1
|
Hosseini MS, Bejnordi BE, Trinh VQH, Chan L, Hasan D, Li X, Yang S, Kim T, Zhang H, Wu T, Chinniah K, Maghsoudlou S, Zhang R, Zhu J, Khaki S, Buin A, Chaji F, Salehi A, Nguyen BN, Samaras D, Plataniotis KN. Computational pathology: A survey review and the way forward. J Pathol Inform 2024; 15:100357. [PMID: 38420608 PMCID: PMC10900832 DOI: 10.1016/j.jpi.2023.100357] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2023] [Revised: 12/21/2023] [Accepted: 12/23/2023] [Indexed: 03/02/2024] Open
Abstract
Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath. For updated information on this survey review paper and accessing to the original model cards repository, please refer to GitHub. Updated version of this draft can also be found from arXiv.
Collapse
Affiliation(s)
- Mahdi S Hosseini
- Department of Computer Science and Software Engineering (CSSE), Concordia Univeristy, Montreal, QC H3H 2R9, Canada
| | | | - Vincent Quoc-Huy Trinh
- Institute for Research in Immunology and Cancer of the University of Montreal, Montreal, QC H3T 1J4, Canada
| | - Lyndon Chan
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Danial Hasan
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Xingwen Li
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Stephen Yang
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Taehyo Kim
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Haochen Zhang
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Theodore Wu
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Kajanan Chinniah
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Sina Maghsoudlou
- Department of Computer Science and Software Engineering (CSSE), Concordia Univeristy, Montreal, QC H3H 2R9, Canada
| | - Ryan Zhang
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Jiadai Zhu
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Samir Khaki
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Andrei Buin
- Huron Digitial Pathology, St. Jacobs, ON N0B 2N0, Canada
| | - Fatemeh Chaji
- Department of Computer Science and Software Engineering (CSSE), Concordia Univeristy, Montreal, QC H3H 2R9, Canada
| | - Ala Salehi
- Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada
| | - Bich Ngoc Nguyen
- University of Montreal Hospital Center, Montreal, QC H2X 0C2, Canada
| | - Dimitris Samaras
- Department of Computer Science, Stony Brook University, Stony Brook, NY 11794, United States
| | - Konstantinos N Plataniotis
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| |
Collapse
|
2
|
Qasim AB, Motta A, Studier-Fischer A, Sellner J, Ayala L, Hübner M, Bressan M, Özdemir B, Kowalewski KF, Nickel F, Seidlitz S, Maier-Hein L. Test-time augmentation with synthetic data addresses distribution shifts in spectral imaging. Int J Comput Assist Radiol Surg 2024; 19:1021-1031. [PMID: 38483702 PMCID: PMC11178652 DOI: 10.1007/s11548-024-03085-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2024] [Accepted: 02/22/2024] [Indexed: 06/15/2024]
Abstract
PURPOSE Surgical scene segmentation is crucial for providing context-aware surgical assistance. Recent studies highlight the significant advantages of hyperspectral imaging (HSI) over traditional RGB data in enhancing segmentation performance. Nevertheless, the current hyperspectral imaging (HSI) datasets remain limited and do not capture the full range of tissue variations encountered clinically. METHODS Based on a total of 615 hyperspectral images from a total of 16 pigs, featuring porcine organs in different perfusion states, we carry out an exploration of distribution shifts in spectral imaging caused by perfusion alterations. We further introduce a novel strategy to mitigate such distribution shifts, utilizing synthetic data for test-time augmentation. RESULTS The effect of perfusion changes on state-of-the-art (SOA) segmentation networks depended on the organ and the specific perfusion alteration induced. In the case of the kidney, we observed a performance decline of up to 93% when applying a state-of-the-art (SOA) network under ischemic conditions. Our method improved on the state-of-the-art (SOA) by up to 4.6 times. CONCLUSION Given its potential wide-ranging relevance to diverse pathologies, our approach may serve as a pivotal tool to enhance neural network generalization within the realm of spectral imaging.
Collapse
Affiliation(s)
- Ahmad Bin Qasim
- Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany.
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany.
| | - Alessandro Motta
- Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Alexander Studier-Fischer
- Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany
| | - Jan Sellner
- Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany
- Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
- National Center for Tumor Diseases (NCT), NCT Heidelberg, A Partnership between DKFZ and University Medical Center Heidelberg, Heidelberg, Germany
| | - Leonardo Ayala
- Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Marco Hübner
- Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
| | - Marc Bressan
- Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany
| | - Berkin Özdemir
- Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany
| | - Karl Friedrich Kowalewski
- Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany
- Department of Urology, University Medical Center Mannheim, Heidelberg University, Mannheim, Germany
| | - Felix Nickel
- Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany
- Medical Faculty, Heidelberg University, Heidelberg, Germany
| | - Silvia Seidlitz
- Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany
- Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
- National Center for Tumor Diseases (NCT), NCT Heidelberg, A Partnership between DKFZ and University Medical Center Heidelberg, Heidelberg, Germany
| | - Lena Maier-Hein
- Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany
- Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
- National Center for Tumor Diseases (NCT), NCT Heidelberg, A Partnership between DKFZ and University Medical Center Heidelberg, Heidelberg, Germany
- Medical Faculty, Heidelberg University, Heidelberg, Germany
| |
Collapse
|
3
|
Carini C, Seyhan AA. Tribulations and future opportunities for artificial intelligence in precision medicine. J Transl Med 2024; 22:411. [PMID: 38702711 PMCID: PMC11069149 DOI: 10.1186/s12967-024-05067-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2024] [Accepted: 03/05/2024] [Indexed: 05/06/2024] Open
Abstract
Upon a diagnosis, the clinical team faces two main questions: what treatment, and at what dose? Clinical trials' results provide the basis for guidance and support for official protocols that clinicians use to base their decisions. However, individuals do not consistently demonstrate the reported response from relevant clinical trials. The decision complexity increases with combination treatments where drugs administered together can interact with each other, which is often the case. Additionally, the individual's response to the treatment varies with the changes in their condition. In practice, the drug and the dose selection depend significantly on the medical protocol and the medical team's experience. As such, the results are inherently varied and often suboptimal. Big data and Artificial Intelligence (AI) approaches have emerged as excellent decision-making tools, but multiple challenges limit their application. AI is a rapidly evolving and dynamic field with the potential to revolutionize various aspects of human life. AI has become increasingly crucial in drug discovery and development. AI enhances decision-making across different disciplines, such as medicinal chemistry, molecular and cell biology, pharmacology, pathology, and clinical practice. In addition to these, AI contributes to patient population selection and stratification. The need for AI in healthcare is evident as it aids in enhancing data accuracy and ensuring the quality care necessary for effective patient treatment. AI is pivotal in improving success rates in clinical practice. The increasing significance of AI in drug discovery, development, and clinical trials is underscored by many scientific publications. Despite the numerous advantages of AI, such as enhancing and advancing Precision Medicine (PM) and remote patient monitoring, unlocking its full potential in healthcare requires addressing fundamental concerns. These concerns include data quality, the lack of well-annotated large datasets, data privacy and safety issues, biases in AI algorithms, legal and ethical challenges, and obstacles related to cost and implementation. Nevertheless, integrating AI in clinical medicine will improve diagnostic accuracy and treatment outcomes, contribute to more efficient healthcare delivery, reduce costs, and facilitate better patient experiences, making healthcare more sustainable. This article reviews AI applications in drug development and clinical practice, making healthcare more sustainable, and highlights concerns and limitations in applying AI.
