1
|
Huang CY, Chang RF, Lin CY, Hsieh MS, Liao PC, Wang YJ, Kao YC, Porta L, Lin PY, Lee CC, Lee YH. Deep-learning model to improve histological grading and predict upstaging of atypical ductal hyperplasia / ductal carcinoma in situ on breast biopsy. Histopathology 2024; 84:983-1002. [PMID: 38288642 DOI: 10.1111/his.15144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Revised: 01/02/2024] [Accepted: 01/06/2024] [Indexed: 04/04/2024]
Abstract
AIMS Risk stratification of atypical ductal hyperplasia (ADH) and ductal carcinoma in situ (DCIS), diagnosed using breast biopsy, has great clinical significance. Clinical trials are currently exploring the possibility of active surveillance for low-risk lesions, whereas axillary lymph node staging may be considered during surgical planning for high-risk lesions. We aimed to develop a machine-learning algorithm based on whole-slide images of breast biopsy specimens and clinical information to predict the risk of upstaging to invasive breast cancer after wide excision. METHODS AND RESULTS Patients diagnosed with ADH/DCIS on breast biopsy were included in this study, comprising 592 (740 slides) and 141 (198 slides) patients in the development and independent testing cohorts, respectively. Histological grading of the lesions was independently evaluated by two pathologists. Clinical information, including biopsy method, lesion size, and Breast Imaging Reporting and Data System (BI-RADS) classification of ultrasound and mammograms, were collected. Deep DCIS consisted of three deep neural networks to evaluate nuclear grade, necrosis, and stromal reactivity. Deep DCIS output comprised five parameters: total patches, lesion extent, Deep Grade, Deep Necrosis, and Deep Stroma. Deep DCIS highly correlated with the pathologists' evaluations of both slide- and patient-level labels. All five parameters of Deep DCIS were significantly associated with upstaging to invasive carcinoma in subsequent wide excisional specimens. Using multivariate logistic regression, Deep DCIS predicted upstaging to invasive carcinoma with an area under the curve (AUC) of 0.81, outperforming pathologists' evaluation (AUC, 0.71 and 0.69). After including clinical and hormone receptor status information, performance further improved (AUC, 0.87). This combined model retained its predictive power in two subgroup analyses: the first subgroup included unequivocal DCIS (excluding cases of ADH and DCIS suspicious for microinvasion) (AUC, 0.83), while the second excluded cases of high-grade DCIS (AUC, 0.81). The model was validated in an independent testing cohort (AUC, 0.81). CONCLUSION This study demonstrated that deep-learning models can refine histological evaluation of ADH and DCIS on breast biopsies, which may help guide future treatment planning.
Collapse
Affiliation(s)
- Chung-Yen Huang
- Department of Pathology, National Taiwan University Hospital, Taipei, Taiwan
| | - Ruey-Feng Chang
- Center for Intelligent Healthcare, National Taiwan University Hospital, Taipei, Taiwan
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan
| | - Chih-Yung Lin
- Center for Intelligent Healthcare, National Taiwan University Hospital, Taipei, Taiwan
| | - Min-Shu Hsieh
- Department of Pathology, National Taiwan University Hospital, Taipei, Taiwan
- Department of Pathology, National Taiwan University Cancer Center, Taipei, Taiwan
| | - Po-Chun Liao
- Department of Emergency Medicine, National Taiwan University Hospital, Taipei, Taiwan
| | - Yu-Jui Wang
- Department of Pathology, National Taiwan University Hospital, Taipei, Taiwan
| | - Yu-Chien Kao
- Department of Pathology, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan
| | - Lorenzo Porta
- School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy
- Department of Emergency Medicine, ASST Grande Ospedale Metropolitano Niguarda, Milan, Italy
| | - Pin-Yu Lin
- Department of Pathology, National Taiwan University Hospital, Taipei, Taiwan
| | - Chien-Chang Lee
- Center for Intelligent Healthcare, National Taiwan University Hospital, Taipei, Taiwan
- Department of Emergency Medicine, National Taiwan University Hospital, Taipei, Taiwan
| | - Yi-Hsuan Lee
- Department of Pathology, National Taiwan University Hospital, Taipei, Taiwan
| |
Collapse
|
2
|
