1
|
Gonzalez R, Saha A, Campbell CJ, Nejat P, Lokker C, Norgan AP. Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities. J Pathol Inform 2024; 15:100347. [PMID: 38162950 PMCID: PMC10755052 DOI: 10.1016/j.jpi.2023.100347] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2023] [Revised: 10/06/2023] [Accepted: 11/01/2023] [Indexed: 01/03/2024] Open
Abstract
This paper discusses some overlooked challenges faced when working with machine learning models for histopathology and presents a novel opportunity to support "Learning Health Systems" with them. Initially, the authors elaborate on these challenges after separating them according to their mitigation strategies: those that need innovative approaches, time, or future technological capabilities and those that require a conceptual reappraisal from a critical perspective. Then, a novel opportunity to support "Learning Health Systems" by integrating hidden information extracted by ML models from digitalized histopathology slides with other healthcare big data is presented.
Collapse
Affiliation(s)
- Ricardo Gonzalez
- DeGroote School of Business, McMaster University, Hamilton, Ontario, Canada
- Division of Computational Pathology and Artificial Intelligence, Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, United States
| | - Ashirbani Saha
- Department of Oncology, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
- Escarpment Cancer Research Institute, McMaster University and Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Clinton J.V. Campbell
- William Osler Health System, Brampton, Ontario, Canada
- Department of Pathology and Molecular Medicine, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Peyman Nejat
- Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, United States
| | - Cynthia Lokker
- Health Information Research Unit, Department of Health Research Methods, Evidence and Impact, McMaster University, Hamilton, Ontario, Canada
| | - Andrew P. Norgan
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, United States
| |
Collapse
|
2
|
Shen Y, Shen D, Ke J. Identify Representative Samples by Conditional Random Field of Cancer Histology Images. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:3835-3848. [PMID: 35951579 DOI: 10.1109/tmi.2022.3198526] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Pathology analysis is crucial to precise cancer diagnoses and the succeeding treatment plan as well. To detect abnormality in histopathology images with prevailing patch-based convolutional neural networks (CNNs), contextual information often serves as a powerful cue. However, as whole-slide images (WSIs) are characterized by intense morphological heterogeneity and extensive tissue scale, a straightforward visual span to a larger context may not well capture the information closely associated with the focal patch. In this paper, we propose a novel pixel-offset based patch-location method to identify high-representative tissues, with a CNN backbone. Pathology Deformable Conditional Random Field (PDCRF) is proposed to learn the offsets and weights of neighboring contexts in a spatial-adaptive manner, to search for high-representative patches. A CNN structure with the localized patches as training input is then capable of consistently reaching superior classification outcomes for histology images. Overall, the proposed method has achieved state-of-the-art performance, in terms of the test classification accuracy improvement to the baseline by 1.15-2.60%, 0.78-1.78%, and 1.47-2.18% on TCGA public datasets of TCGA-STAD, TCGA-COAD, and TCGA-READ respectively. It also achieves 88.95% test accuracy and 0.920 test AUC on Camelyon 16. To show the effectiveness of the proposed framework on downstream tasks, we take a further step by incorporating an active learning model, which noticeably reduces the number of manual annotations by PDCRF to reach a parallel patch-based histology classifier.
Collapse
|
3
|
Shen Y, Ke J. Sampling Based Tumor Recognition in Whole-Slide Histology Image With Deep Learning Approaches. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022; 19:2431-2441. [PMID: 33630739 DOI: 10.1109/tcbb.2021.3062230] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Histopathological identification of tumor tissue is one of the routine pathological diagnoses for pathologists. Recently, computational pathology has been successfully interpreted by a variety of deep learning-based applications. Nevertheless, the high-efficient and spatial-correlated processing of individual patches have always attracted attention in whole-slide image (WSI) analysis. In this paper, we propose a high-throughput system to detect tumor regions in colorectal cancer histology slides precisely. We train a deep convolutional neural network (CNN) model and design a Monte Carlo (MC) adaptive sampling method to estimate the most representative patches in a WSI. Two conditional random field (CRF) models are designed, namely the correction CRF and the prediction CRF are integrated for spatial dependencies of patches. We use three datasets of colorectal cancer from The Cancer Genome Atlas (TCGA) to evaluate the performance of the system. The overall diagnostic time can be reduced from 56.7 percent to 71.7 percent on the slides of a varying tumor distribution, with an increase in classification accuracy.
Collapse
|
4
|
Ke J, Shen Y, Lu Y, Deng J, Wright JD, Zhang Y, Huang Q, Wang D, Jing N, Liang X, Jiang F. Quantitative analysis of abnormalities in gynecologic cytopathology with deep learning. J Transl Med 2021; 101:513-524. [PMID: 33526806 DOI: 10.1038/s41374-021-00537-1] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2020] [Revised: 12/21/2020] [Accepted: 01/04/2021] [Indexed: 12/19/2022] Open
Abstract
Cervical cancer is one of the most frequent cancers in women worldwide, yet the early detection and treatment of lesions via regular cervical screening have led to a drastic reduction in the mortality rate. However, the routine examination of screening as a regular health checkup of women is characterized as time-consuming and labor-intensive, while there is lack of characteristic phenotypic profile and quantitative analysis. In this research, over the analysis of a privately collected and manually annotated dataset of 130 cytological whole-slide images, the authors proposed a deep-learning diagnostic system to localize, grade, and quantify squamous cell abnormalities. The system can distinguish abnormalities at the morphology level, namely atypical squamous cells of undetermined significance, low-grade squamous intraepithelial lesion, high-grade squamous intraepithelial lesion, and squamous cell carcinoma, as well as differential phenotypes of normal cells. The case study covered 51 positive and 79 negative digital gynecologic cytology slides collected from 2016 to 2018. Our automatic diagnostic system demonstrated its sensitivity of 100% at slide-level abnormality prediction, with the confirmation with three pathologists who performed slide-level diagnosis and training sample annotations. In the cellular-level classification, we yielded an accuracy of 94.5% in the binary classification between normality and abnormality, and the AUC was above 85% for each subtype of epithelial abnormality. Although the final confirmation from pathologists is often a must, empirically, computer-aided methods are capable of the effective extraction, interpretation, and quantification of morphological features, while also making it more objective and reproducible.
Collapse
Affiliation(s)
- Jing Ke
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.
- School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia.
| | - Yiqing Shen
- School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China
| | - Yizhou Lu
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Junwei Deng
- School of Information, University of Michigan, Ann Arbor, MI, USA
| | - Jason D Wright
- Department of Obstetrics and Gynecology, Columbia University, New York, NY, USA
| | - Yan Zhang
- Department of Pathology, Shanghai Tongshu Medical Laboratory Co.Ltd, Shanghai, China
| | - Qin Huang
- Department of Endocrinology and Metabolism, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai Clinical Center for Diabetes, Shanghai, China
| | - Dadong Wang
- Quantitative Imaging, Data61 CSIRO, Sydney, NSW, Australia
| | - Naifeng Jing
- Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China
| | - Xiaoyao Liang
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China
- Biren Research, Shanghai, China, Shanghai, China
| | - Fusong Jiang
- Department of Endocrinology and Metabolism, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai Clinical Center for Diabetes, Shanghai, China
| |
Collapse
|