1
|
Tafavvoghi M, Bongo LA, Shvetsov N, Busund LTR, Møllersen K. Publicly available datasets of breast histopathology H&E whole-slide images: A scoping review. J Pathol Inform 2024; 15:100363. [PMID: 38405160 PMCID: PMC10884505 DOI: 10.1016/j.jpi.2024.100363] [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: 09/14/2023] [Revised: 11/24/2023] [Accepted: 01/23/2024] [Indexed: 02/27/2024] Open
Abstract
Advancements in digital pathology and computing resources have made a significant impact in the field of computational pathology for breast cancer diagnosis and treatment. However, access to high-quality labeled histopathological images of breast cancer is a big challenge that limits the development of accurate and robust deep learning models. In this scoping review, we identified the publicly available datasets of breast H&E-stained whole-slide images (WSIs) that can be used to develop deep learning algorithms. We systematically searched 9 scientific literature databases and 9 research data repositories and found 17 publicly available datasets containing 10 385 H&E WSIs of breast cancer. Moreover, we reported image metadata and characteristics for each dataset to assist researchers in selecting proper datasets for specific tasks in breast cancer computational pathology. In addition, we compiled 2 lists of breast H&E patches and private datasets as supplementary resources for researchers. Notably, only 28% of the included articles utilized multiple datasets, and only 14% used an external validation set, suggesting that the performance of other developed models may be susceptible to overestimation. The TCGA-BRCA was used in 52% of the selected studies. This dataset has a considerable selection bias that can impact the robustness and generalizability of the trained algorithms. There is also a lack of consistent metadata reporting of breast WSI datasets that can be an issue in developing accurate deep learning models, indicating the necessity of establishing explicit guidelines for documenting breast WSI dataset characteristics and metadata.
Collapse
Affiliation(s)
- Masoud Tafavvoghi
- Department of Community Medicine, Uit The Arctic University of Norway, Tromsø, Norway
| | - Lars Ailo Bongo
- Department of Computer Science, Uit The Arctic University of Norway, Tromsø, Norway
| | - Nikita Shvetsov
- Department of Computer Science, Uit The Arctic University of Norway, Tromsø, Norway
| | | | - Kajsa Møllersen
- Department of Community Medicine, Uit The Arctic University of Norway, Tromsø, Norway
| |
Collapse
|
2
|
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
|
3
|
Shahamatdar S, Saeed-Vafa D, Linsley D, Khalil F, Lovinger K, Li L, McLeod HT, Ramachandran S, Serre T. Deceptive learning in histopathology. Histopathology 2024; 85:116-132. [PMID: 38556922 PMCID: PMC11162337 DOI: 10.1111/his.15180] [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: 02/01/2024] [Revised: 03/08/2024] [Accepted: 03/10/2024] [Indexed: 04/02/2024]
Abstract
AIMS Deep learning holds immense potential for histopathology, automating tasks that are simple for expert pathologists and revealing novel biology for tasks that were previously considered difficult or impossible to solve by eye alone. However, the extent to which the visual strategies learned by deep learning models in histopathological analysis are trustworthy or not has yet to be systematically analysed. Here, we systematically evaluate deep neural networks (DNNs) trained for histopathological analysis in order to understand if their learned strategies are trustworthy or deceptive. METHODS AND RESULTS We trained a variety of DNNs on a novel data set of 221 whole-slide images (WSIs) from lung adenocarcinoma patients, and evaluated their effectiveness at (1) molecular profiling of KRAS versus EGFR mutations, (2) determining the primary tissue of a tumour and (3) tumour detection. While DNNs achieved above-chance performance on molecular profiling, they did so by exploiting correlations between histological subtypes and mutations, and failed to generalise to a challenging test set obtained through laser capture microdissection (LCM). In contrast, DNNs learned robust and trustworthy strategies for determining the primary tissue of a tumour as well as detecting and localising tumours in tissue. CONCLUSIONS Our work demonstrates that DNNs hold immense promise for aiding pathologists in analysing tissue. However, they are also capable of achieving seemingly strong performance by learning deceptive strategies that leverage spurious correlations, and are ultimately unsuitable for research or clinical work. The framework we propose for model evaluation and interpretation is an important step towards developing reliable automated systems for histopathological analysis.
Collapse
Affiliation(s)
- Sahar Shahamatdar
- Center for Computational Molecular Biology, Brown University, Providence, RI, USA
- The Warren Alpert Medical School, Brown University, Providence, RI, USA
| | - Daryoush Saeed-Vafa
- Department of Anatomic Pathology, H. Lee Moffitt Cancer and Research Institute, Tampa, FL, USA
| | - Drew Linsley
- Carney Institute for Brain Science, Brown University, Providence, RI, USA
- Department of Cognitive Linguistic & Psychological Sciences, Brown University, Providence, RI, USA
| | - Farah Khalil
- Department of Anatomic Pathology, H. Lee Moffitt Cancer and Research Institute, Tampa, FL, USA
| | - Katherine Lovinger
- Department of Molecular Biology, H. Lee Moffitt Cancer and Research Institute, Tampa, FL, USA
| | - Lester Li
- University of Rochester, Rochester, NY, USA
| | | | - Sohini Ramachandran
- Center for Computational Molecular Biology, Brown University, Providence, RI, USA
- Department of Ecology, Evolution and Organismal Biology, Brown University, Providence, RI, USA
- The Data Science Initiative, Brown University, Providence, RI, USA
| | - Thomas Serre
- Carney Institute for Brain Science, Brown University, Providence, RI, USA
- Department of Cognitive Linguistic & Psychological Sciences, Brown University, Providence, RI, USA
| |
Collapse
|
4
|
Zhang S, Yang B, Yang H, Zhao J, Zhang Y, Gao Y, Monteiro O, Zhang K, Liu B, Wang S. Potential rapid intraoperative cancer diagnosis using dynamic full-field optical coherence tomography and deep learning: A prospective cohort study in breast cancer patients. Sci Bull (Beijing) 2024; 69:1748-1756. [PMID: 38702279 DOI: 10.1016/j.scib.2024.03.061] [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: 10/27/2023] [Revised: 03/18/2024] [Accepted: 03/19/2024] [Indexed: 05/06/2024]
Abstract
An intraoperative diagnosis is critical for precise cancer surgery. However, traditional intraoperative assessments based on hematoxylin and eosin (H&E) histology, such as frozen section, are time-, resource-, and labor-intensive, and involve specimen-consuming concerns. Here, we report a near-real-time automated cancer diagnosis workflow for breast cancer that combines dynamic full-field optical coherence tomography (D-FFOCT), a label-free optical imaging method, and deep learning for bedside tumor diagnosis during surgery. To classify the benign and malignant breast tissues, we conducted a prospective cohort trial. In the modeling group (n = 182), D-FFOCT images were captured from April 26 to June 20, 2018, encompassing 48 benign lesions, 114 invasive ductal carcinoma (IDC), 10 invasive lobular carcinoma, 4 ductal carcinoma in situ (DCIS), and 6 rare tumors. Deep learning model was built up and fine-tuned in 10,357 D-FFOCT patches. Subsequently, from June 22 to August 17, 2018, independent tests (n = 42) were conducted on 10 benign lesions, 29 IDC, 1 DCIS, and 2 rare tumors. The model yielded excellent performance, with an accuracy of 97.62%, sensitivity of 96.88% and specificity of 100%; only one IDC was misclassified. Meanwhile, the acquisition of the D-FFOCT images was non-destructive and did not require any tissue preparation or staining procedures. In the simulated intraoperative margin evaluation procedure, the time required for our novel workflow (approximately 3 min) was significantly shorter than that required for traditional procedures (approximately 30 min). These findings indicate that the combination of D-FFOCT and deep learning algorithms can streamline intraoperative cancer diagnosis independently of traditional pathology laboratory procedures.
Collapse
MESH Headings
- Humans
- Breast Neoplasms/diagnostic imaging
- Breast Neoplasms/surgery
- Breast Neoplasms/pathology
- Tomography, Optical Coherence/methods
- Deep Learning
- Female
- Prospective Studies
- Middle Aged
- Carcinoma, Ductal, Breast/diagnostic imaging
- Carcinoma, Ductal, Breast/surgery
- Carcinoma, Ductal, Breast/pathology
- Aged
- Adult
- Carcinoma, Intraductal, Noninfiltrating/diagnostic imaging
- Carcinoma, Intraductal, Noninfiltrating/surgery
- Carcinoma, Intraductal, Noninfiltrating/pathology
- Intraoperative Period
Collapse
Affiliation(s)
- Shuwei Zhang
- Breast Center, Peking University People's Hospital, Beijing 100044, China
| | - Bin Yang
- China ESG Institute, Capital University of Economics and Business, Beijing 100070, China; Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
| | - Houpu Yang
- Breast Center, Peking University People's Hospital, Beijing 100044, China
| | - Jin Zhao
- Breast Center, Peking University People's Hospital, Beijing 100044, China
| | - Yuanyuan Zhang
- Department of Pathology, Peking University People's Hospital, Beijing 100044, China
| | - Yuanxu Gao
- Center for Biomedicine and Innovations, Faculty of Medicine, Macau University of Science and Technology, Macao 999078, China
| | - Olivia Monteiro
- Center for Biomedicine and Innovations, Faculty of Medicine, Macau University of Science and Technology, Macao 999078, China
| | - Kang Zhang
- Center for Biomedicine and Innovations, Faculty of Medicine, Macau University of Science and Technology, Macao 999078, China; College of Future Technology, Peking University, Beijing 100091, China.
| | - Bo Liu
- School of Mathematical and Computational Sciences, Massey University, Auckland 0745, New Zealand.
| | - Shu Wang
- Breast Center, Peking University People's Hospital, Beijing 100044, China.
| |
Collapse
|
5
|
Cui Y, Li Y, Miedema JR, Edmiston SN, Farag S, Marron JS, Thomas NE. Region of Interest Detection in Melanocytic Skin Tumor Whole Slide Images - Nevus & Melanoma. ARXIV 2024:arXiv:2405.09851v1. [PMID: 38800658 PMCID: PMC11118677] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 05/29/2024]
Abstract
Automated region of interest detection in histopathological image analysis is a challenging and important topic with tremendous potential impact on clinical practice. The deep-learning methods used in computational pathology may help us to reduce costs and increase the speed and accuracy of cancer diagnosis. We started with the UNC Melanocytic Tumor Dataset cohort that contains 160 hematoxylin and eosin whole-slide images of primary melanomas (86) and nevi (74). We randomly assigned 80% (134) as a training set and built an in-house deep-learning method to allow for classification, at the slide level, of nevi and melanomas. The proposed method performed well on the other 20% (26) test dataset; the accuracy of the slide classification task was 92.3% and our model also performed well in terms of predicting the region of interest annotated by the pathologists, showing excellent performance of our model on melanocytic skin tumors. Even though we tested the experiments on the skin tumor dataset, our work could also be extended to other medical image detection problems to benefit the clinical evaluation and diagnosis of different tumors.
Collapse
Affiliation(s)
- Yi Cui
- Department of Economics, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA
| | - Yao Li
- Department of Statistics & Operations Research, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA
| | - Jayson R Miedema
- School of Medicine, University of North Carolina at Chapel Hill, Chapel Hill, NC 27516, USA
| | - Sharon N Edmiston
- Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA
| | - Sherif Farag
- School of Medicine, University of North Carolina at Chapel Hill, Chapel Hill, NC 27516, USA
| | - J S Marron
- Department of Statistics & Operations Research, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA
- School of Medicine, University of North Carolina at Chapel Hill, Chapel Hill, NC 27516, USA
| | - Nancy E Thomas
- School of Medicine, University of North Carolina at Chapel Hill, Chapel Hill, NC 27516, USA
| |
Collapse
|
6
|
Liu Y, Chen W, Ruan R, Zhang Z, Wang Z, Guan T, Lin Q, Tang W, Deng J, Wang Z, Li G. Deep learning based digital pathology for predicting treatment response to first-line PD-1 blockade in advanced gastric cancer. J Transl Med 2024; 22:438. [PMID: 38720336 PMCID: PMC11077733 DOI: 10.1186/s12967-024-05262-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2024] [Accepted: 04/29/2024] [Indexed: 05/12/2024] Open
Abstract
BACKGROUND Advanced unresectable gastric cancer (GC) patients were previously treated with chemotherapy alone as the first-line therapy. However, with the Food and Drug Administration's (FDA) 2022 approval of programmed cell death protein 1 (PD-1) inhibitor combined with chemotherapy as the first-li ne treatment for advanced unresectable GC, patients have significantly benefited. However, the significant costs and potential adverse effects necessitate precise patient selection. In recent years, the advent of deep learning (DL) has revolutionized the medical field, particularly in predicting tumor treatment responses. Our study utilizes DL to analyze pathological images, aiming to predict first-line PD-1 combined chemotherapy response for advanced-stage GC. METHODS In this multicenter retrospective analysis, Hematoxylin and Eosin (H&E)-stained slides were collected from advanced GC patients across four medical centers. Treatment response was evaluated according to iRECIST 1.1 criteria after a comprehensive first-line PD-1 immunotherapy combined with chemotherapy. Three DL models were employed in an ensemble approach to create the immune checkpoint inhibitors Response Score (ICIsRS) as a novel histopathological biomarker derived from Whole Slide Images (WSIs). RESULTS Analyzing 148,181 patches from 313 WSIs of 264 advanced GC patients, the ensemble model exhibited superior predictive accuracy, leading to the creation of ICIsNet. The model demonstrated robust performance across four testing datasets, achieving AUC values of 0.92, 0.95, 0.96, and 1 respectively. The boxplot, constructed from the ICIsRS, reveals statistically significant disparities between the well response and poor response (all p-values < = 0.001). CONCLUSION ICIsRS, a DL-derived biomarker from WSIs, effectively predicts advanced GC patients' responses to PD-1 combined chemotherapy, offering a novel approach for personalized treatment planning and allowing for more individualized and potentially effective treatment strategies based on a patient's unique response situations.