Katayama A, Aoki Y, Watanabe Y, Horiguchi J, Rakha EA, Oyama T. Current status and prospects of artificial intelligence in breast cancer pathology: convolutional neural networks to prospective Vision Transformers. Int J Clin Oncol 2024:10.1007/s10147-024-02513-3. [PMID: 38619651 DOI: 10.1007/s10147-024-02513-3] [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: 01/16/2024] [Accepted: 03/12/2024] [Indexed: 04/16/2024]
Abstract
Breast cancer is the most prevalent cancer among women, and its diagnosis requires the accurate identification and classification of histological features for effective patient management. Artificial intelligence, particularly through deep learning, represents the next frontier in cancer diagnosis and management. Notably, the use of convolutional neural networks and emerging Vision Transformers (ViT) has been reported to automate pathologists' tasks, including tumor detection and classification, in addition to improving the efficiency of pathology services. Deep learning applications have also been extended to the prediction of protein expression, molecular subtype, mutation status, therapeutic efficacy, and outcome prediction directly from hematoxylin and eosin-stained slides, bypassing the need for immunohistochemistry or genetic testing. This review explores the current status and prospects of deep learning in breast cancer diagnosis with a focus on whole-slide image analysis. Artificial intelligence applications are increasingly applied to many tasks in breast pathology ranging from disease diagnosis to outcome prediction, thus serving as valuable tools for assisting pathologists and supporting breast cancer management.
Collapse
Affiliation(s)
- Ayaka Katayama
- Diagnostic Pathology, Gunma University Graduate School of Medicine, 3-39-22 Showamachi, Maebashi, Gunma, 371-8511, Japan.
| | - Yuki Aoki
- Center for Mathematics and Data Science, Gunma University, Maebashi, Japan
| | - Yukako Watanabe
- Clinical Training Center, Gunma University Hospital, Maebashi, Japan
| | - Jun Horiguchi
- Department of Breast Surgery, International University of Health and Welfare, Narita, Japan
| | - Emad A Rakha
- Department of Histopathology School of Medicine, University of Nottingham, University Park, Nottingham, UK
- Department of Pathology, Hamad Medical Corporation, Doha, Qatar
| | - Tetsunari Oyama
- Diagnostic Pathology, Gunma University Graduate School of Medicine, 3-39-22 Showamachi, Maebashi, Gunma, 371-8511, Japan
| |
Collapse
|
3
|
Sakashita M, Motoi N, Yamamoto G, Gambe E, Suzuki M, Yoshida Y, Watanabe SI, Takazawa Y, Aoki K, Ochiai A, Sakashita S. An algorithm-based technique for counting mitochondria in cells using immunohistochemical staining of formalin-fixed and paraffin-embedded sections. J Cancer Res Clin Oncol 2024; 150:172. [PMID: 38565653 PMCID: PMC10987345 DOI: 10.1007/s00432-024-05653-1] [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: 01/27/2024] [Accepted: 02/15/2024] [Indexed: 04/04/2024]
Abstract
PURPOSE Visualizing mitochondria in cancer cells from human pathological specimens may improve our understanding of cancer biology. However, using immunohistochemistry to evaluate mitochondria remains difficult because almost all cells contain mitochondria and the number of mitochondria per cell may have important effects on mitochondrial function. Herein, we established an objective system (Mito-score) for evaluating mitochondria using machine-based processing of hue, saturation, and value color spaces. METHODS The Mito-score was defined as the number of COX4 (mitochondrial inner membrane) immunohistochemistry-positive pixels divided by the number of nuclei per cell. The system was validated using four lung cancer cell lines, normal tissues, and lung cancer tissues (199 cases). RESULTS The Mito-score correlated with MitoTracker, a fluorescent dye used to selectively label and visualize mitochondria within cells under a microscope (R2 = 0.68) and with the number of mitochondria counted using electron microscopy (R2 = 0.79). Histologically, the Mito-score of small cell carcinoma (57.25) was significantly lower than that of adenocarcinoma (147.5, p < 0.0001), squamous cell carcinoma (120.6, p = 0.0004), and large cell neuroendocrine carcinoma (111.8, p = 0.002). CONCLUSION The Mito-score method enables the analysis of the mitochondrial status of human formalin-fixed paraffin-embedded specimens and may provide insights into the metabolic status of cancer.