Collapse
Affiliation(s)
- Claudio Carini
- School of Cancer and Pharmaceutical Sciences, Faculty of Life Sciences and Medicine, New Hunt's House, King's College London, Guy's Campus, London, UK.
- Biomarkers Consortium, Foundation of the National Institute of Health, Bethesda, MD, USA.
| | - Attila A Seyhan
- Laboratory of Translational Oncology and Experimental Cancer Therapeutics, Warren Alpert Medical School, Brown University, Providence, RI, USA.
- Department of Pathology and Laboratory Medicine, Warren Alpert Medical School, Brown University, Providence, RI, USA.
- Joint Program in Cancer Biology, Lifespan Health System and Brown University, Providence, RI, USA.
- Legorreta Cancer Center at Brown University, Providence, RI, USA.
| |
Collapse
|
4
|
Wagner SJ, Matek C, Shetab Boushehri S, Boxberg M, Lamm L, Sadafi A, Winter DJE, Marr C, Peng T. Built to Last? Reproducibility and Reusability of Deep Learning Algorithms in Computational Pathology. Mod Pathol 2024; 37:100350. [PMID: 37827448 DOI: 10.1016/j.modpat.2023.100350] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Revised: 10/02/2023] [Accepted: 10/03/2023] [Indexed: 10/14/2023]
Abstract
Recent progress in computational pathology has been driven by deep learning. While code and data availability are essential to reproduce findings from preceding publications, ensuring a deep learning model's reusability is more challenging. For that, the codebase should be well-documented and easy to integrate into existing workflows and models should be robust toward noise and generalizable toward data from different sources. Strikingly, only a few computational pathology algorithms have been reused by other researchers so far, let alone employed in a clinical setting. To assess the current state of reproducibility and reusability of computational pathology algorithms, we evaluated peer-reviewed articles available in PubMed, published between January 2019 and March 2021, in 5 use cases: stain normalization; tissue type segmentation; evaluation of cell-level features; genetic alteration prediction; and inference of grading, staging, and prognostic information. We compiled criteria for data and code availability and statistical result analysis and assessed them in 160 publications. We found that only one-quarter (41 of 160 publications) made code publicly available. Among these 41 studies, three-quarters (30 of 41) analyzed their results statistically, half of them (20 of 41) released their trained model weights, and approximately a third (16 of 41) used an independent cohort for evaluation. Our review is intended for both pathologists interested in deep learning and researchers applying algorithms to computational pathology challenges. We provide a detailed overview of publications with published code in the field, list reusable data handling tools, and provide criteria for reproducibility and reusability.
Collapse
Affiliation(s)
- Sophia J Wagner
- Helmholtz AI, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; School of Computation, Information and Technology, Technical University of Munich, Garching, Germany
| | - Christian Matek
- Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; Institute of Pathology, University Hospital Erlangen, Erlangen, Germany
| | - Sayedali Shetab Boushehri
- School of Computation, Information and Technology, Technical University of Munich, Garching, Germany; Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; Data & Analytics (D&A), Roche Pharma Research and Early Development (pRED), Roche Innovation Center Munich, Germany
| | - Melanie Boxberg
- Institute of Pathology, Technical University Munich, Munich, Germany; Institute of Pathology Munich-North, Munich, Germany
| | - Lorenz Lamm
- Helmholtz AI, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; Helmholtz Pioneer Campus, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany
| | - Ario Sadafi
- School of Computation, Information and Technology, Technical University of Munich, Garching, Germany; Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany
| | - Dominik J E Winter
- Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; School of Life Sciences, Technical University of Munich, Weihenstephan, Germany
| | - Carsten Marr
- Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany.
| | - Tingying Peng
- Helmholtz AI, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany.
| |
Collapse
|
5
|
Pati P, Jaume G, Ayadi Z, Thandiackal K, Bozorgtabar B, Gabrani M, Goksel O. Weakly supervised joint whole-slide segmentation and classification in prostate cancer. Med Image Anal 2023; 89:102915. [PMID: 37633177 DOI: 10.1016/j.media.2023.102915] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Revised: 05/17/2023] [Accepted: 07/25/2023] [Indexed: 08/28/2023]
Abstract
The identification and segmentation of histological regions of interest can provide significant support to pathologists in their diagnostic tasks. However, segmentation methods are constrained by the difficulty in obtaining pixel-level annotations, which are tedious and expensive to collect for whole-slide images (WSI). Though several methods have been developed to exploit image-level weak-supervision for WSI classification, the task of segmentation using WSI-level labels has received very little attention. The research in this direction typically require additional supervision beyond image labels, which are difficult to obtain in real-world practice. In this study, we propose WholeSIGHT, a weakly-supervised method that can simultaneously segment and classify WSIs of arbitrary shapes and sizes. Formally, WholeSIGHT first constructs a tissue-graph representation of WSI, where the nodes and edges depict tissue regions and their interactions, respectively. During training, a graph classification head classifies the WSI and produces node-level pseudo-labels via post-hoc feature attribution. These pseudo-labels are then used to train a node classification head for WSI segmentation. During testing, both heads simultaneously render segmentation and class prediction for an input WSI. We evaluate the performance of WholeSIGHT on three public prostate cancer WSI datasets. Our method achieves state-of-the-art weakly-supervised segmentation performance on all datasets while resulting in better or comparable classification with respect to state-of-the-art weakly-supervised WSI classification methods. Additionally, we assess the generalization capability of our method in terms of segmentation and classification performance, uncertainty estimation, and model calibration. Our code is available at: https://github.com/histocartography/wholesight.