Collapse
Affiliation(s)
- Yifan Liu
- Department of Gastrointestinal Surgery, First Affiliated Hospital of Sun Yat-sen University, Zhongshan 2nd Street, No. 58, Guangzhou, 510080, 86, Guangdong, China
| | - Wei Chen
- Guangdong Provincial Key Laboratory of Digestive Cancer Research, Digestive Diseases Center, Scientific Research Center, The Seventh Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong, China
| | - Ruiwen Ruan
- Department of Oncology, First Affiliated Hospital of Nanchang University, Nanchang, 330006, Jiangxi Province, China
| | - Zhimei Zhang
- Department of Pathology, First Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Zhixiong Wang
- Department of Gastrointestinal Surgery, First Affiliated Hospital of Sun Yat-sen University, Zhongshan 2nd Street, No. 58, Guangzhou, 510080, 86, Guangdong, China
| | - Tianpei Guan
- Department of Gastrointestinal Surgery, Affiliated Cancer Hospital & Institute of Guangzhou Medical University, Guangzhou, Guangdong, China
| | - Qi Lin
- Department of Gastrointestinal Surgery, First Affiliated Hospital of Sun Yat-sen University, Zhongshan 2nd Street, No. 58, Guangzhou, 510080, 86, Guangdong, China
| | - Wei Tang
- Department of Gastrointestinal Surgery, First Affiliated Hospital of Sun Yat-sen University, Zhongshan 2nd Street, No. 58, Guangzhou, 510080, 86, Guangdong, China
| | - Jun Deng
- Department of Oncology, First Affiliated Hospital of Nanchang University, Nanchang, 330006, Jiangxi Province, China.
| | - Zhao Wang
- Department of Gastrointestinal Surgery, First Affiliated Hospital of Sun Yat-sen University, Zhongshan 2nd Street, No. 58, Guangzhou, 510080, 86, Guangdong, China.
| | - Guanghua Li
- Department of Gastrointestinal Surgery, First Affiliated Hospital of Sun Yat-sen University, Zhongshan 2nd Street, No. 58, Guangzhou, 510080, 86, Guangdong, China.
| |
Collapse
|
7
|
McGenity C, Clarke EL, Jennings C, Matthews G, Cartlidge C, Freduah-Agyemang H, Stocken DD, Treanor D. Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy. NPJ Digit Med 2024; 7:114. [PMID: 38704465 PMCID: PMC11069583 DOI: 10.1038/s41746-024-01106-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2023] [Accepted: 04/12/2024] [Indexed: 05/06/2024] Open
Abstract
Ensuring diagnostic performance of artificial intelligence (AI) before introduction into clinical practice is essential. Growing numbers of studies using AI for digital pathology have been reported over recent years. The aim of this work is to examine the diagnostic accuracy of AI in digital pathology images for any disease. This systematic review and meta-analysis included diagnostic accuracy studies using any type of AI applied to whole slide images (WSIs) for any disease. The reference standard was diagnosis by histopathological assessment and/or immunohistochemistry. Searches were conducted in PubMed, EMBASE and CENTRAL in June 2022. Risk of bias and concerns of applicability were assessed using the QUADAS-2 tool. Data extraction was conducted by two investigators and meta-analysis was performed using a bivariate random effects model, with additional subgroup analyses also performed. Of 2976 identified studies, 100 were included in the review and 48 in the meta-analysis. Studies were from a range of countries, including over 152,000 whole slide images (WSIs), representing many diseases. These studies reported a mean sensitivity of 96.3% (CI 94.1-97.7) and mean specificity of 93.3% (CI 90.5-95.4). There was heterogeneity in study design and 99% of studies identified for inclusion had at least one area at high or unclear risk of bias or applicability concerns. Details on selection of cases, division of model development and validation data and raw performance data were frequently ambiguous or missing. AI is reported as having high diagnostic accuracy in the reported areas but requires more rigorous evaluation of its performance.
Collapse
Affiliation(s)
- Clare McGenity
- University of Leeds, Leeds, UK.
- Leeds Teaching Hospitals NHS Trust, Leeds, UK.
| | - Emily L Clarke
- University of Leeds, Leeds, UK
- Leeds Teaching Hospitals NHS Trust, Leeds, UK
| | - Charlotte Jennings
- University of Leeds, Leeds, UK
- Leeds Teaching Hospitals NHS Trust, Leeds, UK
| | | | | | | | | | - Darren Treanor
- University of Leeds, Leeds, UK
- Leeds Teaching Hospitals NHS Trust, Leeds, UK
- Department of Clinical Pathology and Department of Clinical and Experimental Medicine, Linköping University, Linköping, Sweden
- Centre for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| |
Collapse
|
8
|
Omar M, Xu Z, Rand SB, Alexanderani MK, Salles DC, Valencia I, Schaeffer EM, Robinson BD, Lotan TL, Loda M, Marchionni L. Semi-Supervised, Attention-Based Deep Learning for Predicting TMPRSS2:ERG Fusion Status in Prostate Cancer Using Whole Slide Images. Mol Cancer Res 2024; 22:347-359. [PMID: 38284821 PMCID: PMC10985477 DOI: 10.1158/1541-7786.mcr-23-0639] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2023] [Revised: 12/26/2023] [Accepted: 01/22/2024] [Indexed: 01/30/2024]
Abstract
IMPLICATIONS Our study illuminates the potential of deep learning in effectively inferring key prostate cancer genetic alterations from the tissue morphology depicted in routinely available histology slides, offering a cost-effective method that could revolutionize diagnostic strategies in oncology.
Collapse
Affiliation(s)
- Mohamed Omar
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
- Dana-Farber Cancer Institute, Boston, Massachusetts
| | - Zhuoran Xu
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
- Dana-Farber Cancer Institute, Boston, Massachusetts
| | - Sophie B. Rand
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
- Dana-Farber Cancer Institute, Boston, Massachusetts
| | | | - Daniela C. Salles
- Department of Pathology, Johns Hopkins University, Baltimore, Maryland
| | - Itzel Valencia
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
| | | | - Brian D. Robinson
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
| | - Tamara L. Lotan
- Department of Pathology, Johns Hopkins University, Baltimore, Maryland
| | - Massimo Loda
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
| | - Luigi Marchionni
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
| |
Collapse
|
9
|
Godson L, Alemi N, Nsengimana J, Cook GP, Clarke EL, Treanor D, Bishop DT, Newton-Bishop J, Gooya A, Magee D. Immune subtyping of melanoma whole slide images using multiple instance learning. Med Image Anal 2024; 93:103097. [PMID: 38325154 DOI: 10.1016/j.media.2024.103097] [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: 12/16/2022] [Revised: 01/15/2024] [Accepted: 01/25/2024] [Indexed: 02/09/2024]
Abstract
Determining early-stage prognostic markers and stratifying patients for effective treatment are two key challenges for improving outcomes for melanoma patients. Previous studies have used tumour transcriptome data to stratify patients into immune subgroups, which were associated with differential melanoma specific survival and potential predictive biomarkers. However, acquiring transcriptome data is a time-consuming and costly process. Moreover, it is not routinely used in the current clinical workflow. Here, we attempt to overcome this by developing deep learning models to classify gigapixel haematoxylin and eosin (H&E) stained pathology slides, which are well established in clinical workflows, into these immune subgroups. We systematically assess six different multiple instance learning (MIL) frameworks, using five different image resolutions and three different feature extraction methods. We show that pathology-specific self-supervised models using 10x resolution patches generate superior representations for the classification of immune subtypes. In addition, in a primary melanoma dataset, we achieve a mean area under the receiver operating characteristic curve (AUC) of 0.80 for classifying histopathology images into 'high' or 'low immune' subgroups and a mean AUC of 0.82 in an independent TCGA melanoma dataset. Furthermore, we show that these models are able to stratify patients into 'high' and 'low immune' subgroups with significantly different melanoma specific survival outcomes (log rank test, P< 0.005). We anticipate that MIL methods will allow us to find new biomarkers of high importance, act as a tool for clinicians to infer the immune landscape of tumours and stratify patients, without needing to carry out additional expensive genetic tests.
Collapse
Affiliation(s)
- Lucy Godson
- School of Computing, University of Leeds, Woodhouse, Leeds, LS2 9JT, United Kingdom.
| | - Navid Alemi
- School of Computing, University of Leeds, Woodhouse, Leeds, LS2 9JT, United Kingdom
| | - Jérémie Nsengimana
- Population Health Sciences Institute, Newcastle University, Newcastle upon Tyne, NE1 7RU, United Kingdom
| | - Graham P Cook
- Leeds Institute of Medical Research, University of Leeds School of Medicine, St. James's University Hospital, Leeds, United Kingdom
| | - Emily L Clarke
- Department of Histopathology, Leeds Teaching Hospitals NHS Trust, Leeds, United Kingdom; Division of Pathology and Data Analytics, Leeds Institute of Cancer and Pathology, University of Leeds, Beckett Street, Leeds, LS9 7TF, United Kingdom
| | - Darren Treanor
- Department of Histopathology, Leeds Teaching Hospitals NHS Trust, Leeds, United Kingdom; Division of Pathology and Data Analytics, Leeds Institute of Cancer and Pathology, University of Leeds, Beckett Street, Leeds, LS9 7TF, United Kingdom; Department of Clinical Pathology and Department of Clinical and Experimental Medicine, Linköping University, Linköping, Sweden; Centre for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| | - D Timothy Bishop
- Leeds Institute of Medical Research, University of Leeds School of Medicine, St. James's University Hospital, Leeds, United Kingdom
| | - Julia Newton-Bishop
- Division of Pathology and Data Analytics, Leeds Institute of Cancer and Pathology, University of Leeds, Beckett Street, Leeds, LS9 7TF, United Kingdom
| | - Ali Gooya
- School of Computing, University of Glasgow, Glasgow, G12 8QQ, United Kingdom
| | - Derek Magee
- School of Computing, University of Leeds, Woodhouse, Leeds, LS2 9JT, United Kingdom
| |
Collapse
|
10
|
Arslan S, Schmidt J, Bass C, Mehrotra D, Geraldes A, Singhal S, Hense J, Li X, Raharja-Liu P, Maiques O, Kather JN, Pandya P. A systematic pan-cancer study on deep learning-based prediction of multi-omic biomarkers from routine pathology images. COMMUNICATIONS MEDICINE 2024; 4:48. [PMID: 38491101 PMCID: PMC10942985 DOI: 10.1038/s43856-024-00471-5] [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: 11/25/2022] [Accepted: 02/29/2024] [Indexed: 03/18/2024] Open
Abstract
BACKGROUND The objective of this comprehensive pan-cancer study is to evaluate the potential of deep learning (DL) for molecular profiling of multi-omic biomarkers directly from hematoxylin and eosin (H&E)-stained whole slide images. METHODS A total of 12,093 DL models predicting 4031 multi-omic biomarkers across 32 cancer types were trained and validated. The study included a broad range of genetic, transcriptomic, and proteomic biomarkers, as well as established prognostic markers, molecular subtypes, and clinical outcomes. RESULTS Here we show that 50% of the models achieve an area under the curve (AUC) of 0.644 or higher. The observed AUC for 25% of the models is at least 0.719 and exceeds 0.834 for the top 5%. Molecular profiling with image-based histomorphological features is generally considered feasible for most of the investigated biomarkers and across different cancer types. The performance appears to be independent of tumor purity, sample size, and class ratio (prevalence), suggesting a degree of inherent predictability in histomorphology. CONCLUSIONS The results demonstrate that DL holds promise to predict a wide range of biomarkers across the omics spectrum using only H&E-stained histological slides of solid tumors. This paves the way for accelerating diagnosis and developing more precise treatments for cancer patients.
Collapse
Affiliation(s)
| | | | | | - Debapriya Mehrotra
- Panakeia Technologies, London, UK
- Department of Pathology, Barking, Havering and Redbridge University NHS Trust, Romford, UK
| | | | - Shikha Singhal
- Panakeia Technologies, London, UK
- Department of Pathology, The Royal Wolverhampton NHS Trust, Wolverhampton, UK
| | | | - Xiusi Li
- Panakeia Technologies, London, UK
| | | | - Oscar Maiques
- Cytoskeleton and Cancer Metastasis Group, Breast Cancer Now Toby Robins Breast Cancer Research Centre, The Institute of Cancer Research, London, UK
- Cancer Biomarkers & Biotherapeutics, Barts Cancer Institute, Queen Mary University of London, John Vane Science Building, London, UK
| | - Jakob Nikolas Kather
- Medical Oncology, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
| | | |
Collapse
|
11
|
Liu H, Zhang Y, Luo J. Contrastive learning-based histopathological features infer molecular subtypes and clinical outcomes of breast cancer from unannotated whole slide images. Comput Biol Med 2024; 170:107997. [PMID: 38271839 DOI: 10.1016/j.compbiomed.2024.107997] [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: 09/30/2023] [Revised: 12/25/2023] [Accepted: 01/13/2024] [Indexed: 01/27/2024]
Abstract
The artificial intelligence-powered computational pathology has led to significant improvements in the speed and precision of tumor diagnosis, while also exhibiting substantial potential to infer genetic mutations and gene expression levels. However, current studies remain limited in predicting molecular subtypes and clinical outcomes in breast cancer. In this paper, we proposed a weakly supervised contrastive learning framework to address this challenge. Our framework first performed contrastive learning pretraining on a large number of unlabeled patches tiled from whole slide images (WSIs) to extract patch-level features. The gated attention mechanism was leveraged to aggregate patch-level features to produce slide feature that was then applied to various downstream tasks. To confirm the effectiveness of the proposed method, three public cohorts and one external independent cohort of breast cancer have been used to conducted evaluation experiments. The predictive powers of our model to infer gene expression, molecular subtypes, recurrence events and drug responses were validated across cohorts. In addition, the learned patch-level attention scores enabled us to generate heatmaps that were highly consistent with pathologist annotations and spatial transcriptomic data. These findings demonstrated that our model effectively established the high-order genotype-phenotype associations, thereby potentially extend the application of digital pathology in clinical practice.
Collapse
Affiliation(s)
- Hui Liu
- College of Computer and Information Engineering, Nanjing Tech University, Nanjing, 211816, China
| | - Yang Zhang
- College of Computer and Information Engineering, Nanjing Tech University, Nanjing, 211816, China
| | - Judong Luo
- Department of Radiotherapy, Tongji Hospital, School of Medicine, Tongji University, Shanghai, 200065, China.
| |
Collapse
|
12
|
Demir R, Koc S, Ozturk DG, Bilir S, Ozata Hİ, Williams R, Christy J, Akkoc Y, Tinay İ, Gunduz-Demir C, Gozuacik D. Artificial intelligence assisted patient blood and urine droplet pattern analysis for non-invasive and accurate diagnosis of bladder cancer. Sci Rep 2024; 14:2488. [PMID: 38291121 PMCID: PMC10827787 DOI: 10.1038/s41598-024-52728-7] [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: 08/16/2023] [Accepted: 01/23/2024] [Indexed: 02/01/2024] Open
Abstract
Bladder cancer is one of the most common cancer types in the urinary system. Yet, current bladder cancer diagnosis and follow-up techniques are time-consuming, expensive, and invasive. In the clinical practice, the gold standard for diagnosis remains invasive biopsy followed by histopathological analysis. In recent years, costly diagnostic tests involving the use of bladder cancer biomarkers have been developed, however these tests have high false-positive and false-negative rates limiting their reliability. Hence, there is an urgent need for the development of cost-effective, and non-invasive novel diagnosis methods. To address this gap, here we propose a quick, cheap, and reliable diagnostic method. Our approach relies on an artificial intelligence (AI) model to analyze droplet patterns of blood and urine samples obtained from patients and comparing them to cancer-free control subjects. The AI-assisted model in this study uses a deep neural network, a ResNet network, pre-trained on ImageNet datasets. Recognition and classification of complex patterns formed by dried urine or blood droplets under different conditions resulted in cancer diagnosis with a high specificity and sensitivity. Our approach can be systematically applied across droplets, enabling comparisons to reveal shared spatial behaviors and underlying morphological patterns. Our results support the fact that AI-based models have a great potential for non-invasive and accurate diagnosis of malignancies, including bladder cancer.