Collapse
Affiliation(s)
- Mai Sakashita
- Division of Biomarker Discovery, Exploratory Oncology Research and Clinical Trial Center, National Cancer Center, Chiba, Japan
- Department of Pathology, Saitama Cancer Center, Saitama, Japan
| | - Noriko Motoi
- Department of Pathology, Saitama Cancer Center, Saitama, Japan
- Division of Genome Biology, National Cancer Center Research Institute, Tokyo, Japan
| | - Gaku Yamamoto
- Division of Translational Genomics, Exploratory Oncology Research and Clinical Trial Center, National Cancer Center, Kashiwa, Japan
| | - Emi Gambe
- Department of Pathology, Toranomon Hospital, Tokyo, Japan
| | | | - Yukihiro Yoshida
- Department of Thoracic Surgery, National Cancer Center Hospital, Tokyo, Japan
| | - Shun-Ichi Watanabe
- Department of Thoracic Surgery, National Cancer Center Hospital, Tokyo, Japan
| | | | - Kazunori Aoki
- Department of Immune Medicine, National Cancer Center Research Institute, Tokyo, Japan
| | - Atsushi Ochiai
- Research Institute for Biomedical Sciences, Tokyo University of Science, Tokyo, Japan
| | - Shingo Sakashita
- Division of Pathology, Exploratory Oncology Research and Clinical Trial Center, National Cancer Center, 6-5-1, Kashiwanoha, Kashiwa-Shi, Chiba, 277-8577, Japan.
| |
Collapse
|
4
|
Mudeng V, Farid MN, Ayana G, Choe SW. Domain and Histopathology Adaptations-Based Classification for Malignancy Grading System. THE AMERICAN JOURNAL OF PATHOLOGY 2023; 193:2080-2098. [PMID: 37673327 DOI: 10.1016/j.ajpath.2023.07.007] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/05/2023] [Revised: 06/30/2023] [Accepted: 07/19/2023] [Indexed: 09/08/2023]
Abstract
Accurate proliferation rate quantification can be used to devise an appropriate treatment for breast cancer. Pathologists use breast tissue biopsy glass slides stained with hematoxylin and eosin to obtain grading information. However, this manual evaluation may lead to high costs and be ineffective because diagnosis depends on the facility and the pathologists' insights and experiences. Convolutional neural network acts as a computer-based observer to improve clinicians' capacity in grading breast cancer. Therefore, this study proposes a novel scheme for automatic breast cancer malignancy grading from invasive ductal carcinoma. The proposed classifiers implement multistage transfer learning incorporating domain and histopathologic transformations. Domain adaptation using pretrained models, such as InceptionResNetV2, InceptionV3, NASNet-Large, ResNet50, ResNet101, VGG19, and Xception, was applied to classify the ×40 magnification BreaKHis data set into eight classes. Subsequently, InceptionV3 and Xception, which contain the domain and histopathology pretrained weights, were determined to be the best for this study and used to categorize the Databiox database into grades 1, 2, or 3. To provide a comprehensive report, this study offered a patchless automated grading system for magnification-dependent and magnification-independent classifications. With an overall accuracy (means ± SD) of 90.17% ± 3.08% to 97.67% ± 1.09% and an F1 score of 0.9013 to 0.9760 for magnification-dependent classification, the classifiers in this work achieved outstanding performance. The proposed approach could be used for breast cancer grading systems in clinical settings.