Collapse
Affiliation(s)
| | - Guillaume Jaume
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA, USA; Data Science Program, Dana-Farber/Harvard Cancer Center, Boston, MA, USA
| | - Zeineb Ayadi
- IBM Research Europe, Zurich, Switzerland; EPFL, Lausanne, Switzerland
| | - Kevin Thandiackal
- IBM Research Europe, Zurich, Switzerland; Computer-Assisted Applications in Medicine, ETH Zurich, Zurich, Switzerland
| | | | | | - Orcun Goksel
- Computer-Assisted Applications in Medicine, ETH Zurich, Zurich, Switzerland; Department of Information Technology, Uppsala University, Sweden
| |
Collapse
|
6
|
Lin T, Yu Z, Xu Z, Hu H, Xu Y, Chen CW. SGCL: Spatial guided contrastive learning on whole-slide pathological images. Med Image Anal 2023; 89:102845. [PMID: 37597317 DOI: 10.1016/j.media.2023.102845] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2022] [Revised: 05/09/2023] [Accepted: 05/15/2023] [Indexed: 08/21/2023]
Abstract
Self-supervised representation learning (SSL) has achieved remarkable success in its application to natural images while falling behind in performance when applied to whole-slide pathological images (WSIs). This is because the inherent characteristics of WSIs in terms of gigapixel resolution and multiple objects in training patches are fundamentally different from natural images. Directly transferring the state-of-the-art (SOTA) SSL methods designed for natural images to WSIs will inevitably compromise their performance. We present a novel scheme SGCL: Spatial Guided Contrastive Learning, to fully explore the inherent properties of WSIs, leveraging the spatial proximity and multi-object priors for stable self-supervision. Beyond the self-invariance of instance discrimination, we expand and propagate the spatial proximity for the intra-invariance from the same WSI and inter-invariance from different WSIs, as well as propose the spatial-guided multi-cropping for inner-invariance within patches. To adaptively explore such spatial information without supervision, we propose a new loss function and conduct a theoretical analysis to validate it. This novel scheme of SGCL is able to achieve additional improvements over the SOTA pre-training methods on diverse downstream tasks across multiple datasets. Extensive ablation studies have been carried out and visualizations of these results have been presented to aid understanding of the proposed SGCL scheme. As open science, all codes and pre-trained models are available at https://github.com/HHHedo/SGCL.
Collapse
Affiliation(s)
- Tiancheng Lin
- Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China
| | - Zhimiao Yu
- Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China
| | - Zengchao Xu
- Department of Mathematics and Lab for Educational Big Data and Policymaking, Shanghai Normal University, China
| | - Hongyu Hu
- Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China
| | - Yi Xu
- Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China.
| | | |
Collapse
|
7
|
Zheng T, Chen W, Li S, Quan H, Zou M, Zheng S, Zhao Y, Gao X, Cui X. Learning how to detect: A deep reinforcement learning method for whole-slide melanoma histopathology images. Comput Med Imaging Graph 2023; 108:102275. [PMID: 37567046 DOI: 10.1016/j.compmedimag.2023.102275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2023] [Revised: 07/18/2023] [Accepted: 07/22/2023] [Indexed: 08/13/2023]
Abstract
Cutaneous melanoma represents one of the most life-threatening malignancies. Histopathological image analysis serves as a vital tool for early melanoma detection. Deep neural network (DNN) models are frequently employed to aid pathologists in enhancing the efficiency and accuracy of diagnoses. However, due to the paucity of well-annotated, high-resolution, whole-slide histopathology image (WSI) datasets, WSIs are typically fragmented into numerous patches during the model training and testing stages. This process disregards the inherent interconnectedness among patches, potentially impeding the models' performance. Additionally, the presence of excess, non-contributing patches extends processing times and introduces substantial computational burdens. To mitigate these issues, we draw inspiration from the clinical decision-making processes of dermatopathologists to propose an innovative, weakly supervised deep reinforcement learning framework, titled Fast medical decision-making in melanoma histopathology images (FastMDP-RL). This framework expedites model inference by reducing the number of irrelevant patches identified within WSIs. FastMDP-RL integrates two DNN-based agents: the search agent (SeAgent) and the decision agent (DeAgent). The SeAgent initiates actions, steered by the image features observed in the current viewing field at various magnifications. Simultaneously, the DeAgent provides labeling probabilities for each patch. We utilize multi-instance learning (MIL) to construct a teacher-guided model (MILTG), serving a dual purpose: rewarding the SeAgent and guiding the DeAgent. Our evaluations were conducted using two melanoma datasets: the publicly accessible TCIA-CM dataset and the proprietary MELSC dataset. Our experimental findings affirm FastMDP-RL's ability to expedite inference and accurately predict WSIs, even in the absence of pixel-level annotations. Moreover, our research investigates the WSI-based interactive environment, encompassing the design of agents, state and reward functions, and feature extractors suitable for melanoma tissue images. This investigation offers valuable insights and references for researchers engaged in related studies. The code is available at: https://github.com/titizheng/FastMDP-RL.