Collapse
Affiliation(s)
- Ramiz Demir
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey
| | - Soner Koc
- Department of Computer Engineering, Koç University, Istanbul, Turkey
- KUIS AI Center, Koç University, Istanbul, Turkey
| | - Deniz Gulfem Ozturk
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey
| | - Sukriye Bilir
- SUNUM Nanotechnology Research and Application Center, Istanbul, Turkey
| | | | - Rhodri Williams
- School of Engineering, University of Edinburgh, Edinburgh, UK
| | - John Christy
- School of Engineering, University of Edinburgh, Edinburgh, UK
| | - Yunus Akkoc
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey
| | - İlker Tinay
- Anadolu Medical Center, Gebze, Kocaeli, Turkey
| | - Cigdem Gunduz-Demir
- Department of Computer Engineering, Koç University, Istanbul, Turkey.
- KUIS AI Center, Koç University, Istanbul, Turkey.
- School of Medicine, Koç University, Istanbul, Turkey.
| | - Devrim Gozuacik
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey.
- SUNUM Nanotechnology Research and Application Center, Istanbul, Turkey.
- School of Medicine, Koç University, Istanbul, Turkey.
| |
Collapse
|
13
|
Zheng Y, Pizurica M, Carrillo-Perez F, Noor H, Yao W, Wohlfart C, Marchal K, Vladimirova A, Gevaert O. Digital profiling of cancer transcriptomes from histology images with grouped vision attention. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2023.09.28.560068. [PMID: 37808782 PMCID: PMC10557714 DOI: 10.1101/2023.09.28.560068] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/10/2023]
Abstract
Cancer is a heterogeneous disease that demands precise molecular profiling for better understanding and management. Recently, deep learning has demonstrated potentials for cost-efficient prediction of molecular alterations from histology images. While transformer-based deep learning architectures have enabled significant progress in non-medical domains, their application to histology images remains limited due to small dataset sizes coupled with the explosion of trainable parameters. Here, we develop SEQUOIA, a transformer model to predict cancer transcriptomes from whole-slide histology images. To enable the full potential of transformers, we first pre-train the model using data from 1,802 normal tissues. Then, we fine-tune and evaluate the model in 4,331 tumor samples across nine cancer types. The prediction performance is assessed at individual gene levels and pathway levels through Pearson correlation analysis and root mean square error. The generalization capacity is validated across two independent cohorts comprising 1,305 tumors. In predicting the expression levels of 25,749 genes, the highest performance is observed in cancers from breast, kidney and lung, where SEQUOIA accurately predicts the expression of 11,069, 10,086 and 8,759 genes, respectively. The accurately predicted genes are associated with the regulation of inflammatory response, cell cycles and metabolisms. While the model is trained at the tissue level, we showcase its potential in predicting spatial gene expression patterns using spatial transcriptomics datasets. Leveraging the prediction performance, we develop a digital gene expression signature that predicts the risk of recurrence in breast cancer. SEQUOIA deciphers clinically relevant gene expression patterns from histology images, opening avenues for improved cancer management and personalized therapies.
Collapse
Affiliation(s)
- Yuanning Zheng
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, 94305, USA
| | - Marija Pizurica
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, 94305, USA
- Internet technology and Data science Lab (IDLab), Ghent University, Technologiepark-Zwijnaarde 126, Ghent, 9052, Gent, Belgium
| | - Francisco Carrillo-Perez
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, 94305, USA
| | - Humaira Noor
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, 94305, USA
| | - Wei Yao
- Roche Information Solutions, Roche Diagnostics Corporation, Santa Clara, California, USA
| | | | - Kathleen Marchal
- Internet technology and Data science Lab (IDLab), Ghent University, Technologiepark-Zwijnaarde 126, Ghent, 9052, Gent, Belgium
| | - Antoaneta Vladimirova
- Roche Information Solutions, Roche Diagnostics Corporation, Santa Clara, California, USA
| | - Olivier Gevaert
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, 94305, USA
| |
Collapse
|
14
|
Dawood M, Vu QD, Young LS, Branson K, Jones L, Rajpoot N, Minhas FUAA. Cancer drug sensitivity prediction from routine histology images. NPJ Precis Oncol 2024; 8:5. [PMID: 38184744 PMCID: PMC10771481 DOI: 10.1038/s41698-023-00491-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 12/08/2023] [Indexed: 01/08/2024] Open
Abstract
Drug sensitivity prediction models can aid in personalising cancer therapy, biomarker discovery, and drug design. Such models require survival data from randomised controlled trials which can be time consuming and expensive. In this proof-of-concept study, we demonstrate for the first time that deep learning can link histological patterns in whole slide images (WSIs) of Haematoxylin & Eosin (H&E) stained breast cancer sections with drug sensitivities inferred from cell lines. We employ patient-wise drug sensitivities imputed from gene expression-based mapping of drug effects on cancer cell lines to train a deep learning model that predicts patients' sensitivity to multiple drugs from WSIs. We show that it is possible to use routine WSIs to predict the drug sensitivity profile of a cancer patient for a number of approved and experimental drugs. We also show that the proposed approach can identify cellular and histological patterns associated with drug sensitivity profiles of cancer patients.
Collapse
Affiliation(s)
- Muhammad Dawood
- Tissue Image Analytics Centre, University of Warwick, Coventry, UK.
| | - Quoc Dang Vu
- Tissue Image Analytics Centre, University of Warwick, Coventry, UK
| | - Lawrence S Young
- Warwick Medical School, University of Warwick, Coventry, UK
- Cancer Research Centre, University of Warwick, Coventry, UK
| | - Kim Branson
- Artificial Intelligence & Machine Learning, GlaxoSmithKline, San Francisco, CA, USA
| | - Louise Jones
- Barts Cancer Institute, Queen Mary University of London, London, UK
| | - Nasir Rajpoot
- Tissue Image Analytics Centre, University of Warwick, Coventry, UK
- Cancer Research Centre, University of Warwick, Coventry, UK
- The Alan Turing Institute, London, UK
| | - Fayyaz Ul Amir Afsar Minhas
- Tissue Image Analytics Centre, University of Warwick, Coventry, UK
- Cancer Research Centre, University of Warwick, Coventry, UK
| |
Collapse
|
15
|
Medvedev KE, Acosta PH, Jia L, Grishin NV. Deep Learning for Subtypes Identification of Pure Seminoma of the Testis. CLINICAL PATHOLOGY (THOUSAND OAKS, VENTURA COUNTY, CALIF.) 2024; 17:2632010X241232302. [PMID: 38380227 PMCID: PMC10878207 DOI: 10.1177/2632010x241232302] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/07/2023] [Accepted: 01/28/2024] [Indexed: 02/22/2024]
Abstract
The most critical step in the clinical diagnosis workflow is the pathological evaluation of each tumor sample. Deep learning is a powerful approach that is widely used to enhance diagnostic accuracy and streamline the diagnosis process. In our previous study using omics data, we identified 2 distinct subtypes of pure seminoma. Seminoma is the most common histological type of testicular germ cell tumors (TGCTs). Here we developed a deep learning decision making tool for the identification of seminoma subtypes using histopathological slides. We used all available slides for pure seminoma samples from The Cancer Genome Atlas (TCGA). The developed model showed an area under the ROC curve of 0.896. Our model not only confirms the presence of 2 distinct subtypes within pure seminoma but also unveils the presence of morphological differences between them that are imperceptible to the human eye.
Collapse
Affiliation(s)
- Kirill E Medvedev
- Department of Biophysics, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Paul H Acosta
- Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Liwei Jia
- Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Nick V Grishin
- Department of Biophysics, University of Texas Southwestern Medical Center, Dallas, TX, USA
- Department of Biochemistry, University of Texas Southwestern Medical Center, Dallas, TX, USA
| |
Collapse
|
16
|
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
|
17
|
Mukashyaka P, Sheridan TB, Foroughi Pour A, Chuang JH. SAMPLER: unsupervised representations for rapid analysis of whole slide tissue images. EBioMedicine 2024; 99:104908. [PMID: 38101298 PMCID: PMC10733087 DOI: 10.1016/j.ebiom.2023.104908] [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: 08/23/2023] [Revised: 11/27/2023] [Accepted: 11/27/2023] [Indexed: 12/17/2023] Open
Abstract
BACKGROUND Deep learning has revolutionized digital pathology, allowing automatic analysis of hematoxylin and eosin (H&E) stained whole slide images (WSIs) for diverse tasks. WSIs are broken into smaller images called tiles, and a neural network encodes each tile. Many recent works use supervised attention-based models to aggregate tile-level features into a slide-level representation, which is then used for downstream analysis. Training supervised attention-based models is computationally intensive, architecture optimization of the attention module is non-trivial, and labeled data are not always available. Therefore, we developed an unsupervised and fast approach called SAMPLER to generate slide-level representations. METHODS Slide-level representations of SAMPLER are generated by encoding the cumulative distribution functions of multiscale tile-level features. To assess effectiveness of SAMPLER, slide-level representations of breast carcinoma (BRCA), non-small cell lung carcinoma (NSCLC), and renal cell carcinoma (RCC) WSIs of The Cancer Genome Atlas (TCGA) were used to train separate classifiers distinguishing tumor subtypes in FFPE and frozen WSIs. In addition, BRCA and NSCLC classifiers were externally validated on frozen WSIs. Moreover, SAMPLER's attention maps identify regions of interest, which were evaluated by a pathologist. To determine time efficiency of SAMPLER, we compared runtime of SAMPLER with two attention-based models. SAMPLER concepts were used to improve the design of a context-aware multi-head attention model (context-MHA). FINDINGS SAMPLER-based classifiers were comparable to state-of-the-art attention deep learning models to distinguish subtypes of BRCA (AUC = 0.911 ± 0.029), NSCLC (AUC = 0.940 ± 0.018), and RCC (AUC = 0.987 ± 0.006) on FFPE WSIs (internal test sets). However, training SAMLER-based classifiers was >100 times faster. SAMPLER models successfully distinguished tumor subtypes on both internal and external test sets of frozen WSIs. Histopathological review confirmed that SAMPLER-identified high attention tiles contained subtype-specific morphological features. The improved context-MHA distinguished subtypes of BRCA and RCC (BRCA-AUC = 0.921 ± 0.027, RCC-AUC = 0.988 ± 0.010) with increased accuracy on internal test FFPE WSIs. INTERPRETATION Our unsupervised statistical approach is fast and effective for analyzing WSIs, with greatly improved scalability over attention-based deep learning methods. The high accuracy of SAMPLER-based classifiers and interpretable attention maps suggest that SAMPLER successfully encodes the distinct morphologies within WSIs and will be applicable to general histology image analysis problems. FUNDING This study was supported by the National Cancer Institute (Grant No. R01CA230031 and P30CA034196).
Collapse
Affiliation(s)
- Patience Mukashyaka
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Genetics and Genome Sciences, University of Connecticut Health Center, Farmington, CT, USA
| | - Todd B Sheridan
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Pathology, Hartford Hospital, Hartford, CT, USA
| | | | - Jeffrey H Chuang
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Genetics and Genome Sciences, University of Connecticut Health Center, Farmington, CT, USA.
| |
Collapse
|
18
|
Dang J, Shu J, Wang R, Yu H, Chen Z, Yan W, Zhao B, Ding L, Wang Y, Hu H, Li Z. The glycopatterns of Pseudomonas aeruginosa as a potential biomarker for its carbapenem resistance. Microbiol Spectr 2023; 11:e0200123. [PMID: 37861315 PMCID: PMC10714932 DOI: 10.1128/spectrum.02001-23] [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: 05/23/2023] [Accepted: 09/08/2023] [Indexed: 10/21/2023] Open
Abstract
IMPORTANCE Bacterial surface glycans are an attractive therapeutic target in response to antibiotics; however, current knowledge of the corresponding mechanisms is rather limited. Antimicrobial susceptibility testing, genome sequencing, and MALDI-TOF MS, commonly used in recent years to analyze bacterial resistance, are unable to rapidly and efficiently establish associations between glycans and resistance. The discovery of new antimicrobial strategies still requires the introduction of promising analytical methods. In this study, we applied lectin microarray technology and a machine-learning model to screen for important glycan structures associated with carbapenem-resistant P. aeruginosa. This work highlights that specific glycopatterns can be important biomarkers associated with bacterial antibiotic resistance, which promises to provide a rapid entry point for exploring new resistance mechanisms in pathogens.
Collapse
Affiliation(s)
- Jing Dang
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Jian Shu
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Ruiying Wang
- Hospital of Shaanxi Nuclear Industry, Xianyang, Shaanxi, China
| | - Hanjie Yu
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Zhuo Chen
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Wenbo Yan
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Bingxiang Zhao
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Li Ding
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Yuzi Wang
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| | - Huizheng Hu
- Hospital of Shaanxi Nuclear Industry, Xianyang, Shaanxi, China
| | - Zheng Li
- Laboratory of Functional Glycomics, College of Life Sciences, Northwest University, Xi'an, Shaanxi, China
| |
Collapse
|
19
|
Schacherer DP, Herrmann MD, Clunie DA, Höfener H, Clifford W, Longabaugh WJR, Pieper S, Kikinis R, Fedorov A, Homeyer A. The NCI Imaging Data Commons as a platform for reproducible research in computational pathology. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 242:107839. [PMID: 37832430 PMCID: PMC10841477 DOI: 10.1016/j.cmpb.2023.107839] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/15/2023] [Revised: 09/20/2023] [Accepted: 10/01/2023] [Indexed: 10/15/2023]
Abstract
BACKGROUND AND OBJECTIVES Reproducibility is a major challenge in developing machine learning (ML)-based solutions in computational pathology (CompPath). The NCI Imaging Data Commons (IDC) provides >120 cancer image collections according to the FAIR principles and is designed to be used with cloud ML services. Here, we explore its potential to facilitate reproducibility in CompPath research. METHODS Using the IDC, we implemented two experiments in which a representative ML-based method for classifying lung tumor tissue was trained and/or evaluated on different datasets. To assess reproducibility, the experiments were run multiple times with separate but identically configured instances of common ML services. RESULTS The results of different runs of the same experiment were reproducible to a large extent. However, we observed occasional, small variations in AUC values, indicating a practical limit to reproducibility. CONCLUSIONS We conclude that the IDC facilitates approaching the reproducibility limit of CompPath research (i) by enabling researchers to reuse exactly the same datasets and (ii) by integrating with cloud ML services so that experiments can be run in identically configured computing environments.
