeton, NJ, USA；Department of Computer Sciences, University of Wisconsin--Madison, Madison, WI, USA
Adaptive Multi-Scale Integration Unlocks Robust Cell Annotation in Histopathology Images
Department of Computer and Information Science, University of Pennsylvania（计算机与信息科学系，宾夕法尼亚大学）；Department of Bioengineering, University of Pennsylvania（生物工程系，宾夕法尼亚大学）；Department of Pathology and Laboratory Medicine, University of Pennsylvania（病理学与实验室医学系，宾夕法尼亚大学）；Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania（生物统计学、流行病学与信息学系，宾夕法尼亚大学）
Learning latent progression states from spatial heterogeneity in uterine histopathology
Fuzhou University（福州大学）；Fuzhou University Affiliated Provincial Hospital（福州大学附属省立医院）；Interdisciplinary Institute for Medical Engineering, Fuzhou University（福州大学医学工程交叉研究院）；Medical Optical Technology R&D Center, Research Institute of Tsinghua, Pearl River Delta（清华珠三角研究院医学光学技术研发中心）；Peking University Health Science Center（北京大学医学部）；Third Hospital, School of Basic Medical Sciences, Peking University Health Science Center（北京大学医学部基础医学院第三医院）；Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院生物医药与健康工程研究院）；Tsinghua University（清华大学）；Peng Cheng Laboratory（鹏城实验室）；Jinfeng Laboratory（金凤实验室）
CentraleSupélec（巴黎中央理工-高等电力学院）；Université Paris-Saclay（巴黎萨克雷大学）；National Center for Precision Medicine in Oncology（国家肿瘤精准医学中心）；Gustave Roussy（古斯塔夫·鲁西研究所）；ETS Montreal（蒙特利尔高等技术学院）；MILA（蒙特利尔学习算法研究所）；CNRS（法国国家科学研究中心）
Addressing Uncertainty in Imbalanced Histopathology Image Classification of HER2 Breast Cancer: An interpretable Ensemble Approach with Threshold Filtered Single Instance Evaluation (SIE)
American International University-Bangladesh（孟加拉美国国际大学）；Bangladesh University of Business and Technology（孟加拉商业技术大学）；King Saud University（沙特国王大学）；Southern Illinois University（南伊利诺伊大学）
Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation
Sichuan University（四川大学）；West China Hospital, Sichuan University（四川大学华西医院）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所）
Anatomy-Informed Deep Learning and Radiomics for Automated Neurofibroma Segmentation in Whole-Body MRI
Institute for Applied Medical Informatics（应用医学信息学研究所）；Institute of Computational Neuroscience（计算神经科学研究所）；Center for Biomedical Artificial Intelligence (bAIome)（生物医学人工智能中心）；University Medical Center Hamburg-Eppendorf（汉堡埃彭多夫大学医学中心）；Department of Diagnostic and Interventional Radiology and Nuclear Medicine（诊断与介入放射学及核医学部门）；Department of Neurology（神经内科部门）
Deep learning-based survival prediction for multiple cancer types using histopathology images
Google Health（谷歌健康）；Advanced Clinical；Tempus Labs Inc（Tempus实验室公司）
诊断时的预后信息对癌症治疗和监测具有重要意义。虽然癌症分期，组织病理学评估，分子特征和临床变量可以提供有用的预后见解，改善风险分层仍然是一个活跃的研究领域。我们开发了一个深度学习系统（DLS）来预测癌症基因组图谱（TCGA）中10种癌症类型的疾病特异性生存率。我们使用了一种没有像素级注释的弱监督方法，并测试了三种不同的生存损失函数。使用来自3，664例病例的9，086张载玻片开发了DLS，并使用来自1，216例病例的3，009张载玻片进行了评价。在包括所有10种癌症的组合队列的多变量Cox回归分析中，在校正癌症类型、分期、年龄和性别后，DLS与疾病特异性生存率显著相关（风险比为1.58，95%CI 1.28-1.70，p<0.0001）。在每种癌症调整的亚组分析中，DLS仍然是10种癌症中5种癌症的生存率的重要预测因素。与包括分期、年龄和性别的基线模型相比，模型的c指数在合并队列中显示出绝对3.7%的改善（95% CI 1.0-6.5）。此外，我们的模型在各个癌症阶段对患者进行了分层，特别是II期（p=0.025）和III期（p<0.001）。通过开发和评估多种癌症类型的预后模型，这项工作是探索使用深度学习和组织病理学图像直接预测临床结果的最全面的研究之一。我们的分析表明，这种方法有可能在多种癌症类型，甚至在特定的病理阶段提供预后信息。然而，鉴于临床事件的数量相对较少，我们观察到了…
TRAPS: Treatment-Assignment Prediction via Pathway-informed Stratification
Rajshahi University of Engineering \& Technology Bangladesh；University of Dhaka Bangladesh；American International University of Bangladesh Bangladesh；Sonoma State University United States；Iowa State University United States；Rajshahi University of Engineering \& Technology；University of Dhaka；American International University of Bangladesh；Sonoma State University；Iowa State University