Collapse
Affiliation(s)
- Tingting Zheng
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Weixing Chen
- Shenzhen College of Advanced Technology, University of the Chinese Academy of Sciences, Beijing, China
| | - Shuqin Li
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Hao Quan
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Mingchen Zou
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Song Zheng
- National and Local Joint Engineering Research Center of Immunodermatological Theranostics, Department of Dermatology, The First Hospital of China Medical University, Shenyang, China
| | - Yue Zhao
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; National and Local Joint Engineering Research Center of Immunodermatological Theranostics, Department of Dermatology, The First Hospital of China Medical University, Shenyang, China
| | - Xinghua Gao
- National and Local Joint Engineering Research Center of Immunodermatological Theranostics, Department of Dermatology, The First Hospital of China Medical University, Shenyang, China
| | - Xiaoyu Cui
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
| |
Collapse
|
8
|
Reis-Filho JS, Kather JN. Overcoming the challenges to implementation of artificial intelligence in pathology. J Natl Cancer Inst 2023; 115:608-612. [PMID: 36929936 PMCID: PMC10248832 DOI: 10.1093/jnci/djad048] [Citation(s) in RCA: 16] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 03/02/2023] [Accepted: 03/11/2023] [Indexed: 03/18/2023] Open
Abstract
Pathologists worldwide are facing remarkable challenges with increasing workloads and lack of time to provide consistently high-quality patient care. The application of artificial intelligence (AI) to digital whole-slide images has the potential of democratizing the access to expert pathology and affordable biomarkers by supporting pathologists in the provision of timely and accurate diagnosis as well as supporting oncologists by directly extracting prognostic and predictive biomarkers from tissue slides. The long-awaited adoption of AI in pathology, however, has not materialized, and the transformation of pathology is happening at a much slower pace than that observed in other fields (eg, radiology). Here, we provide a critical summary of the developments in digital and computational pathology in the last 10 years, outline key hurdles and ways to overcome them, and provide a perspective for AI-supported precision oncology in the future.
Collapse
Affiliation(s)
- Jorge S Reis-Filho
- Experimental Pathology, Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Jakob Nikolas Kather
- Department of Medicine I, University Hospital and Faculty of Medicine, Technical University Dresden, Dresden, Germany
- Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany
- Pathology and Data Analytics, Leeds Institute of Medical Research at St James’s, University of Leeds, Leeds, UK
| |
Collapse
|
9
|
Alam MN, Yamashita R, Ramesh V, Prabhune T, Lim JI, Chan RVP, Hallak J, Leng T, Rubin D. Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models. Sci Rep 2023; 13:6047. [PMID: 37055475 PMCID: PMC10102012 DOI: 10.1038/s41598-023-33365-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Accepted: 04/12/2023] [Indexed: 04/15/2023] Open
Abstract
Diabetic retinopathy (DR) is a major cause of vision impairment in diabetic patients worldwide. Due to its prevalence, early clinical diagnosis is essential to improve treatment management of DR patients. Despite recent demonstration of successful machine learning (ML) models for automated DR detection, there is a significant clinical need for robust models that can be trained with smaller cohorts of dataset and still perform with high diagnostic accuracy in independent clinical datasets (i.e., high model generalizability). Towards this need, we have developed a self-supervised contrastive learning (CL) based pipeline for classification of referable vs non-referable DR. Self-supervised CL based pretraining allows enhanced data representation, therefore, the development of robust and generalized deep learning (DL) models, even with small, labeled datasets. We have integrated a neural style transfer (NST) augmentation in the CL pipeline to produce models with better representations and initializations for the detection of DR in color fundus images. We compare our CL pretrained model performance with two state of the art baseline models pretrained with Imagenet weights. We further investigate the model performance with reduced labeled training data (down to 10 percent) to test the robustness of the model when trained with small, labeled datasets. The model is trained and validated on the EyePACS dataset and tested independently on clinical datasets from the University of Illinois, Chicago (UIC). Compared to baseline models, our CL pretrained FundusNet model had higher area under the receiver operating characteristics (ROC) curve (AUC) (CI) values (0.91 (0.898 to 0.930) vs 0.80 (0.783 to 0.820) and 0.83 (0.801 to 0.853) on UIC data). At 10 percent labeled training data, the FundusNet AUC was 0.81 (0.78 to 0.84) vs 0.58 (0.56 to 0.64) and 0.63 (0.60 to 0.66) in baseline models, when tested on the UIC dataset. CL based pretraining with NST significantly improves DL classification performance, helps the model generalize well (transferable from EyePACS to UIC data), and allows training with small, annotated datasets, therefore reducing ground truth annotation burden of the clinicians.
Collapse
Affiliation(s)
- Minhaj Nur Alam
- Department of Biomedical Data Science, Stanford University School of Medicine, 1265 Welch Road, Stanford, CA, 94305, USA.
- Department of Electrical and Computer Engineering, University of North Carolina at Charlotte, 9201 University City Boulevard, Charlotte, NC, 28223, USA.
- Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL, 60612, USA.
| | - Rikiya Yamashita
- Department of Biomedical Data Science, Stanford University School of Medicine, 1265 Welch Road, Stanford, CA, 94305, USA
| | - Vignav Ramesh
- Department of Biomedical Data Science, Stanford University School of Medicine, 1265 Welch Road, Stanford, CA, 94305, USA
| | - Tejas Prabhune
- Department of Biomedical Data Science, Stanford University School of Medicine, 1265 Welch Road, Stanford, CA, 94305, USA
| | - Jennifer I Lim
- Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL, 60612, USA
| | - R V P Chan
- Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL, 60612, USA
| | - Joelle Hallak
- Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL, 60612, USA
| | - Theodore Leng
- Department of Ophthalmology, Stanford University School of Medicine, Stanford, CA, 94305, USA
| | - Daniel Rubin
- Department of Biomedical Data Science, Stanford University School of Medicine, 1265 Welch Road, Stanford, CA, 94305, USA
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, 94305, USA
| |
Collapse
|
10
|
Ghaffari Laleh N, Ligero M, Perez-Lopez R, Kather JN. Facts and Hopes on the Use of Artificial Intelligence for Predictive Immunotherapy Biomarkers in Cancer. Clin Cancer Res 2023; 29:316-323. [PMID: 36083132 DOI: 10.1158/1078-0432.ccr-22-0390] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Revised: 07/26/2022] [Accepted: 08/29/2022] [Indexed: 01/19/2023]
Abstract
Immunotherapy by immune checkpoint inhibitors has become a standard treatment strategy for many types of solid tumors. However, the majority of patients with cancer will not respond, and predicting response to this therapy is still a challenge. Artificial intelligence (AI) methods can extract meaningful information from complex data, such as image data. In clinical routine, radiology or histopathology images are ubiquitously available. AI has been used to predict the response to immunotherapy from radiology or histopathology images, either directly or indirectly via surrogate markers. While none of these methods are currently used in clinical routine, academic and commercial developments are pointing toward potential clinical adoption in the near future. Here, we summarize the state of the art in AI-based image biomarkers for immunotherapy response based on radiology and histopathology images. We point out limitations, caveats, and pitfalls, including biases, generalizability, and explainability, which are relevant for researchers and health care providers alike, and outline key clinical use cases of this new class of predictive biomarkers.