Collapse
Affiliation(s)
- Daniela P Schacherer
- Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Straße 2, 28359 Bremen, Germany
| | - Markus D Herrmann
- Department of Pathology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | | | - Henning Höfener
- Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Straße 2, 28359 Bremen, Germany
| | | | | | | | - Ron Kikinis
- Department of Radiology, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA
| | - Andrey Fedorov
- Department of Radiology, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA
| | - André Homeyer
- Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Straße 2, 28359 Bremen, Germany.
| |
Collapse
|
20
|
Haghofer A, Fuchs-Baumgartinger A, Lipnik K, Klopfleisch R, Aubreville M, Scharinger J, Weissenböck H, Winkler SM, Bertram CA. Histological classification of canine and feline lymphoma using a modular approach based on deep learning and advanced image processing. Sci Rep 2023; 13:19436. [PMID: 37945699 PMCID: PMC10636139 DOI: 10.1038/s41598-023-46607-w] [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: 06/27/2023] [Accepted: 11/02/2023] [Indexed: 11/12/2023] Open
Abstract
Histopathological examination of tissue samples is essential for identifying tumor malignancy and the diagnosis of different types of tumor. In the case of lymphoma classification, nuclear size of the neoplastic lymphocytes is one of the key features to differentiate the different subtypes. Based on the combination of artificial intelligence and advanced image processing, we provide a workflow for the classification of lymphoma with regards to their nuclear size (small, intermediate, and large). As the baseline for our workflow testing, we use a Unet++ model trained on histological images of canine lymphoma with individually labeled nuclei. As an alternative to the Unet++, we also used a publicly available pre-trained and unmodified instance segmentation model called Stardist to demonstrate that our modular classification workflow can be combined with different types of segmentation models if they can provide proper nuclei segmentation. Subsequent to nuclear segmentation, we optimize algorithmic parameters for accurate classification of nuclear size using a newly derived reference size and final image classification based on a pathologists-derived ground truth. Our image classification module achieves a classification accuracy of up to 92% on canine lymphoma data. Compared to the accuracy ranging from 66.67 to 84% achieved using measurements provided by three individual pathologists, our algorithm provides a higher accuracy level and reproducible results. Our workflow also demonstrates a high transferability to feline lymphoma, as shown by its accuracy of up to 84.21%, even though our workflow was not optimized for feline lymphoma images. By determining the nuclear size distribution in tumor areas, our workflow can assist pathologists in subtyping lymphoma based on the nuclei size and potentially improve reproducibility. Our proposed approach is modular and comprehensible, thus allowing adaptation for specific tasks and increasing the users' trust in computer-assisted image classification.
Collapse
Affiliation(s)
- Andreas Haghofer
- Bioinformatics Research Group, University of Applied Sciences Upper Austria, Softwarepark 11-13, 4232, Hagenberg, Austria.
- Department of Computer Science, Johannes Kepler University, Altenberger Straße 69, 4040, Linz, Austria.
| | - Andrea Fuchs-Baumgartinger
- Institute of Pathology, University of Veterinary Medicine Vienna, Veterinärplatz 1, 1210, Vienna, Austria
| | - Karoline Lipnik
- Institute of Pathology, University of Veterinary Medicine Vienna, Veterinärplatz 1, 1210, Vienna, Austria
| | - Robert Klopfleisch
- Institute of Veterinary Pathology, Freie Univerisität Berlin, Robert-von-Ostertag-Str. 15, 14163, Berlin, Germany
| | - Marc Aubreville
- Technische Hochschule Ingolstadt, Esplanade 10, 85049, Ingolstadt, Germany
| | - Josef Scharinger
- Institute of Computational Perception, Johannes Kepler University, Altenberger Straße 69, 4040, Linz, Austria
| | - Herbert Weissenböck
- Institute of Pathology, University of Veterinary Medicine Vienna, Veterinärplatz 1, 1210, Vienna, Austria
| | - Stephan M Winkler
- Bioinformatics Research Group, University of Applied Sciences Upper Austria, Softwarepark 11-13, 4232, Hagenberg, Austria
- Department of Computer Science, Johannes Kepler University, Altenberger Straße 69, 4040, Linz, Austria
| | - Christof A Bertram
- Institute of Pathology, University of Veterinary Medicine Vienna, Veterinärplatz 1, 1210, Vienna, Austria
| |
Collapse
|
21
|
Jia W, Shi W, Yao Q, Mao Z, Chen C, Fan AQ, Wang Y, Zhao Z, Li J, Song W. Identifying immune infiltration by deep learning to assess the prognosis of patients with hepatocellular carcinoma. J Cancer Res Clin Oncol 2023; 149:12621-12635. [PMID: 37450030 DOI: 10.1007/s00432-023-05097-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Accepted: 06/30/2023] [Indexed: 07/18/2023]
Abstract
BACKGROUND The treatment situation for hepatocellular carcinoma remains critical. The use of deep learning algorithms to assess immune infiltration is a promising new diagnostic tool. METHODS Patient data and whole slide images (WSIs) were obtained for the Xijing Hospital (XJH) cohort and TCGA cohort. We wrote programs using Visual studio 2022 with C# language to segment the WSI into tiles. Pathologists classified the tiles and later trained deep learning models using the ResNet 101V2 network via ML.NET with the TensorFlow framework. Model performance was evaluated using AccuracyMicro versus AccuracyMacro. Model performance was examined using ROC curves versus PR curves. The percentage of immune infiltration was calculated using the R package survminer to calculate the intergroup cutoff, and the Kaplan‒Meier method was used to plot the overall survival curve of patients. Cox regression was used to determine whether the percentage of immune infiltration was an independent risk factor for prognosis. A nomogram was constructed, and its accuracy was verified using time-dependent ROC curves with calibration curves. The CIBERSORT algorithm was used to assess immune infiltration between groups. Gene Ontology was used to explore the pathways of differentially expressed genes. RESULTS There were 100 WSIs and 165,293 tiles in the training set. The final deep learning models had an AccuracyMicro of 97.46% and an AccuracyMacro of 82.28%. The AUCs of the ROC curves on both the training and validation sets exceeded 0.95. The areas under the classification PR curves exceeded 0.85, except that of the TLS on the validation set, which might have had poor results (0.713) due to too few samples. There was a significant difference in OS between the TIL classification groups (p < 0.001), while there was no significant difference in OS between the TLS groups (p = 0.294). Cox regression showed that TIL percentage was an independent risk factor for prognosis in HCC patients (p = 0.015). The AUCs according to the nomogram were 0.714, 0.690, and 0.676 for the 1-year, 2-year, and 5-year AUCs in the TCGA cohort and 0.756, 0.797, and 0.883 in the XJH cohort, respectively. There were significant differences in the levels of infiltration of seven immune cell types between the two groups of samples, and gene ontology showed that the differentially expressed genes between the groups were immune related. Their expression levels of PD-1 and CTLA4 were also significantly different. CONCLUSION We constructed and tested a deep learning model that evaluates the immune infiltration of liver cancer tissue in HCC patients. Our findings demonstrate the value of the model in assessing patient prognosis, immune infiltration and immune checkpoint expression levels.
Collapse
Affiliation(s)
- Weili Jia
- Xi'an Medical University, Xi'an, China
- Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - Wen Shi
- Xi'an Medical University, Xi'an, China
- Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | | | - Zhenzhen Mao
- Xi'an Medical University, Xi'an, China
- Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - Chao Chen
- Xi'an Medical University, Xi'an, China
- Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - AQiang Fan
- Xi'an Medical University, Xi'an, China
- Department of Gastrointestinal Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - Yanfang Wang
- Xi'an Medical University, Xi'an, China
- Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - Zihao Zhao
- Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - Jipeng Li
- Department of Gastrointestinal Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China.
| | - Wenjie Song
- Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, China.
| |
Collapse
|
22
|
Gan J, Wang H, Yu H, He Z, Zhang W, Ma K, Zhu L, Bai Y, Zhou Z, Yullie A, Bai X, Wang M, Yang D, Chen Y, Chen G, Lasenby J, Cheng C, Wu J, Zhang J, Wang X, Chen Y, Wang G, Xia T. Focalizing regions of biomarker relevance facilitates biomarker prediction on histopathological images. iScience 2023; 26:107243. [PMID: 37767002 PMCID: PMC10520807 DOI: 10.1016/j.isci.2023.107243] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Revised: 05/11/2023] [Accepted: 06/26/2023] [Indexed: 09/29/2023] Open
Abstract
Image-based AI has thrived as a potentially revolutionary tool for predicting molecular biomarker statuses, which aids in categorizing patients for appropriate medical treatments. However, many methods using hematoxylin and eosin-stained (H&E) whole-slide images (WSIs) have been found to be inefficient because of the presence of numerous uninformative or irrelevant image patches. In this study, we introduced the region of biomarker relevance (ROB) concept to identify the morphological areas most closely associated with biomarkers for accurate status prediction. We actualized this concept within a framework called saliency ROB search (SRS) to enable efficient and effective predictions. By evaluating various lung adenocarcinoma (LUAD) biomarkers, we showcased the superior performance of SRS compared to current state-of-the-art AI approaches. These findings suggest that AI tools, built on the ROB concept, can achieve enhanced molecular biomarker prediction accuracy from pathological images.
Collapse
Affiliation(s)
- Jiefeng Gan
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
| | - Hanchen Wang
- Department of Engineering, University of Cambridge, Fitzwilliam House 32 Trumpington Street, Cambridge CB2 1QY, UK
- Computing + Mathematical Sciences Department, California Institute of Technology, 1200 East California Boulevard, Pasadena, CA 91125, USA
| | - Hui Yu
- Wuhan Children’s Hospital, Tongji Medical College, Wuhan, Hubei 430000, China
| | - Zitong He
- Department of Computer Science, Johns Hopkins University, 3400 N Charles St, Baltimore, MD 21218, USA
| | - Wenjuan Zhang
- Department of Pathology, Maternal and Child Hospital of Hubei Province, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 43000, China
| | - Ke Ma
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lianghui Zhu
- School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, Hubei 430000, China
| | - Yutong Bai
- Department of Computer Science, Johns Hopkins University, 3400 N Charles St, Baltimore, MD 21218, USA
| | - Zongwei Zhou
- Department of Computer Science, Johns Hopkins University, 3400 N Charles St, Baltimore, MD 21218, USA
| | - Alan Yullie
- Department of Computer Science, Johns Hopkins University, 3400 N Charles St, Baltimore, MD 21218, USA
| | - Xiang Bai
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 43000, China
| | - Mingwei Wang
- The National Center for Drug Screening, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai 201203, China
| | - Dehua Yang
- The National Center for Drug Screening, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai 201203, China
| | - Yanyan Chen
- Department of Information Management, Tongji Hospital, Huazhong University of Science and Technology, Wuhan, Hubei 430000, China
| | - Guoan Chen
- Wuhan Blood Center, Wuhan, Hubei 43000, China
| | - Joan Lasenby
- Department of Engineering, University of Cambridge, Fitzwilliam House 32 Trumpington Street, Cambridge CB2 1QY, UK
| | - Chao Cheng
- Baylor College of Medicine, One Baylor Plaza, Houston, TX 77030, USA
| | - Jia Wu
- Department of Radiation Oncology, Stanford University School of Medicine, 875 Blake Wilbur Dr, Palo Alto, CA 94304, USA
| | - Jianjun Zhang
- Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Xinggang Wang
- School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, Hubei 430000, China
| | - Yaobing Chen
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Guoping Wang
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Tian Xia
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|
23
|
Hoang DT, Dinstag G, Hermida LC, Ben-Zvi DS, Elis E, Caley K, Sammut SJ, Sinha S, Sinha N, Dampier CH, Stossel C, Patil T, Rajan A, Lassoued W, Strauss J, Bailey S, Allen C, Redman J, Beker T, Jiang P, Golan T, Wilkinson S, Sowalsky AG, Pine SR, Caldas C, Gulley JL, Aldape K, Aharonov R, Stone EA, Ruppin E. Prediction of cancer treatment response from histopathology images through imputed transcriptomics. RESEARCH SQUARE 2023:rs.3.rs-3193270. [PMID: 37790315 PMCID: PMC10543028 DOI: 10.21203/rs.3.rs-3193270/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/05/2023]
Abstract
Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin (H&E)-stained tumor slides for precision oncology. We present ENLIGHT-DeepPT, an approach for predicting response to multiple targeted and immunotherapies from H&E-slides. In difference from existing approaches that aim to predict treatment response directly from the slides, ENLIGHT-DeepPT is an indirect two-step approach consisting of (1) DeepPT, a new deep-learning framework that predicts genome-wide tumor mRNA expression from slides, and (2) ENLIGHT, which predicts response based on the DeepPT inferred expression values. DeepPT successfully predicts transcriptomics in all 16 TCGA cohorts tested and generalizes well to two independent datasets. Our key contribution is showing that ENLIGHT-DeepPT successfully predicts true responders in five independent patients' cohorts involving four different treatments spanning six cancer types with an overall odds ratio of 2.44, increasing the baseline response rate by 43.47% among predicted responders, without the need for any treatment data for training. Furthermore, its prediction accuracy on these datasets is comparable to a supervised approach predicting the response directly from the images, which needs to be trained and tested on the same cohort. ENLIGHT-DeepPT future application could provide clinicians with rapid treatment recommendations to an array of different therapies and importantly, may contribute to advancing precision oncology in developing countries.
Collapse
Affiliation(s)
- Danh-Tai Hoang
- Biological Data Science Institute, College of Science, Australian National University, Canberra, ACT, Australia
| | | | - Leandro C. Hermida
- Department of Immunology, University of Pittsburgh, Pittsburgh, PA, USA
- Tumor Microenvironment Center, UPMC Hillman Cancer Center, University of Pittsburgh, Pittsburgh, PA, USA
| | | | | | - Katherine Caley
- Biological Data Science Institute, College of Science, Australian National University, Canberra, ACT, Australia
| | - Stephen-John Sammut
- Breast Cancer Now Toby Robins Research Centre, The Institute of Cancer Research, London, United Kingdom
- The Royal Marsden Hospital NHS Foundation Trust, London, United Kingdom
- Cancer Research UK Cambridge Institute, University of Cambridge, Li Ka Shing Centre, Cambridge, UK
| | - Sanju Sinha
- Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Neelam Sinha
- Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Christopher H. Dampier
- Laboratory of Pathology, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Chani Stossel
- Oncology Institute, Sheba Medical Center at Tel-Hashomer, Tel Aviv University, Tel Aviv, Israel
| | - Tejas Patil
- Division of Medical Oncology, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Arun Rajan
- Thoracic and GI Malignancies Branch, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Wiem Lassoued
- Center for Immuno-Oncology, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Julius Strauss
- Center for Immuno-Oncology, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Shania Bailey
- Center for Immuno-Oncology, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Clint Allen
- Surgical Oncology Program, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Jason Redman
- Center for Immuno-Oncology, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | | | - Peng Jiang
- Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Talia Golan
- Oncology Institute, Sheba Medical Center at Tel-Hashomer, Tel Aviv University, Tel Aviv, Israel
| | - Scott Wilkinson
- Laboratory of Genitourinary Cancer Pathogenesis, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Adam G. Sowalsky
- Laboratory of Genitourinary Cancer Pathogenesis, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Sharon R. Pine
- Division of Medical Oncology, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Carlos Caldas
- Cancer Research UK Cambridge Institute, University of Cambridge, Li Ka Shing Centre, Cambridge, UK
| | - James L. Gulley
- Genitourinary Malignancy Branch, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | - Kenneth Aldape
- Laboratory of Pathology, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| | | | - Eric A. Stone
- Biological Data Science Institute, College of Science, Australian National University, Canberra, ACT, Australia
| | - Eytan Ruppin
- Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
| |
Collapse
|
24
|
Khoraminia F, Fuster S, Kanwal N, Olislagers M, Engan K, van Leenders GJLH, Stubbs AP, Akram F, Zuiverloon TCM. Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review. Cancers (Basel) 2023; 15:4518. [PMID: 37760487 PMCID: PMC10526515 DOI: 10.3390/cancers15184518] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 08/30/2023] [Accepted: 09/08/2023] [Indexed: 09/29/2023] Open
Abstract
Bladder cancer (BC) diagnosis and prediction of prognosis are hindered by subjective pathological evaluation, which may cause misdiagnosis and under-/over-treatment. Computational pathology (CPATH) can identify clinical outcome predictors, offering an objective approach to improve prognosis. However, a systematic review of CPATH in BC literature is lacking. Therefore, we present a comprehensive overview of studies that used CPATH in BC, analyzing 33 out of 2285 identified studies. Most studies analyzed regions of interest to distinguish normal versus tumor tissue and identify tumor grade/stage and tissue types (e.g., urothelium, stroma, and muscle). The cell's nuclear area, shape irregularity, and roundness were the most promising markers to predict recurrence and survival based on selected regions of interest, with >80% accuracy. CPATH identified molecular subtypes by detecting features, e.g., papillary structures, hyperchromatic, and pleomorphic nuclei. Combining clinicopathological and image-derived features improved recurrence and survival prediction. However, due to the lack of outcome interpretability and independent test datasets, robustness and clinical applicability could not be ensured. The current literature demonstrates that CPATH holds the potential to improve BC diagnosis and prediction of prognosis. However, more robust, interpretable, accurate models and larger datasets-representative of clinical scenarios-are needed to address artificial intelligence's reliability, robustness, and black box challenge.
Collapse
Affiliation(s)
- Farbod Khoraminia
- Department of Urology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands;
| | - Saul Fuster
- Department of Electrical Engineering and Computer Science, University of Stavanger, 4021 Stavanger, Norway; (S.F.); (N.K.); (K.E.)
| | - Neel Kanwal
- Department of Electrical Engineering and Computer Science, University of Stavanger, 4021 Stavanger, Norway; (S.F.); (N.K.); (K.E.)
| | - Mitchell Olislagers
- Department of Urology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands;
| | - Kjersti Engan
- Department of Electrical Engineering and Computer Science, University of Stavanger, 4021 Stavanger, Norway; (S.F.); (N.K.); (K.E.)
| | - Geert J. L. H. van Leenders
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands; (G.J.L.H.v.L.); (A.P.S.); (F.A.)
| | - Andrew P. Stubbs
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands; (G.J.L.H.v.L.); (A.P.S.); (F.A.)
| | - Farhan Akram
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands; (G.J.L.H.v.L.); (A.P.S.); (F.A.)
| | - Tahlita C. M. Zuiverloon
- Department of Urology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands;
| |
Collapse
|
25
|
Pizurica M, Larmuseau M, Van der Eecken K, de Schaetzen van Brienen L, Carrillo-Perez F, Isphording S, Lumen N, Van Dorpe J, Ost P, Verbeke S, Gevaert O, Marchal K. Whole Slide Imaging-Based Prediction of TP53 Mutations Identifies an Aggressive Disease Phenotype in Prostate Cancer. Cancer Res 2023; 83:2970-2984. [PMID: 37352385 PMCID: PMC10538366 DOI: 10.1158/0008-5472.can-22-3113] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2022] [Revised: 03/08/2023] [Accepted: 06/20/2023] [Indexed: 06/25/2023]
Abstract
In prostate cancer, there is an urgent need for objective prognostic biomarkers that identify the metastatic potential of a tumor at an early stage. While recent analyses indicated TP53 mutations as candidate biomarkers, molecular profiling in a clinical setting is complicated by tumor heterogeneity. Deep learning models that predict the spatial presence of TP53 mutations in whole slide images (WSI) offer the potential to mitigate this issue. To assess the potential of WSIs as proxies for spatially resolved profiling and as biomarkers for aggressive disease, we developed TiDo, a deep learning model that achieves state-of-the-art performance in predicting TP53 mutations from WSIs of primary prostate tumors. In an independent multifocal cohort, the model showed successful generalization at both the patient and lesion level. Analysis of model predictions revealed that false positive (FP) predictions could at least partially be explained by TP53 deletions, suggesting that some FP carry an alteration that leads to the same histological phenotype as TP53 mutations. Comparative expression and histologic cell type analyses identified a TP53-like cellular phenotype triggered by expression of pathways affecting stromal composition. Together, these findings indicate that WSI-based models might not be able to perfectly predict the spatial presence of individual TP53 mutations but they have the potential to elucidate the prognosis of a tumor by depicting a downstream phenotype associated with aggressive disease biomarkers. SIGNIFICANCE Deep learning models predicting TP53 mutations from whole slide images of prostate cancer capture histologic phenotypes associated with stromal composition, lymph node metastasis, and biochemical recurrence, indicating their potential as in silico prognostic biomarkers. See related commentary by Bordeleau, p. 2809.
Collapse
Affiliation(s)
- Marija Pizurica
- Internet Technology and Data Science Lab (IDLab/IMEC), Ghent University, Gent, Belgium
- Department of Plant biotechnology and Bioinformatics, Ghent University, Gent, Belgium
- Department of Biomedical Data Science, Stanford University, School of Medicine, Stanford, California
| | - Maarten Larmuseau
- Internet Technology and Data Science Lab (IDLab/IMEC), Ghent University, Gent, Belgium
- Department of Plant biotechnology and Bioinformatics, Ghent University, Gent, Belgium
| | | | - Louise de Schaetzen van Brienen
- Internet Technology and Data Science Lab (IDLab/IMEC), Ghent University, Gent, Belgium
- Department of Plant biotechnology and Bioinformatics, Ghent University, Gent, Belgium
| | - Francisco Carrillo-Perez
- Department of Architecture and Computer Technology (ATC), University of Granada, Granada, Spain
- Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, School of Medicine, Stanford, California
| | - Simon Isphording
- Internet Technology and Data Science Lab (IDLab/IMEC), Ghent University, Gent, Belgium
- Department of Plant biotechnology and Bioinformatics, Ghent University, Gent, Belgium
| | - Nicolaas Lumen
- Department of Urology, Ghent University Hospital, Ghent, Belgium
| | - Jo Van Dorpe
- Department of Urology, Ghent University Hospital, Ghent, Belgium
| | - Piet Ost
- Department of Radiotherapy, Ghent University Hospital, Ghent, Belgium
| | - Sofie Verbeke
- Department of Urology, Ghent University Hospital, Ghent, Belgium
| | - Olivier Gevaert
- Department of Biomedical Data Science, Stanford University, School of Medicine, Stanford, California
- Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, School of Medicine, Stanford, California
| | - Kathleen Marchal
- Internet Technology and Data Science Lab (IDLab/IMEC), Ghent University, Gent, Belgium
- Department of Plant biotechnology and Bioinformatics, Ghent University, Gent, Belgium
| |
Collapse
|
26
|
Nasrallah MP, Zhao J, Tsai CC, Meredith D, Marostica E, Ligon KL, Golden JA, Yu KH. Machine learning for cryosection pathology predicts the 2021 WHO classification of glioma. MED 2023; 4:526-540.e4. [PMID: 37421953 PMCID: PMC10527821 DOI: 10.1016/j.medj.2023.06.002] [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: 11/27/2022] [Revised: 04/17/2023] [Accepted: 06/06/2023] [Indexed: 07/10/2023]
Abstract
BACKGROUND Timely and accurate intraoperative cryosection evaluations remain the gold standard for guiding surgical treatments for gliomas. However, the tissue-freezing process often generates artifacts that make histologic interpretation difficult. In addition, the 2021 WHO Classification of Tumors of the Central Nervous System incorporates molecular profiles in the diagnostic categories, so standard visual evaluation of cryosections alone cannot completely inform diagnoses based on the new classification system. METHODS To address these challenges, we develop the context-aware Cryosection Histopathology Assessment and Review Machine (CHARM) using samples from 1,524 glioma patients from three different patient populations to systematically analyze cryosection slides. FINDINGS Our CHARM models successfully identified malignant cells (AUROC = 0.98 ± 0.01 in the independent validation cohort), distinguished isocitrate dehydrogenase (IDH)-mutant tumors from wild type (AUROC = 0.79-0.82), classified three major types of molecularly defined gliomas (AUROC = 0.88-0.93), and identified the most prevalent subtypes of IDH-mutant tumors (AUROC = 0.89-0.97). CHARM further predicts clinically important genetic alterations in low-grade glioma, including ATRX, TP53, and CIC mutations, CDKN2A/B homozygous deletion, and 1p/19q codeletion via cryosection images. CONCLUSIONS Our approaches accommodate the evolving diagnostic criteria informed by molecular studies, provide real-time clinical decision support, and will democratize accurate cryosection diagnoses. FUNDING Supported in part by the National Institute of General Medical Sciences grant R35GM142879, the Google Research Scholar Award, the Blavatnik Center for Computational Biomedicine Award, the Partners' Innovation Discovery Grant, and the Schlager Family Award for Early Stage Digital Health Innovations.
Collapse
Affiliation(s)
- MacLean P Nasrallah
- Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Junhan Zhao
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA
| | - Cheng Che Tsai
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA
| | - David Meredith
- Department of Pathology, Brigham and Women's Hospital, Boston, MA 02115, USA
| | - Eliana Marostica
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA; Division of Health Sciences and Technology, Harvard-Massachusetts Institute of Technology, Boston, MA 02139, USA
| | - Keith L Ligon
- Department of Pathology, Dana-Farber Cancer Institute, Boston, MA 02215, USA
| | - Jeffrey A Golden
- Department of Pathology, Brigham and Women's Hospital, Boston, MA 02115, USA; Department of Pathology, Cedars-Sinai Medical Center, Los Angeles, CA 90048, USA
| | - Kun-Hsing Yu
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA; Department of Pathology, Brigham and Women's Hospital, Boston, MA 02115, USA.
| |
Collapse
|
27
|
Mukashyaka P, Sheridan TB, Foroughi Pour A, Chuang JH. SAMPLER: Empirical distribution representations for rapid analysis of whole slide tissue images. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.08.01.551468. [PMID: 37577691 PMCID: PMC10418159 DOI: 10.1101/2023.08.01.551468] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/15/2023]
Abstract
Deep learning has revolutionized digital pathology, allowing for automatic analysis of hematoxylin and eosin (H&E) stained whole slide images (WSIs) for diverse tasks. In such analyses, WSIs are typically broken into smaller images called tiles, and a neural network backbone encodes each tile in a feature space. Many recent works have applied attention based deep learning models to aggregate tile-level features into a slide-level representation, which is then used for slide-level prediction tasks. However, training attention models is computationally intensive, necessitating hyperparameter optimization and specialized training procedures. Here, we propose SAMPLER, a fully statistical approach to generate efficient and informative WSI representations by encoding the empirical cumulative distribution functions (CDFs) of multiscale tile features. We demonstrate that SAMPLER-based classifiers are as accurate or better than state-of-the-art fully deep learning attention models for classification tasks including distinction of: subtypes of breast carcinoma (BRCA: AUC=0.911 ± 0.029); subtypes of non-small cell lung carcinoma (NSCLC: AUC=0.940±0.018); and subtypes of renal cell carcinoma (RCC: AUC=0.987±0.006). A major advantage of the SAMPLER representation is that predictive models are >100X faster compared to attention models. Histopathological review confirms that SAMPLER-identified high attention tiles contain tumor morphological features specific to the tumor type, while low attention tiles contain fibrous stroma, blood, or tissue folding artifacts. We further apply SAMPLER concepts to improve the design of attention-based neural networks, yielding a context aware multi-head attention model with increased accuracy for subtype classification within BRCA and RCC (BRCA: AUC=0.921±0.027, and RCC: AUC=0.988±0.010). Finally, we provide theoretical results identifying sufficient conditions for which SAMPLER is optimal. SAMPLER is a fast and effective approach for analyzing WSIs, with greatly improved scalability over attention methods to benefit digital pathology analysis.
Collapse
Affiliation(s)
- Patience Mukashyaka
- The Jackson Laboratory for Genomic Medicine, Farmington, CT
- University of Connecticut Health Center, Department of Genetics and Genome Sciences, Farmington, CT
| | - Todd B Sheridan
- The Jackson Laboratory for Genomic Medicine, Farmington, CT
- Department of Pathology, Hartford hospital, Hartford, CT
| | | | - Jeffrey H Chuang
- The Jackson Laboratory for Genomic Medicine, Farmington, CT
- University of Connecticut Health Center, Department of Genetics and Genome Sciences, Farmington, CT
| |
Collapse
|
28
|
Zhou J, Foroughi Pour A, Deirawan H, Daaboul F, Aung TN, Beydoun R, Ahmed FS, Chuang JH. Integrative deep learning analysis improves colon adenocarcinoma patient stratification at risk for mortality. EBioMedicine 2023; 94:104726. [PMID: 37499603 PMCID: PMC10388166 DOI: 10.1016/j.ebiom.2023.104726] [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: 01/12/2023] [Revised: 06/19/2023] [Accepted: 07/10/2023] [Indexed: 07/29/2023] Open
Abstract
BACKGROUND Colorectal cancers are the fourth most diagnosed cancer and the second leading cancer in number of deaths. Many clinical variables, pathological features, and genomic signatures are associated with patient risk, but reliable patient stratification in the clinic remains a challenging task. Here we assess how image, clinical, and genomic features can be combined to predict risk. METHODS We developed and evaluated integrative deep learning models combining formalin-fixed, paraffin-embedded (FFPE) whole slide images (WSIs), clinical variables, and mutation signatures to stratify colon adenocarcinoma (COAD) patients based on their risk of mortality. Our models were trained using a dataset of 108 patients from The Cancer Genome Atlas (TCGA), and were externally validated on newly generated dataset from Wayne State University (WSU) of 123 COAD patients and rectal adenocarcinoma (READ) patients in TCGA (N = 52). FINDINGS We first observe that deep learning models trained on FFPE WSIs of TCGA-COAD separate high-risk (OS < 3 years, N = 38) and low-risk (OS > 5 years, N = 25) patients (AUC = 0.81 ± 0.08, 5 year survival p < 0.0001, 5 year relative risk = 1.83 ± 0.04) though such models are less effective at predicting overall survival (OS) for moderate-risk (3 years < OS < 5 years, N = 45) patients (5 year survival p-value = 0.5, 5 year relative risk = 1.05 ± 0.09). We find that our integrative models combining WSIs, clinical variables, and mutation signatures can improve patient stratification for moderate-risk patients (5 year survival p < 0.0001, 5 year relative risk = 1.87 ± 0.07). Our integrative model combining image and clinical variables is also effective on an independent pathology dataset (WSU-COAD, N = 123) generated by our team (5 year survival p < 0.0001, 5 year relative risk = 1.52 ± 0.08), and the TCGA-READ data (5 year survival p < 0.0001, 5 year relative risk = 1.18 ± 0.17). Our multicenter integrative image and clinical model trained on combined TCGA-COAD and WSU-COAD is effective in predicting risk on TCGA-READ (5 year survival p < 0.0001, 5 year relative risk = 1.82 ± 0.13) data. Pathologist review of image-based heatmaps suggests that nuclear size pleomorphism, intense cellularity, and abnormal structures are associated with high-risk, while low-risk regions have more regular and small cells. Quantitative analysis shows high cellularity, high ratios of tumor cells, large tumor nuclei, and low immune infiltration are indicators of high-risk tiles. INTERPRETATION The improved stratification of colorectal cancer patients from our computational methods can be beneficial for treatment plans and enrollment of patients in clinical trials. FUNDING This study was supported by the National Cancer Institutes (Grant No. R01CA230031 and P30CA034196). The funders had no roles in study design, data collection and analysis or preparation of the manuscript.