Collapse
Affiliation(s)
| | - Marta Ligero
- Radiomics Group, Vall d'Hebron Institute of Oncology, Vall d'Hebron Barcelona Hospital Campus, Barcelona, Spain
| | - Raquel Perez-Lopez
- Radiomics Group, Vall d'Hebron Institute of Oncology, Vall d'Hebron Barcelona Hospital Campus, Barcelona, Spain.,Department of Radiology, Vall d'Hebron University Hospital, Barcelona, Spain
| | - Jakob Nikolas Kather
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany.,Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, United Kingdom.,Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.,Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany
| |
Collapse
|
11
|
Couture HD. Deep Learning-Based Prediction of Molecular Tumor Biomarkers from H&E: A Practical Review. J Pers Med 2022; 12:2022. [PMID: 36556243 PMCID: PMC9784641 DOI: 10.3390/jpm12122022] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2022] [Revised: 10/26/2022] [Accepted: 12/05/2022] [Indexed: 12/12/2022] Open
Abstract
Molecular and genomic properties are critical in selecting cancer treatments to target individual tumors, particularly for immunotherapy. However, the methods to assess such properties are expensive, time-consuming, and often not routinely performed. Applying machine learning to H&E images can provide a more cost-effective screening method. Dozens of studies over the last few years have demonstrated that a variety of molecular biomarkers can be predicted from H&E alone using the advancements of deep learning: molecular alterations, genomic subtypes, protein biomarkers, and even the presence of viruses. This article reviews the diverse applications across cancer types and the methodology to train and validate these models on whole slide images. From bottom-up to pathologist-driven to hybrid approaches, the leading trends include a variety of weakly supervised deep learning-based approaches, as well as mechanisms for training strongly supervised models in select situations. While results of these algorithms look promising, some challenges still persist, including small training sets, rigorous validation, and model explainability. Biomarker prediction models may yield a screening method to determine when to run molecular tests or an alternative when molecular tests are not possible. They also create new opportunities in quantifying intratumoral heterogeneity and predicting patient outcomes.
Collapse
|
12
|
Area under the curve may hide poor generalisation to external datasets. ESMO Open 2022; 7:100429. [PMID: 35397433 PMCID: PMC9006654 DOI: 10.1016/j.esmoop.2022.100429] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Accepted: 02/10/2022] [Indexed: 11/23/2022] Open
|
13
|
Echle A, Ghaffari Laleh N, Quirke P, Grabsch HI, Muti HS, Saldanha OL, Brockmoeller SF, van den Brandt PA, Hutchins GGA, Richman SD, Horisberger K, Galata C, Ebert MP, Eckardt M, Boutros M, Horst D, Reissfelder C, Alwers E, Brinker TJ, Langer R, Jenniskens JCA, Offermans K, Mueller W, Gray R, Gruber SB, Greenson JK, Rennert G, Bonner JD, Schmolze D, Chang-Claude J, Brenner H, Trautwein C, Boor P, Jaeger D, Gaisa NT, Hoffmeister M, West NP, Kather JN. Artificial intelligence for detection of microsatellite instability in colorectal cancer-a multicentric analysis of a pre-screening tool for clinical application. ESMO Open 2022; 7:100400. [PMID: 35247870 PMCID: PMC9058894 DOI: 10.1016/j.esmoop.2022.100400] [Citation(s) in RCA: 49] [Impact Index Per Article: 24.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2021] [Revised: 01/18/2022] [Accepted: 01/21/2022] [Indexed: 12/27/2022] Open
Abstract
BACKGROUND Microsatellite instability (MSI)/mismatch repair deficiency (dMMR) is a key genetic feature which should be tested in every patient with colorectal cancer (CRC) according to medical guidelines. Artificial intelligence (AI) methods can detect MSI/dMMR directly in routine pathology slides, but the test performance has not been systematically investigated with predefined test thresholds. METHOD We trained and validated AI-based MSI/dMMR detectors and evaluated predefined performance metrics using nine patient cohorts of 8343 patients across different countries and ethnicities. RESULTS Classifiers achieved clinical-grade performance, yielding an area under the receiver operating curve (AUROC) of up to 0.96 without using any manual annotations. Subsequently, we show that the AI system can be applied as a rule-out test: by using cohort-specific thresholds, on average 52.73% of tumors in each surgical cohort [total number of MSI/dMMR = 1020, microsatellite stable (MSS)/ proficient mismatch repair (pMMR) = 7323 patients] could be identified as MSS/pMMR with a fixed sensitivity at 95%. In an additional cohort of N = 1530 (MSI/dMMR = 211, MSS/pMMR = 1319) endoscopy biopsy samples, the system achieved an AUROC of 0.89, and the cohort-specific threshold ruled out 44.12% of tumors with a fixed sensitivity at 95%. As a more robust alternative to cohort-specific thresholds, we showed that with a fixed threshold of 0.25 for all the cohorts, we can rule-out 25.51% in surgical specimens and 6.10% in biopsies. INTERPRETATION When applied in a clinical setting, this means that the AI system can rule out MSI/dMMR in a quarter (with global thresholds) or half of all CRC patients (with local fine-tuning), thereby reducing cost and turnaround time for molecular profiling.