Collapse
Affiliation(s)
- Jie Zhou
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Genetics and Genome Sciences, UCONN Health, Farmington, CT, USA
| | | | - Hany Deirawan
- Department of Pathology, Wayne State University, Detroit, MI, USA; Department of Dermatology, Wayne State University, Detroit, MI, USA
| | - Fayez Daaboul
- Department of Pathology, Wayne State University, Detroit, MI, USA
| | - Thazin Nwe Aung
- Department of Pathology, Yale University, New Haven, CT, USA
| | - Rafic Beydoun
- Department of Pathology, Wayne State University, Detroit, MI, USA
| | | | - Jeffrey H Chuang
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Genetics and Genome Sciences, UCONN Health, Farmington, CT, USA.
| |
Collapse
|
29
|
Azher ZL, Suvarna A, Chen JQ, Zhang Z, Christensen BC, Salas LA, Vaickus LJ, Levy JJ. Assessment of emerging pretraining strategies in interpretable multimodal deep learning for cancer prognostication. BioData Min 2023; 16:23. [PMID: 37481666 PMCID: PMC10363299 DOI: 10.1186/s13040-023-00338-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Accepted: 07/05/2023] [Indexed: 07/24/2023] Open
Abstract
BACKGROUND Deep learning models can infer cancer patient prognosis from molecular and anatomic pathology information. Recent studies that leveraged information from complementary multimodal data improved prognostication, further illustrating the potential utility of such methods. However, current approaches: 1) do not comprehensively leverage biological and histomorphological relationships and 2) make use of emerging strategies to "pretrain" models (i.e., train models on a slightly orthogonal dataset/modeling objective) which may aid prognostication by reducing the amount of information required for achieving optimal performance. In addition, model interpretation is crucial for facilitating the clinical adoption of deep learning methods by fostering practitioner understanding and trust in the technology. METHODS Here, we develop an interpretable multimodal modeling framework that combines DNA methylation, gene expression, and histopathology (i.e., tissue slides) data, and we compare performance of crossmodal pretraining, contrastive learning, and transfer learning versus the standard procedure. RESULTS Our models outperform the existing state-of-the-art method (average 11.54% C-index increase), and baseline clinically driven models (average 11.7% C-index increase). Model interpretations elucidate consideration of biologically meaningful factors in making prognosis predictions. DISCUSSION Our results demonstrate that the selection of pretraining strategies is crucial for obtaining highly accurate prognostication models, even more so than devising an innovative model architecture, and further emphasize the all-important role of the tumor microenvironment on disease progression.
Collapse
Affiliation(s)
- Zarif L Azher
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, USA
| | - Anish Suvarna
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, USA
| | - Ji-Qing Chen
- Cancer Biology Graduate Program, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
- Program in Quantitative Biomedical Sciences, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
- Department of Epidemiology, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
| | - Ze Zhang
- Program in Quantitative Biomedical Sciences, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
- Department of Epidemiology, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
| | - Brock C Christensen
- Department of Epidemiology, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
- Department of Molecular and Systems Biology, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
- Department of Community and Family Medicine, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
| | - Lucas A Salas
- Department of Epidemiology, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
- Department of Molecular and Systems Biology, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
- Integrative Neuroscience at Dartmouth (IND) Graduate Program, Dartmouth College Geisel School of Medicine, Hanover, NH, USA
| | - Louis J Vaickus
- Emerging Diagnostic and Investigative Technologies, Department of Pathology and Laboratory Medicine, Dartmouth Health, Lebanon, NH, USA
| | - Joshua J Levy
- Program in Quantitative Biomedical Sciences, Dartmouth College Geisel School of Medicine, Hanover, NH, USA.
- Department of Epidemiology, Dartmouth College Geisel School of Medicine, Hanover, NH, USA.
- Emerging Diagnostic and Investigative Technologies, Department of Pathology and Laboratory Medicine, Dartmouth Health, Lebanon, NH, USA.
- Department of Dermatology, Dartmouth Health, Lebanon, NH, USA.
| |
Collapse
|
30
|
Zhou C, Zhang YF, Guo S, Wang D, Lv HX, Qiao XN, Wang R, Chang DH, Zhao LM, Zhou FH. Multiparametric MRI radiomics in prostate cancer for predicting Ki-67 expression and Gleason score: a multicenter retrospective study. Discov Oncol 2023; 14:133. [PMID: 37470865 PMCID: PMC10361451 DOI: 10.1007/s12672-023-00752-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Accepted: 07/11/2023] [Indexed: 07/21/2023] Open
Abstract
PURPOSE Prostate cancer (PCa) with high Ki-67 expression and high Gleason Scores (GS) tends to have aggressive clinicopathological characteristics and a dismal prognosis. In order to predict the Ki-67 expression status and the GS in PCa, we sought to construct and verify MRI-based radiomics signatures. METHODS AND MATERIALS We collected T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) images from 170 PCa patients at three institutions and extracted 321 original radiomic features from each image modality. We used support vector machine (SVM) and least absolute shrinkage and selection operator (LASSO) logistic regression to select the most informative radiomic features and built predictive models using up sampling and feature selection techniques. Using receiver operating characteristic (ROC) analysis, the discriminating power of this feature was determined. Subsequent decision curve analysis (DCA) assessed the clinical utility of the radiomic features. The Kaplan-Meier (KM) test revealed that the radiomics-predicted Ki-67 expression status and GS were prognostic factors for PCa survival. RESULT The hypothesized radiomics signature, which included 15 and 9 selected radiomics features, respectively, was significantly correlated with pathological Ki-67 and GS outcomes in both the training and validation datasets. Areas under the curve (AUC) for the developed model were 0.813 (95% CI 0.681,0.930) and 0.793 (95% CI 0.621, 0.929) for the training and validation datasets, respectively, demonstrating discrimination and calibration performance. The model's clinical usefulness was verified using DCA. In both the training and validation sets, high Ki-67 expression and high GS predicted by radiomics using SVM models were substantially linked with poor overall survival (OS). CONCLUSIONS Both Ki-67 expression status and high GS correlate with PCa patient survival outcomes; therefore, the ability of the SVM classifier-based model to estimate Ki-67 expression status and the Lasso classifier-based model to assess high GS may enhance clinical decision-making.
Collapse
Affiliation(s)
- Chuan Zhou
- The First Clinical Medical College of Lanzhou University, Lanzhou, 73000, China
| | - Yun-Feng Zhang
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, China
| | - Sheng Guo
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, China
| | - Dong Wang
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, China
| | - Hao-Xuan Lv
- The First Clinical Medical College of Lanzhou University, Lanzhou, 73000, China
| | - Xiao-Ni Qiao
- Department of Information Management, Gansu Provincial Hospital, Lanzhou, 730000, China
| | - Rong Wang
- The First Clinical Medical College of Lanzhou University, Lanzhou, 73000, China
- Department of Nuclear Medicine, Gansu Provincial Hospital, Lanzhou, 730000, China
| | - De-Hui Chang
- Department of Urology, The 940 Hospital of Joint Logistics Support Force of Chinese PLA, Lanzhou, 730000, China
| | - Li-Ming Zhao
- Department of Urology, Second People's Hospital of Gansu Province, Lanzhou, 730000, China
| | - Feng-Hai Zhou
- The First Clinical Medical College of Lanzhou University, Lanzhou, 73000, China.
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, China.
- Department of Urology, Gansu Provincial Hospital, Lanzhou, 730000, China.
| |
Collapse
|
31
|
Wu Y, Li Y, Xiong X, Liu X, Lin B, Xu B. Recent advances of pathomics in colorectal cancer diagnosis and prognosis. Front Oncol 2023; 13:1094869. [PMID: 37538112 PMCID: PMC10396402 DOI: 10.3389/fonc.2023.1094869] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2022] [Accepted: 06/13/2023] [Indexed: 08/05/2023] Open
Abstract
Colorectal cancer (CRC) is one of the most common malignancies, with the third highest incidence and the second highest mortality in the world. To improve the therapeutic outcome, the risk stratification and prognosis predictions would help guide clinical treatment decisions. Achieving these goals have been facilitated by the fast development of artificial intelligence (AI) -based algorithms using radiological and pathological data, in combination with genomic information. Among them, features extracted from pathological images, termed pathomics, are able to reflect sub-visual characteristics linking to better stratification and prediction of therapeutic responses. In this paper, we review recent advances in pathological image-based algorithms in CRC, focusing on diagnosis of benign and malignant lesions, micro-satellite instability, as well as prediction of neoadjuvant chemoradiotherapy and the prognosis of CRC patients.
Collapse
Affiliation(s)
- Yihan Wu
- School of Medicine, Chongqing University, Chongqing, China
- Chongqing Key Laboratory of Intelligent Oncology for Breast Cancer, Chongqing University Cancer Hospital, Chongqing, China
| | - Yi Li
- Chongqing Key Laboratory of Intelligent Oncology for Breast Cancer, Chongqing University Cancer Hospital, Chongqing, China
- Bioengineering College, Chongqing University, Chongqing, China
| | - Xiaomin Xiong
- Chongqing Key Laboratory of Intelligent Oncology for Breast Cancer, Chongqing University Cancer Hospital, Chongqing, China
- Bioengineering College, Chongqing University, Chongqing, China
| | - Xiaohua Liu
- Bioengineering College, Chongqing University, Chongqing, China
| | - Bo Lin
- Chongqing Key Laboratory of Intelligent Oncology for Breast Cancer, Chongqing University Cancer Hospital, Chongqing, China
| | - Bo Xu
- School of Medicine, Chongqing University, Chongqing, China
- Chongqing Key Laboratory of Intelligent Oncology for Breast Cancer, Chongqing University Cancer Hospital, Chongqing, China
| |
Collapse
|
32
|
Predicting EGFR gene mutation status in lung adenocarcinoma based on multifeature fusion. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104786] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/09/2023]
|
33
|
Alam MR, Seo KJ, Abdul-Ghafar J, Yim K, Lee SH, Jang HJ, Jung CK, Chong Y. Recent application of artificial intelligence on histopathologic image-based prediction of gene mutation in solid cancers. Brief Bioinform 2023; 24:bbad151. [PMID: 37114657 DOI: 10.1093/bib/bbad151] [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: 12/26/2022] [Revised: 03/24/2023] [Accepted: 03/24/2023] [Indexed: 04/29/2023] Open
Abstract
PURPOSE Evaluation of genetic mutations in cancers is important because distinct mutational profiles help determine individualized drug therapy. However, molecular analyses are not routinely performed in all cancers because they are expensive, time-consuming and not universally available. Artificial intelligence (AI) has shown the potential to determine a wide range of genetic mutations on histologic image analysis. Here, we assessed the status of mutation prediction AI models on histologic images by a systematic review. METHODS A literature search using the MEDLINE, Embase and Cochrane databases was conducted in August 2021. The articles were shortlisted by titles and abstracts. After a full-text review, publication trends, study characteristic analysis and comparison of performance metrics were performed. RESULTS Twenty-four studies were found mostly from developed countries, and their number is increasing. The major targets were gastrointestinal, genitourinary, gynecological, lung and head and neck cancers. Most studies used the Cancer Genome Atlas, with a few using an in-house dataset. The area under the curve of some of the cancer driver gene mutations in particular organs was satisfactory, such as 0.92 of BRAF in thyroid cancers and 0.79 of EGFR in lung cancers, whereas the average of all gene mutations was 0.64, which is still suboptimal. CONCLUSION AI has the potential to predict gene mutations on histologic images with appropriate caution. Further validation with larger datasets is still required before AI models can be used in clinical practice to predict gene mutations.
Collapse
Affiliation(s)
- Mohammad Rizwan Alam
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Kyung Jin Seo
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Jamshid Abdul-Ghafar
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Kwangil Yim
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Sung Hak Lee
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Hyun-Jong Jang
- Catholic Big Data Integration Center, Department of Physiology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Chan Kwon Jung
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Yosep Chong
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| |
Collapse
|
34
|
Cao L, Wang J, Zhang Y, Rong Z, Wang M, Wang L, Ji J, Qian Y, Zhang L, Wu H, Song J, Liu Z, Wang W, Li S, Wang P, Xu Z, Zhang J, Zhao L, Wang H, Sun M, Huang X, Yin R, Lu Y, Liu Z, Deng K, Wang G, Qiu M, Li K, Wang J, Hou Y. E2EFP-MIL: End-to-end and high-generalizability weakly supervised deep convolutional network for lung cancer classification from whole slide image. Med Image Anal 2023; 88:102837. [PMID: 37216736 DOI: 10.1016/j.media.2023.102837] [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: 04/27/2022] [Revised: 03/11/2023] [Accepted: 05/05/2023] [Indexed: 05/24/2023]
Abstract
Efficient and accurate distinction of histopathological subtype of lung cancer is quite critical for the individualized treatment. So far, artificial intelligence techniques have been developed, whose performance yet remained debatable on more heterogenous data, hindering their clinical deployment. Here, we propose an end-to-end, well-generalized and data-efficient weakly supervised deep learning-based method. The method, end-to-end feature pyramid deep multi-instance learning model (E2EFP-MIL), contains an iterative sampling module, a trainable feature pyramid module and a robust feature aggregation module. E2EFP-MIL uses end-to-end learning to extract generalized morphological features automatically and identify discriminative histomorphological patterns. This method is trained with 1007 whole slide images (WSIs) of lung cancer from TCGA, with AUCs of 0.95-0.97 in test sets. We validated E2EFP-MIL in 5 real-world external heterogenous cohorts including nearly 1600 WSIs from both United States and China with AUCs of 0.94-0.97, and found that 100-200 training images are enough to achieve an AUC of >0.9. E2EFP-MIL overperforms multiple state-of-the-art MIL-based methods with high accuracy and low hardware requirements. Excellent and robust results prove generalizability and effectiveness of E2EFP-MIL in clinical practice. Our code is available at https://github.com/raycaohmu/E2EFP-MIL.