Collapse
Affiliation(s)
- A Echle
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - N Ghaffari Laleh
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - P Quirke
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - H I Grabsch
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK; Department of Pathology, GROW School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, The Netherlands
| | - H S Muti
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - O L Saldanha
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - S F Brockmoeller
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - P A van den Brandt
- Department of Epidemiology, Maastricht University Medical Center+, Maastricht, The Netherlands
| | - G G A Hutchins
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - S D Richman
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - K Horisberger
- Department of Abdominal and Transplantation Surgery, University Hospital of Zurich, Zurich, Switzerland
| | - C Galata
- Department of Surgery, Universitätsmedizin Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; Division of Thoracic Surgery, Academic Thoracic Center Mainz, University Medical Center Mainz, Johannes Gutenberg University Mainz, Mainz, Germany
| | - M P Ebert
- Department of Medicine II, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; Mannheim Institute for Innate Immunoscience (MI3) and Clinical Cooperation Unit Healthy Metabolism, Center of Preventive Medicine and Digital Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; Mannheim Cancer Center, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - M Eckardt
- Department of Medicine II, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - M Boutros
- Division of Signaling and Functional Genomics, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - D Horst
- Institut für Pathologie Charité, Berlin, Germany
| | - C Reissfelder
- Department of Surgery, Universitätsmedizin Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - E Alwers
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center, Heidelberg, Germany
| | - T J Brinker
- Digital Biomarkers for Oncology Group, National Center for Tumor Diseases (NCT), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - R Langer
- Institute of Pathology, Inselspital, University of Bern, Bern, Switzerland
| | - J C A Jenniskens
- Department of Epidemiology, Maastricht University Medical Center+, Maastricht, The Netherlands
| | - K Offermans
- Department of Epidemiology, Maastricht University Medical Center+, Maastricht, The Netherlands
| | - W Mueller
- Gemeinschaftspraxis Pathologie, Starnberg, Germany
| | - R Gray
- Clinical Trial Service Unit, University of Oxford, Oxford, UK
| | - S B Gruber
- Center for Precision Medicine and Department of Medical Oncology, City of Hope National Medical Center, Duarte, USA
| | - J K Greenson
- Department of Pathology, City of Hope Comprehensive Cancer Center, Duarte, USA
| | - G Rennert
- Department of Community Medicine & Epidemiology, Lady Davis Carmel Medical Center, Ruth & Bruce Rappaport Faculty of Medicine, Technion-Israel Institute of Technology, Haifa, Israel; Steve and Cindy Rasmussen Institute for Genomic Medicine, Lady Davis Carmel Medical Center and Technion Faculty of Medicine, Clalit National Cancer Control Center, Haifa, Israel
| | - J D Bonner
- Center for Precision Medicine and Department of Medical Oncology, City of Hope National Medical Center, Duarte, USA
| | - D Schmolze
- Department of Pathology, City of Hope Comprehensive Cancer Center, Duarte, USA
| | - J Chang-Claude
- Division of Cancer Epidemiology, German Cancer Research Center (DKFZ), Heidelberg, Germany; Cancer Epidemiology Group, University Cancer Center Hamburg, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - H Brenner
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center, Heidelberg, Germany; Division of Preventive Oncology, German Cancer Research Center (DKFZ) and National Center for Tumor Diseases (NCT), Heidelberg, Germany; German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - C Trautwein
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - P Boor
- Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany; Department of Nephrology and Immunology, University Hospital RWTH Aachen, Aachen, Germany
| | - D Jaeger
- Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany
| | - N T Gaisa
- Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany
| | - M Hoffmeister
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center, Heidelberg, Germany
| | - N P West
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - J N Kather
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany; Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK; Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.
| |
Collapse
|
14
|
Muti HS, Heij LR, Keller G, Kohlruss M, Langer R, Dislich B, Cheong JH, Kim YW, Kim H, Kook MC, Cunningham D, Allum WH, Langley RE, Nankivell MG, Quirke P, Hayden JD, West NP, Irvine AJ, Yoshikawa T, Oshima T, Huss R, Grosser B, Roviello F, d'Ignazio A, Quaas A, Alakus H, Tan X, Pearson AT, Luedde T, Ebert MP, Jäger D, Trautwein C, Gaisa NT, Grabsch HI, Kather JN. Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: a retrospective multicentre cohort study. Lancet Digit Health 2021; 3:e654-e664. [PMID: 34417147 PMCID: PMC8460994 DOI: 10.1016/s2589-7500(21)00133-3] [Citation(s) in RCA: 56] [Impact Index Per Article: 18.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2021] [Revised: 05/20/2021] [Accepted: 06/16/2021] [Indexed: 02/07/2023]
Abstract
BACKGROUND Response to immunotherapy in gastric cancer is associated with microsatellite instability (or mismatch repair deficiency) and Epstein-Barr virus (EBV) positivity. We therefore aimed to develop and validate deep learning-based classifiers to detect microsatellite instability and EBV status from routine histology slides. METHODS In this retrospective, multicentre study, we collected tissue samples from ten cohorts of patients with gastric cancer from seven countries (South Korea, Switzerland, Japan, Italy, Germany, the UK and the USA). We trained a deep learning-based classifier to detect microsatellite instability and EBV positivity from digitised, haematoxylin and eosin stained resection slides without annotating tumour containing regions. The performance of the classifier was assessed by within-cohort cross-validation in all ten cohorts and by external validation, for which we split the cohorts into a five-cohort training dataset and a five-cohort test dataset. We measured the area under the receiver operating curve (AUROC) for detection of microsatellite instability and EBV status. Microsatellite instability and EBV status were determined to be detectable if the lower bound of the 95% CI for the AUROC was above 0·5. FINDINGS Across the ten cohorts, our analysis included 2823 patients with known microsatellite instability status and 2685 patients with known EBV status. In the within-cohort cross-validation, the deep learning-based classifier could detect microsatellite instability status in nine of ten cohorts, with AUROCs ranging from 0·597 (95% CI 0·522-0·737) to 0·836 (0·795-0·880) and EBV status in five of eight cohorts, with AUROCs ranging from 0·819 (0·752-0·841) to 0·897 (0·513-0·966). Training a classifier on the pooled training dataset and testing it on the five remaining cohorts resulted in high classification performance with AUROCs ranging from 0·723 (95% CI 0·676-0·794) to 0·863 (0·747-0·969) for detection of microsatellite instability and from 0·672 (0·403-0·989) to 0·859 (0·823-0·919) for detection of EBV status. INTERPRETATION Classifiers became increasingly robust when trained on pooled cohorts. After prospective validation, this deep learning-based tissue classification system could be used as an inexpensive predictive biomarker for immunotherapy in gastric cancer. FUNDING German Cancer Aid and German Federal Ministry of Health.
Collapse
Affiliation(s)
- Hannah Sophie Muti
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - Lara Rosaline Heij
- Department of Surgery and Transplantation, University Hospital RWTH Aachen, Aachen, Germany; Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany
| | - Gisela Keller
- Institute of Pathology, TUM School of Medicine, Technical University of Munich, Munich, Germany
| | - Meike Kohlruss
- Institute of Pathology, TUM School of Medicine, Technical University of Munich, Munich, Germany
| | - Rupert Langer
- Institute of Pathology, Inselspital, University of Bern, Switzerland; Institute of Pathology and Molecular Pathology, Kepler University Hospital, Johannes Kepler University Linz, Linz, Austria
| | - Bastian Dislich
- Institute of Pathology, Inselspital, University of Bern, Switzerland
| | - Jae-Ho Cheong
- Department of Surgery, Yonsei University Health System, Yonsei University College of Medicine, Seoul, South Korea
| | - Young-Woo Kim
- Center for Gastric Cancer, National Cancer Center, Goyang, South Korea
| | - Hyunki Kim
- Department of Pathology, Yonsei University College of Medicine, Seoul, South Korea
| | - Myeong-Cherl Kook
- Department of Pathology, National Cancer Center, Goyang, South Korea
| | - David Cunningham
- Department of Medicine, Gastrointestinal and Lymphoma Units, The Royal Marsden NHS Foundation Trust, London, UK
| | | | - Ruth E Langley
- Medical Research Council Clinical Trials Unit, University College London, London, UK
| | - Matthew G Nankivell
- Medical Research Council Clinical Trials Unit, University College London, London, UK
| | - Philip Quirke
- Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - Jeremy D Hayden
- Department of Oesophago-Gastric Surgery, St James's University Hospital, Leeds, UK
| | - Nicholas P West
- Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - Andrew J Irvine
- Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - Takaki Yoshikawa
- Department of Gastric Surgery, National Cancer Center Hospital, Tokyo, Japan
| | - Takashi Oshima
- Department of Gastrointestinal Surgery, Kanagawa Cancer Center, Yokohama, Japan
| | - Ralf Huss
- Institute of Pathology and Molecular Diagnostics, University Hospital Augsburg, Augsburg, Germany
| | - Bianca Grosser
- Institute of Pathology and Molecular Diagnostics, University Hospital Augsburg, Augsburg, Germany
| | - Franco Roviello
- Department of Medicine, Surgery and Neuroscience, Unit of General Surgery and Surgical Oncology, University of Siena, Italy
| | - Alessia d'Ignazio
- Department of Medicine, Surgery and Neuroscience, Unit of General Surgery and Surgical Oncology, University of Siena, Italy
| | - Alexander Quaas
- Institute of Pathology, University Hospital Cologne, Cologne, Germany
| | - Hakan Alakus
- Department of General, Visceral, Cancer and Transplantation Surgery, University Hospital Cologne, Cologne, Germany
| | - Xiuxiang Tan
- Department of Surgery and Transplantation, University Hospital RWTH Aachen, Aachen, Germany
| | | | - Tom Luedde
- Department of Gastroenterology, Hepatology and Infectious Diseases, University Hospital Duesseldorf, Düsseldorf, Germany
| | - Matthias P Ebert
- Department of Medicine II, Mannheim Institute for Innate Immunoscience and Clinical Cooperation Unit Healthy Metabolism, Center of Preventive Medicine and Digital Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - Dirk Jäger
- Department of Medical Oncology, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
| | - Christian Trautwein
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | | | - Heike I Grabsch
- Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK; Department of Pathology, GROW School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, Netherlands
| | - Jakob Nikolas Kather
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany; Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK; Department of Medical Oncology, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany.
| |
Collapse
|
15
|
Schrammen PL, Ghaffari Laleh N, Echle A, Truhn D, Schulz V, Brinker TJ, Brenner H, Chang-Claude J, Alwers E, Brobeil A, Kloor M, Heij LR, Jäger D, Trautwein C, Grabsch HI, Quirke P, West NP, Hoffmeister M, Kather JN. Weakly supervised annotation-free cancer detection and prediction of genotype in routine histopathology. J Pathol 2021; 256:50-60. [PMID: 34561876 DOI: 10.1002/path.5800] [Citation(s) in RCA: 35] [Impact Index Per Article: 11.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2021] [Revised: 08/01/2021] [Accepted: 09/03/2021] [Indexed: 12/17/2022]
Abstract
Deep learning is a powerful tool in computational pathology: it can be used for tumor detection and for predicting genetic alterations based on histopathology images alone. Conventionally, tumor detection and prediction of genetic alterations are two separate workflows. Newer methods have combined them, but require complex, manually engineered computational pipelines, restricting reproducibility and robustness. To address these issues, we present a new method for simultaneous tumor detection and prediction of genetic alterations: The Slide-Level Assessment Model (SLAM) uses a single off-the-shelf neural network to predict molecular alterations directly from routine pathology slides without any manual annotations, improving upon previous methods by automatically excluding normal and non-informative tissue regions. SLAM requires only standard programming libraries and is conceptually simpler than previous approaches. We have extensively validated SLAM for clinically relevant tasks using two large multicentric cohorts of colorectal cancer patients, Darmkrebs: Chancen der Verhütung durch Screening (DACHS) from Germany and Yorkshire Cancer Research Bowel Cancer Improvement Programme (YCR-BCIP) from the UK. We show that SLAM yields reliable slide-level classification of tumor presence with an area under the receiver operating curve (AUROC) of 0.980 (confidence interval 0.975, 0.984; n = 2,297 tumor and n = 1,281 normal slides). In addition, SLAM can detect microsatellite instability (MSI)/mismatch repair deficiency (dMMR) or microsatellite stability/mismatch repair proficiency with an AUROC of 0.909 (0.888, 0.929; n = 2,039 patients) and BRAF mutational status with an AUROC of 0.821 (0.786, 0.852; n = 2,075 patients). The improvement with respect to previous methods was validated in a large external testing cohort in which MSI/dMMR status was detected with an AUROC of 0.900 (0.864, 0.931; n = 805 patients). In addition, SLAM provides human-interpretable visualization maps, enabling the analysis of multiplexed network predictions by human experts. In summary, SLAM is a new simple and powerful method for computational pathology that could be applied to multiple disease contexts. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.