Collapse
Affiliation(s)
- Lei Cao
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Jie Wang
- Department of Tumor Biobank, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing 210009, China
| | - Yuanyuan Zhang
- Department of Pathology, Peking University People's Hospital, Beijing 100044, China
| | - Zhiwei Rong
- Department of Biostatistics, School of Public Health, Peking University, Beijing 100191, China
| | - Meng Wang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Liuying Wang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Jianxin Ji
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Youhui Qian
- Department of Thoracic Surgery, The First Affiliated Hospital of Shenzhen University, Shenzhen 518000, China
| | - Liuchao Zhang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Hao Wu
- Department of Thoracic Surgery, The First Affiliated Hospital of Shenzhen University, Shenzhen 518000, China
| | - Jiali Song
- Department of Biostatistics, School of Public Health, Peking University, Beijing 100191, China
| | - Zheng Liu
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing 100044, China
| | - Wenjie Wang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Shuang Li
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Peiyu Wang
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing 100044, China
| | - Zhenyi Xu
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Jingyuan Zhang
- Department of Pathology, Jiangsu Cancer Hospital, The Affiliated Cancer Hospital of Nanjing Medical University, Nanjing 210009, China
| | - Liang Zhao
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Hang Wang
- Department of Tumor Biobank, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing 210009, China
| | - Mengting Sun
- Department of Tumor Biobank, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing 210009, China
| | - Xing Huang
- Department of Pathology, Jiangsu Cancer Hospital, The Affiliated Cancer Hospital of Nanjing Medical University, Nanjing 210009, China
| | - Rong Yin
- Department of Thoracic Surgery, Jiangsu Key Laboratory of Molecular and Translational Cancer Research, Jiangsu Cancer Hospital, Nanjing 210009, China
| | - Yuhong Lu
- Department of Biostatistics, School of Public Health, Peking University, Beijing 100191, China
| | - Ziqian Liu
- Biostatistics and SAS Programming, Clinical Sciences, Johnson & Johnson Vision Care, Inc., FL 32256, US
| | - Kui Deng
- Division of Epidemiology, Department of Medicine, Vanderbilt Epidemiology Center, Vanderbilt University Medical Center, Nashville, TN 37232, US
| | - Gongwei Wang
- Department of Pathology, Peking University People's Hospital, Beijing 100044, China
| | - Mantang Qiu
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing 100044, China.
| | - Kang Li
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China.
| | - Jun Wang
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing 100044, China.
| | - Yan Hou
- Department of Biostatistics, School of Public Health, Peking University, Beijing 100191, China.
| |
Collapse
|
35
|
Alhazmi W, Turki T. Applying Deep Transfer Learning to Assess the Impact of Imaging Modalities on Colon Cancer Detection. Diagnostics (Basel) 2023; 13:diagnostics13101721. [PMID: 37238207 DOI: 10.3390/diagnostics13101721] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2023] [Revised: 05/04/2023] [Accepted: 05/11/2023] [Indexed: 05/28/2023] Open
Abstract
The use of medical images for colon cancer detection is considered an important problem. As the performance of data-driven methods relies heavily on the images generated by a medical method, there is a need to inform research organizations about the effective imaging modalities, when coupled with deep learning (DL), for detecting colon cancer. Unlike previous studies, this study aims to comprehensively report the performance behavior for detecting colon cancer using various imaging modalities coupled with different DL models in the transfer learning (TL) setting to report the best overall imaging modality and DL model for detecting colon cancer. Therefore, we utilized three imaging modalities, namely computed tomography, colonoscopy, and histology, using five DL architectures, including VGG16, VGG19, ResNet152V2, MobileNetV2, and DenseNet201. Next, we assessed the DL models on the NVIDIA GeForce RTX 3080 Laptop GPU (16GB GDDR6 VRAM) using 5400 processed images divided equally between normal colons and colons with cancer for each of the imaging modalities used. Comparing the imaging modalities when applied to the five DL models presented in this study and twenty-six ensemble DL models, the experimental results show that the colonoscopy imaging modality, when coupled with the DenseNet201 model under the TL setting, outperforms all the other models by generating the highest average performance result of 99.1% (99.1%, 99.8%, and 99.1%) based on the accuracy results (AUC, precision, and F1, respectively).
Collapse
Affiliation(s)
- Wael Alhazmi
- Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Turki Turki
- Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| |
Collapse
|
36
|
Kang H, Yang M, Zhang F, Xu H, Ren S, Li J, Chen D, Wang F, Li D, Chen X. Identification lymph node metastasis in esophageal squamous cell carcinoma using whole slide images and a hybrid network of multiple instance and transfer learning. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104577] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
|
37
|
Ameen YA, Badary DM, Abonnoor AEI, Hussain KF, Sewisy AA. Which data subset should be augmented for deep learning? a simulation study using urothelial cell carcinoma histopathology images. BMC Bioinformatics 2023; 24:75. [PMID: 36869300 PMCID: PMC9983182 DOI: 10.1186/s12859-023-05199-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2022] [Accepted: 02/21/2023] [Indexed: 03/05/2023] Open
Abstract
BACKGROUND Applying deep learning to digital histopathology is hindered by the scarcity of manually annotated datasets. While data augmentation can ameliorate this obstacle, its methods are far from standardized. Our aim was to systematically explore the effects of skipping data augmentation; applying data augmentation to different subsets of the whole dataset (training set, validation set, test set, two of them, or all of them); and applying data augmentation at different time points (before, during, or after dividing the dataset into three subsets). Different combinations of the above possibilities resulted in 11 ways to apply augmentation. The literature contains no such comprehensive systematic comparison of these augmentation ways. RESULTS Non-overlapping photographs of all tissues on 90 hematoxylin-and-eosin-stained urinary bladder slides were obtained. Then, they were manually classified as either inflammation (5948 images), urothelial cell carcinoma (5811 images), or invalid (3132 images; excluded). If done, augmentation was eight-fold by flipping and rotation. Four convolutional neural networks (Inception-v3, ResNet-101, GoogLeNet, and SqueezeNet), pre-trained on the ImageNet dataset, were fine-tuned to binary classify images of our dataset. This task was the benchmark for our experiments. Model testing performance was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve. Model validation accuracy was also estimated. The best testing performance was achieved when augmentation was done to the remaining data after test-set separation, but before division into training and validation sets. This leaked information between the training and the validation sets, as evidenced by the optimistic validation accuracy. However, this leakage did not cause the validation set to malfunction. Augmentation before test-set separation led to optimistic results. Test-set augmentation yielded more accurate evaluation metrics with less uncertainty. Inception-v3 had the best overall testing performance. CONCLUSIONS In digital histopathology, augmentation should include both the test set (after its allocation), and the remaining combined training/validation set (before being split into separate training and validation sets). Future research should try to generalize our results.
Collapse
Affiliation(s)
- Yusra A Ameen
- Department of Computer Science, Faculty of Computers and Information, Assiut University, Asyut, Egypt.
| | - Dalia M Badary
- Department of Pathology, Faculty of Medicine, Assiut University, Asyut, Egypt
| | | | - Khaled F Hussain
- Department of Computer Science, Faculty of Computers and Information, Assiut University, Asyut, Egypt
| | - Adel A Sewisy
- Department of Computer Science, Faculty of Computers and Information, Assiut University, Asyut, Egypt
| |
Collapse
|
38
|
Rubinstein JC, Foroughi Pour A, Zhou J, Sheridan TB, White BS, Chuang JH. Deep learning image analysis quantifies tumor heterogeneity and identifies microsatellite instability in colon cancer. J Surg Oncol 2023; 127:426-433. [PMID: 36251352 DOI: 10.1002/jso.27118] [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: 05/27/2022] [Revised: 09/09/2022] [Accepted: 09/24/2022] [Indexed: 02/01/2023]
Abstract
BACKGROUND AND OBJECTIVES Deep learning utilizing convolutional neural networks (CNNs) applied to hematoxylin & eosin (H&E)-stained slides numerically encodes histomorphological tumor features. Tumor heterogeneity is an emerging biomarker in colon cancer that is, captured by these features, whereas microsatellite instability (MSI) is an established biomarker traditionally assessed by immunohistochemistry or polymerase chain reaction. METHODS H&E-stained slides from The Cancer Genome Atlas (TCGA) colon cohort are passed through the CNN. Resulting imaging features are used to cluster morphologically similar slide regions. Tile-level pairwise similarities are calculated and used to generate a tumor heterogeneity score (THS). Patient-level THS is then correlated with TCGA-reported biomarkers, including MSI-status. RESULTS H&E-stained images from 313 patients generated 534 771 tiles. Deep learning automatically identified and annotated cells by type and clustered morphologically similar slide regions. MSI-high tumors demonstrated significantly higher THS than MSS/MSI-low (p < 0.001). THS was higher in MLH1-silent versus non-silent tumors (p < 0.001). The sequencing derived MSIsensor score also correlated with THS (r = 0.51, p < 0.0001). CONCLUSIONS Deep learning provides spatially resolved visualization of imaging-derived biomarkers and automated quantification of tumor heterogeneity. Our novel THS correlates with MSI-status, indicating that with expanded training sets, translational tools could be developed that predict MSI-status using H&E-stained images alone.
Collapse
Affiliation(s)
- Jill C Rubinstein
- The Jackson Laboratory for Genomic Medicine, Farmington, Connecticut, USA.,University of Connecticut School of Medicine, Farmington, Connecticut, USA.,Hartford Healthcare, Hartford, Connecticut, USA
| | - Ali Foroughi Pour
- The Jackson Laboratory for Genomic Medicine, Farmington, Connecticut, USA
| | - Jie Zhou
- The Jackson Laboratory for Genomic Medicine, Farmington, Connecticut, USA
| | - Todd B Sheridan
- The Jackson Laboratory for Genomic Medicine, Farmington, Connecticut, USA.,Hartford Healthcare, Hartford, Connecticut, USA
| | - Brian S White
- The Jackson Laboratory for Genomic Medicine, Farmington, Connecticut, USA
| | - Jeffrey H Chuang
- The Jackson Laboratory for Genomic Medicine, Farmington, Connecticut, USA
| |
Collapse
|
39
|
Wen Z, Wang S, Yang DM, Xie Y, Chen M, Bishop J, Xiao G. Deep learning in digital pathology for personalized treatment plans of cancer patients. Semin Diagn Pathol 2023; 40:109-119. [PMID: 36890029 DOI: 10.1053/j.semdp.2023.02.003] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/12/2023] [Accepted: 02/22/2023] [Indexed: 02/27/2023]
Abstract
Over the past decade, many new cancer treatments have been developed and made available to patients. However, in most cases, these treatments only benefit a specific subgroup of patients, making the selection of treatment for a specific patient an essential but challenging task for oncologists. Although some biomarkers were found to associate with treatment response, manual assessment is time-consuming and subjective. With the rapid developments and expanded implementation of artificial intelligence (AI) in digital pathology, many biomarkers can be quantified automatically from histopathology images. This approach allows for a more efficient and objective assessment of biomarkers, aiding oncologists in formulating personalized treatment plans for cancer patients. This review presents an overview and summary of the recent studies on biomarker quantification and treatment response prediction using hematoxylin-eosin (H&E) stained pathology images. These studies have shown that an AI-based digital pathology approach can be practical and will become increasingly important in improving the selection of cancer treatments for patients.
Collapse
Affiliation(s)
- Zhuoyu Wen
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Shidan Wang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Donghan M Yang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Yang Xie
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX, USA; Simmons Comprehensive Cancer Center, UT Southwestern Medical Center, Dallas, TX, USA; Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Mingyi Chen
- Department of Bioinformatics, UT Southwestern Medical Center, Dallas, TX, USA
| | - Justin Bishop
- Department of Bioinformatics, UT Southwestern Medical Center, Dallas, TX, USA
| | - Guanghua Xiao
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX, USA; Simmons Comprehensive Cancer Center, UT Southwestern Medical Center, Dallas, TX, USA; Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USA.
| |
Collapse
|
40
|
Predicting gene mutation status via artificial intelligence technologies based on multimodal integration (MMI) to advance precision oncology. Semin Cancer Biol 2023; 91:1-15. [PMID: 36801447 DOI: 10.1016/j.semcancer.2023.02.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2022] [Revised: 01/30/2023] [Accepted: 02/15/2023] [Indexed: 02/21/2023]
Abstract
Personalized treatment strategies for cancer frequently rely on the detection of genetic alterations which are determined by molecular biology assays. Historically, these processes typically required single-gene sequencing, next-generation sequencing, or visual inspection of histopathology slides by experienced pathologists in a clinical context. In the past decade, advances in artificial intelligence (AI) technologies have demonstrated remarkable potential in assisting physicians with accurate diagnosis of oncology image-recognition tasks. Meanwhile, AI techniques make it possible to integrate multimodal data such as radiology, histology, and genomics, providing critical guidance for the stratification of patients in the context of precision therapy. Given that the mutation detection is unaffordable and time-consuming for a considerable number of patients, predicting gene mutations based on routine clinical radiological scans or whole-slide images of tissue with AI-based methods has become a hot issue in actual clinical practice. In this review, we synthesized the general framework of multimodal integration (MMI) for molecular intelligent diagnostics beyond standard techniques. Then we summarized the emerging applications of AI in the prediction of mutational and molecular profiles of common cancers (lung, brain, breast, and other tumor types) pertaining to radiology and histology imaging. Furthermore, we concluded that there truly exist multiple challenges of AI techniques in the way of its real-world application in the medical field, including data curation, feature fusion, model interpretability, and practice regulations. Despite these challenges, we still prospect the clinical implementation of AI as a highly potential decision-support tool to aid oncologists in future cancer treatment management.
Collapse
|
41
|
Miyagawa C, Nakai H, Otani T, Murakami R, Takamura S, Takaya H, Murakami K, Mandai M, Matsumura N. Histopathological subtyping of high-grade serous ovarian cancer using whole slide imaging. J Gynecol Oncol 2023:34.e47. [PMID: 36807749 DOI: 10.3802/jgo.2023.34.e47] [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: 09/19/2022] [Revised: 01/02/2023] [Accepted: 01/18/2023] [Indexed: 02/16/2023] Open
Abstract
OBJECTIVE We have established 4 histopathologic subtyping of high-grade serous ovarian cancer (HGSOC) and reported that the mesenchymal transition (MT) type has a worse prognosis than the other subtypes. In this study, we modified the histopathologic subtyping algorithm to achieve high interobserver agreement in whole slide imaging (WSI) and to characterize the tumor biology of MT type for treatment individualization. METHODS Four observers performed histopathological subtyping using WSI of HGSOC in The Cancer Genome Atlas data. As a validation set, cases from Kindai and Kyoto Universities were independently evaluated by the 4 observers to determine concordance rates. In addition, genes highly expressed in MT type were examined by gene ontology term analysis. Immunohistochemistry was also performed to validate the pathway analysis. RESULTS After algorithm modification, the kappa coefficient, which indicates interobserver agreement, was greater than 0.5 (moderate agreement) for the 4 classifications and greater than 0.7 (substantial agreement) for the 2 classifications (MT vs. non-MT). Gene expression analysis showed that gene ontology terms related to angiogenesis and immune response were enriched in the genes highly expressed in the MT type. CD31 positive microvessel density was higher in the MT type compared to the non-MT type, and tumor groups with high infiltration of CD8/CD103 positive immune cells were observed in the MT type. CONCLUSION We developed an algorithm for reproducible histopathologic subtyping classification of HGSOC using WSI. The results of this study may be useful for treatment individualization of HGSOC, including angiogenesis inhibitors and immunotherapy.