Collapse
Affiliation(s)
| | | | - Amelie Echle
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - Daniel Truhn
- Department of Radiology, University Hospital RWTH Aachen, Aachen, Germany
| | - Volkmar Schulz
- Department of Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University, Aachen, Germany.,Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany.,Comprehensive Diagnostic Center Aachen (CDCA), University Hospital Aachen, Aachen, Germany.,Hyperion Hybrid Imaging Systems GmbH, Aachen, Germany
| | - Titus J Brinker
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Hermann Brenner
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany.,Division of Preventive Oncology, German Cancer Research Center (DKFZ) and National Center for Tumor Diseases (NCT), Heidelberg, Germany.,German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Jenny Chang-Claude
- Division of Cancer Epidemiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.,Cancer Epidemiology Group, University Cancer Center Hamburg, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Elizabeth Alwers
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Alexander Brobeil
- Institute of Pathology, University Hospital Heidelberg, Heidelberg, Germany.,Tumor Bank Unit, Tissue Bank of the National Center for Tumor Diseases, Heidelberg, Germany
| | - Matthias Kloor
- Institute of Pathology, University Hospital Heidelberg, Heidelberg, Germany
| | - Lara R Heij
- Department of Pathology, GROW School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, The Netherlands.,Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany.,Department of Surgery and Transplantation, University Hospital RWTH Aachen, Aachen, Germany
| | - Dirk Jäger
- Medical Oncology, National Center of Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany
| | - Christian Trautwein
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
| | - Heike I Grabsch
- Department of Pathology, GROW School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, The Netherlands.,Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - Philip Quirke
- Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - Nicholas P West
- Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| | - Michael Hoffmeister
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Jakob Nikolas Kather
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany.,German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany.,Medical Oncology, National Center of Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.,Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
| |
Collapse
|
16
|
Mali SA, Ibrahim A, Woodruff HC, Andrearczyk V, Müller H, Primakov S, Salahuddin Z, Chatterjee A, Lambin P. Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods. J Pers Med 2021; 11:842. [PMID: 34575619 PMCID: PMC8472571 DOI: 10.3390/jpm11090842] [Citation(s) in RCA: 68] [Impact Index Per Article: 22.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2021] [Revised: 08/21/2021] [Accepted: 08/24/2021] [Indexed: 12/13/2022] Open
Abstract
Radiomics converts medical images into mineable data via a high-throughput extraction of quantitative features used for clinical decision support. However, these radiomic features are susceptible to variation across scanners, acquisition protocols, and reconstruction settings. Various investigations have assessed the reproducibility and validation of radiomic features across these discrepancies. In this narrative review, we combine systematic keyword searches with prior domain knowledge to discuss various harmonization solutions to make the radiomic features more reproducible across various scanners and protocol settings. Different harmonization solutions are discussed and divided into two main categories: image domain and feature domain. The image domain category comprises methods such as the standardization of image acquisition, post-processing of raw sensor-level image data, data augmentation techniques, and style transfer. The feature domain category consists of methods such as the identification of reproducible features and normalization techniques such as statistical normalization, intensity harmonization, ComBat and its derivatives, and normalization using deep learning. We also reflect upon the importance of deep learning solutions for addressing variability across multi-centric radiomic studies especially using generative adversarial networks (GANs), neural style transfer (NST) techniques, or a combination of both. We cover a broader range of methods especially GANs and NST methods in more detail than previous reviews.
Collapse
Affiliation(s)
- Shruti Atul Mali
- The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (A.I.); (H.C.W.); (S.P.); (Z.S.); (A.C.); (P.L.)
| | - Abdalla Ibrahim
- The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (A.I.); (H.C.W.); (S.P.); (Z.S.); (A.C.); (P.L.)
- Department of Radiology and Nuclear Medicine, GROW—School for Oncology, Maastricht University Medical Center+, P.O. Box 5800, 6202 AZ Maastricht, The Netherlands
- Department of Medical Physics, Division of Nuclear Medicine and Oncological Imaging, Hospital Center Universitaire de Liege, 4000 Liege, Belgium
- Department of Nuclear Medicine and Comprehensive Diagnostic Center Aachen (CDCA), University Hospital RWTH Aachen University, 52074 Aachen, Germany
| | - Henry C. Woodruff
- The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (A.I.); (H.C.W.); (S.P.); (Z.S.); (A.C.); (P.L.)
- Department of Radiology and Nuclear Medicine, GROW—School for Oncology, Maastricht University Medical Center+, P.O. Box 5800, 6202 AZ Maastricht, The Netherlands
| | - Vincent Andrearczyk
- Institute of Information Systems, University of Applied Sciences and Arts Western Switzerland (HES-SO), rue du Technopole 3, 3960 Sierre, Switzerland; (V.A.); (H.M.)
| | - Henning Müller
- Institute of Information Systems, University of Applied Sciences and Arts Western Switzerland (HES-SO), rue du Technopole 3, 3960 Sierre, Switzerland; (V.A.); (H.M.)
| | - Sergey Primakov
- The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (A.I.); (H.C.W.); (S.P.); (Z.S.); (A.C.); (P.L.)
| | - Zohaib Salahuddin
- The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (A.I.); (H.C.W.); (S.P.); (Z.S.); (A.C.); (P.L.)
| | - Avishek Chatterjee
- The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (A.I.); (H.C.W.); (S.P.); (Z.S.); (A.C.); (P.L.)
| | - Philippe Lambin
- The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (A.I.); (H.C.W.); (S.P.); (Z.S.); (A.C.); (P.L.)
- Department of Radiology and Nuclear Medicine, GROW—School for Oncology, Maastricht University Medical Center+, P.O. Box 5800, 6202 AZ Maastricht, The Netherlands
| |
Collapse
|