Collapse
Affiliation(s)
- Chiho Miyagawa
- Department of Obstetrics and Gynecology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan
| | - Hidekatsu Nakai
- Department of Obstetrics and Gynecology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan.
| | - Tomoyuki Otani
- Department of Pathology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan
| | - Ryusuke Murakami
- Department of Gynecology and Obstetrics, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Shiki Takamura
- Department of Immunology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan
| | - Hisamitsu Takaya
- Department of Obstetrics and Gynecology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan
| | - Kosuke Murakami
- Department of Obstetrics and Gynecology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan
| | - Masaki Mandai
- Department of Gynecology and Obstetrics, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Noriomi Matsumura
- Department of Obstetrics and Gynecology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan
| |
Collapse
|
42
|
Using deep learning to predict survival outcome in non-surgical cervical cancer patients based on pathological images. J Cancer Res Clin Oncol 2023:10.1007/s00432-022-04446-8. [PMID: 36653539 PMCID: PMC10356676 DOI: 10.1007/s00432-022-04446-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2022] [Accepted: 10/19/2022] [Indexed: 01/20/2023]
Abstract
PURPOSE We analyzed clinical features and the representative HE-stained pathologic images to predict 5-year overall survival via the deep-learning approach in cervical cancer patients in order to assist oncologists in designing the optimal treatment strategies. METHODS The research retrospectively collected 238 non-surgical cervical cancer patients treated with radiochemotherapy from 2014 to 2017. These patients were randomly divided into the training set (n = 165) and test set (n = 73). Then, we extract deep features after segmenting the HE-stained image into patches of size 224 × 224. A Lasso-Cox model was constructed with clinical data to predict 5-year OS. C-index evaluated this model performance with 95% CI, calibration curve, and ROC. RESULTS Based on multivariate analysis, 2 of 11 clinical characteristics (C-index 0.68) and 2 of 2048 pathomic features (C-index 0.74) and clinical-pathomic model (C-index 0.83) of nomograms predict 5-year survival in the training set, respectively. In test set, compared with the pathomic and clinical characteristics used alone, the clinical-pathomic model had an AUC of 0.750 (95% CI 0.540-0.959), the clinical predictor model had an AUC of 0.729 (95% CI 0.551-0.909), and the pathomic model AUC was 0.703 (95% CI 0.487-0.919). Based on appropriate nomogram scores, we divided patients into high-risk and low-risk groups, and Kaplan-Meier survival probability curves for both groups showed statistical differences. CONCLUSION We built a clinical-pathomic model to predict 5-year OS in non-surgical cervical cancer patients, which may be a promising method to improve the precision of personalized therapy.
Collapse
|
43
|
Jiang Y, Sui X, Ding Y, Xiao W, Zheng Y, Zhang Y. A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis. Front Oncol 2023; 12:1044026. [PMID: 36698401 PMCID: PMC9870542 DOI: 10.3389/fonc.2022.1044026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2022] [Accepted: 12/06/2022] [Indexed: 01/12/2023] Open
Abstract
Introduction Manual inspection of histopathological images is important in clinical cancer diagnosis. Pathologists implement pathological diagnosis and prognostic evaluation through the microscopic examination of histopathological slices. This entire process is time-consuming, laborious, and challenging for pathologists. The modern use of whole-slide imaging, which scans histopathology slides to digital slices, and analysis using computer-aided diagnosis is an essential problem. Methods To solve the problem of difficult labeling of histopathological data, and improve the flexibility of histopathological analysis in clinical applications, we herein propose a semi-supervised learning algorithm coupled with consistency regularization strategy, called"Semi- supervised Histopathology Analysis Network"(Semi-His-Net), for automated normal-versus-tumor and subtype classifications. Specifically, when inputted disturbing versions of the same image, the model should predict similar outputs. Based on this, the model itself can assign artificial labels to unlabeled data for subsequent model training, thereby effectively reducing the labeled data required for training. Results Our Semi-His-Net is able to classify patches from breast cancer histopathological images into normal tissue and three other different tumor subtypes, achieving an accuracy was 90%. The average AUC of cross-classification between tumors reached 0.893. Discussion To overcome the limitations of visual inspection by pathologists for histopathology images, such as long time and low repeatability, we have developed a deep learning-based framework (Semi-His-Net) for automatic classification subdivision of the subtypes contained in the whole pathological images. This learning-based framework has great potential to improve the efficiency and repeatability of histopathological image diagnosis.
Collapse
Affiliation(s)
- Yanyun Jiang
- School of Mathematics and Statistics, Shandong Normal University, Jinan, China
| | - Xiaodan Sui
- School of Mathematics and Statistics, Shandong Normal University, Jinan, China
| | - Yanhui Ding
- School of Mathematics and Statistics, Shandong Normal University, Jinan, China
| | - Wei Xiao
- Shandong Provincial Hospital, Shandong University, Jinan, China
| | - Yuanjie Zheng
- School of Mathematics and Statistics, Shandong Normal University, Jinan, China,*Correspondence: Yuanjie Zheng, ; Yongxin Zhang,
| | - Yongxin Zhang
- School of Mathematics and Statistics, Shandong Normal University, Jinan, China,*Correspondence: Yuanjie Zheng, ; Yongxin Zhang,
| |
Collapse
|
44
|
Dogar GM, Shahzad M, Fraz MM. Attention augmented distance regression and classification network for nuclei instance segmentation and type classification in histology images. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104199] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
|
45
|
Gao Z, Hong B, Li Y, Zhang X, Wu J, Wang C, Zhang X, Gong T, Zheng Y, Meng D, Li C. A semi-supervised multi-task learning framework for cancer classification with weak annotation in whole-slide images. Med Image Anal 2023; 83:102652. [PMID: 36327654 DOI: 10.1016/j.media.2022.102652] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2021] [Revised: 09/15/2022] [Accepted: 10/08/2022] [Indexed: 11/06/2022]
Abstract
Cancer region detection (CRD) and subtyping are two fundamental tasks in digital pathology image analysis. The development of data-driven models for CRD and subtyping on whole-slide images (WSIs) would mitigate the burden of pathologists and improve their accuracy in diagnosis. However, the existing models are facing two major limitations. Firstly, they typically require large-scale datasets with precise annotations, which contradicts with the original intention of reducing labor effort. Secondly, for the subtyping task, the non-cancerous regions are treated as the same as cancerous regions within a WSI, which confuses a subtyping model in its training process. To tackle the latter limitation, the previous research proposed to perform CRD first for ruling out the non-cancerous region, then train a subtyping model based on the remaining cancerous patches. However, separately training ignores the interaction of these two tasks, also leads to propagating the error of the CRD task to the subtyping task. To address these issues and concurrently improve the performance on both CRD and subtyping tasks, we propose a semi-supervised multi-task learning (MTL) framework for cancer classification. Our framework consists of a backbone feature extractor, two task-specific classifiers, and a weight control mechanism. The backbone feature extractor is shared by two task-specific classifiers, such that the interaction of CRD and subtyping tasks can be captured. The weight control mechanism preserves the sequential relationship of these two tasks and guarantees the error back-propagation from the subtyping task to the CRD task under the MTL framework. We train the overall framework in a semi-supervised setting, where datasets only involve small quantities of annotations produced by our minimal point-based (min-point) annotation strategy. Extensive experiments on four large datasets with different cancer types demonstrate the effectiveness of the proposed framework in both accuracy and generalization.
Collapse
Affiliation(s)
- Zeyu Gao
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an 710049, China
| | - Bangyang Hong
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an 710049, China
| | - Yang Li
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an 710049, China
| | - Xianli Zhang
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an 710049, China
| | - Jialun Wu
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an 710049, China
| | - Chunbao Wang
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Department of Pathology, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an 710061, China
| | - Xiangrong Zhang
- School of Artificial Intelligence, Xidian University, Xi'an 710071, China
| | - Tieliang Gong
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an 710049, China
| | - Yefeng Zheng
- Tencent Jarvis Lab, Shenzhen, Guangdong 518075, China
| | - Deyu Meng
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an 710049, China
| | - Chen Li
- School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an 710049, China.
| |
Collapse
|
46
|
Artificial intelligence: A review of current applications in hepatocellular carcinoma imaging. Diagn Interv Imaging 2023; 104:24-36. [PMID: 36272931 DOI: 10.1016/j.diii.2022.10.001] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2022] [Accepted: 10/03/2022] [Indexed: 01/10/2023]
Abstract
Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and currently the third-leading cause of cancer-related death worldwide. Recently, artificial intelligence (AI) has emerged as an important tool to improve clinical management of HCC, including for diagnosis, prognostication and evaluation of treatment response. Different AI approaches, such as machine learning and deep learning, are both based on the concept of developing prediction algorithms from large amounts of data, or big data. The era of digital medicine has led to a rapidly expanding amount of routinely collected health data which can be leveraged for the development of AI models. Various studies have constructed AI models by using features extracted from ultrasound imaging, computed tomography imaging and magnetic resonance imaging. Most of these models have used convolutional neural networks. These tools have shown promising results for HCC detection, characterization of liver lesions and liver/tumor segmentation. Regarding treatment, studies have outlined a role for AI in evaluation of treatment response and improvement of pre-treatment planning. Several challenges remain to fully integrate AI models in clinical practice. Future research is still needed to robustly evaluate AI algorithms in prospective trials, and improve interpretability, generalizability and transparency. If such challenges can be overcome, AI has the potential to profoundly change the management of patients with HCC. The purpose of this review was to sum up current evidence on AI approaches using imaging for the clinical management of HCC.
Collapse
|
47
|
Biomarker Discovery for Meta-Classification of Melanoma Metastatic Progression Using Transfer Learning. Genes (Basel) 2022; 13:genes13122303. [PMID: 36553569 PMCID: PMC9777873 DOI: 10.3390/genes13122303] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Accepted: 12/02/2022] [Indexed: 12/12/2022] Open
Abstract
Melanoma is considered to be the most serious and aggressive type of skin cancer, and metastasis appears to be the most important factor in its prognosis. Herein, we developed a transfer learning-based biomarker discovery model that could aid in the diagnosis and prognosis of this disease. After applying it to the ensemble machine learning model, results revealed that the genes found were consistent with those found using other methodologies previously applied to the same TCGA (The Cancer Genome Atlas) data set. Further novel biomarkers were also found. Our ensemble model achieved an AUC of 0.9861, an accuracy of 91.05, and an F1 score of 90.60 using an independent validation data set. This study was able to identify potential genes for diagnostic classification (C7 and GRIK5) and diagnostic and prognostic biomarkers (S100A7, S100A7, KRT14, KRT17, KRT6B, KRTDAP, SERPINB4, TSHR, PVRL4, WFDC5, IL20RB) in melanoma. The results show the utility of a transfer learning approach for biomarker discovery in melanoma.
Collapse
|
48
|
Tharwat M, Sakr NA, El-Sappagh S, Soliman H, Kwak KS, Elmogy M. Colon Cancer Diagnosis Based on Machine Learning and Deep Learning: Modalities and Analysis Techniques. SENSORS (BASEL, SWITZERLAND) 2022; 22:9250. [PMID: 36501951 PMCID: PMC9739266 DOI: 10.3390/s22239250] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Accepted: 11/24/2022] [Indexed: 06/17/2023]
Abstract
The treatment and diagnosis of colon cancer are considered to be social and economic challenges due to the high mortality rates. Every year, around the world, almost half a million people contract cancer, including colon cancer. Determining the grade of colon cancer mainly depends on analyzing the gland's structure by tissue region, which has led to the existence of various tests for screening that can be utilized to investigate polyp images and colorectal cancer. This article presents a comprehensive survey on the diagnosis of colon cancer. This covers many aspects related to colon cancer, such as its symptoms and grades as well as the available imaging modalities (particularly, histopathology images used for analysis) in addition to common diagnosis systems. Furthermore, the most widely used datasets and performance evaluation metrics are discussed. We provide a comprehensive review of the current studies on colon cancer, classified into deep-learning (DL) and machine-learning (ML) techniques, and we identify their main strengths and limitations. These techniques provide extensive support for identifying the early stages of cancer that lead to early treatment of the disease and produce a lower mortality rate compared with the rate produced after symptoms develop. In addition, these methods can help to prevent colorectal cancer from progressing through the removal of pre-malignant polyps, which can be achieved using screening tests to make the disease easier to diagnose. Finally, the existing challenges and future research directions that open the way for future work in this field are presented.
Collapse
Affiliation(s)
- Mai Tharwat
- Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt
| | - Nehal A. Sakr
- Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt
| | - Shaker El-Sappagh
- Information Systems Department, Faculty of Computers and Artificial Intelligence, Benha University, Benha 13512, Egypt
- Faculty of Computer Science and Engineering, Galala University, Suez 435611, Egypt
| | - Hassan Soliman
- Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt
| | - Kyung-Sup Kwak
- Department of Information and Communication Engineering, Inha University, Incheon 22212, Republic of Korea
| | - Mohammed Elmogy
- Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt
| |
Collapse
|
49
|
Ding K, Zhou M, Wang H, Zhang S, Metaxas DN. Spatially aware graph neural networks and cross-level molecular profile prediction in colon cancer histopathology: a retrospective multi-cohort study. Lancet Digit Health 2022; 4:e787-e795. [DOI: 10.1016/s2589-7500(22)00168-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2021] [Revised: 06/28/2022] [Accepted: 08/15/2022] [Indexed: 11/05/2022]
|
50
|
Lee SH, Jang HJ. Deep learning-based prediction of molecular cancer biomarkers from tissue slides: A new tool for precision oncology. Clin Mol Hepatol 2022; 28:754-772. [PMID: 35443570 PMCID: PMC9597228 DOI: 10.3350/cmh.2021.0394] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/20/2021] [Accepted: 04/17/2022] [Indexed: 02/06/2023] Open
Abstract
Molecular tests are necessary to stratify cancer patients for targeted therapy. However, high cost and technical barriers limit the application of these tests, hindering optimal treatment. Recently, deep learning (DL) has been applied to predict molecular test results from digitized images of tissue slides. Furthermore, treatment response and prognosis can be predicted from tissue slides using DL. In this review, we summarized DL-based studies regarding the prediction of genetic mutation, microsatellite instability, tumor mutational burden, molecular subtypes, gene expression, treatment response, and prognosis directly from hematoxylin- and eosin-stained tissue slides. Although performance needs to be improved, these studies clearly demonstrated the feasibility of DL-based prediction of key molecular features in cancer tissues. With the accumulation of data and technical advances, the performance of the DL system could be improved in the near future. Therefore, we expect that DL could provide cost- and time-effective alternative tools for patient stratification in the era of precision oncology.
Collapse
Affiliation(s)
- Sung Hak Lee
- Department of Hospital Pathology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Hyun-Jong Jang
- Catholic Big Data Integration Center, Department of Physiology, College of Medicine, The Catholic University of Korea, Seoul, Korea,Corresponding author : Hyun-Jong Jang Department of Physiology, College of Medicine, The Catholic University of Korea, 222 Banpo-daero, Seocho-gu, Seoul 06591, Korea Tel: +82-2-2258-7274, Fax: +82-2-532-9575, E-mail:
| |
Collapse
|