Collapse
Affiliation(s)
- Vicky Mudeng
- Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea; Department of Electrical Engineering, Institut Teknologi Kalimantan, Balikpapan, Indonesia
| | - Mifta Nur Farid
- Department of Electrical Engineering, Institut Teknologi Kalimantan, Balikpapan, Indonesia
| | - Gelan Ayana
- Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea
| | - Se-Woon Choe
- Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea; Department of IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea.
| |
Collapse
|
5
|
Verghese G, Lennerz JK, Ruta D, Ng W, Thavaraj S, Siziopikou KP, Naidoo T, Rane S, Salgado R, Pinder SE, Grigoriadis A. Computational pathology in cancer diagnosis, prognosis, and prediction - present day and prospects. J Pathol 2023; 260:551-563. [PMID: 37580849 PMCID: PMC10785705 DOI: 10.1002/path.6163] [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: 05/05/2023] [Revised: 06/12/2023] [Accepted: 06/17/2023] [Indexed: 08/16/2023]
Abstract
Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists' perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Collapse
Affiliation(s)
- Gregory Verghese
- School of Cancer & Pharmaceutical Sciences, Faculty of Life Sciences and MedicineKing's College LondonLondonUK
- The Breast Cancer Now Research Unit, School of Cancer and Pharmaceutical Sciences, Faculty of Life Sciences and MedicineKing's College LondonLondonUK
| | - Jochen K Lennerz
- Center for Integrated Diagnostics, Department of PathologyMassachusetts General Hospital/Harvard Medical SchoolBostonMAUSA
| | - Danny Ruta
- Guy's CancerGuy's and St Thomas’ NHS Foundation TrustLondonUK
| | - Wen Ng
- Department of Cellular PathologyGuy's and St Thomas NHS Foundation TrustLondonUK
| | - Selvam Thavaraj
- Head & Neck PathologyGuy's and St Thomas NHS Foundation TrustLondonUK
- Centre for Clinical, Oral & Translational Science, Faculty of Dentistry, Oral & Craniofacial SciencesKing's College LondonLondonUK
| | - Kalliopi P Siziopikou
- Department of Pathology, Section of Breast PathologyNorthwestern University Feinberg School of MedicineChicagoILUSA
| | - Threnesan Naidoo
- Department of Laboratory Medicine and Pathology, Walter Sisulu University, Mthatha, Eastern CapeSouth Africa and Africa Health Research InstituteDurbanSouth Africa
| | - Swapnil Rane
- Department of PathologyTata Memorial Centre – ACTRECHBNINavi MumbaiIndia
- Computational Pathology, AI & Imaging LaboratoryTata Memorial Centre – ACTREC, HBNINavi MumbaiIndia
| | - Roberto Salgado
- Department of PathologyGZA–ZNA ZiekenhuizenAntwerpBelgium
- Division of ResearchPeter MacCallum Cancer CentreMelbourneVictoriaAustralia
| | - Sarah E Pinder
- School of Cancer & Pharmaceutical Sciences, Faculty of Life Sciences and MedicineKing's College LondonLondonUK
- Department of Cellular PathologyGuy's and St Thomas NHS Foundation TrustLondonUK
| | - Anita Grigoriadis
- School of Cancer & Pharmaceutical Sciences, Faculty of Life Sciences and MedicineKing's College LondonLondonUK
- The Breast Cancer Now Research Unit, School of Cancer and Pharmaceutical Sciences, Faculty of Life Sciences and MedicineKing's College LondonLondonUK
| |
Collapse
|
6
|
Köteles MM, Vigdorovits A, Kumar D, Mihai IM, Jurescu A, Gheju A, Bucur A, Harich OO, Olteanu GE. Comparative Evaluation of Breast Ductal Carcinoma Grading: A Deep-Learning Model and General Pathologists' Assessment Approach. Diagnostics (Basel) 2023; 13:2326. [PMID: 37510069 PMCID: PMC10377791 DOI: 10.3390/diagnostics13142326] [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: 06/02/2023] [Revised: 07/05/2023] [Accepted: 07/07/2023] [Indexed: 07/30/2023] Open
Abstract
Breast cancer is the most prevalent neoplasia among women, with early and accurate diagnosis critical for effective treatment. In clinical practice, however, the subjective nature of histological grading of infiltrating ductal adenocarcinoma of the breast (DAC-NOS) often leads to inconsistencies among pathologists, posing a significant challenge to achieving optimal patient outcomes. Our study aimed to address this reproducibility problem by leveraging artificial intelligence (AI). We trained a deep-learning model using a convolutional neural network-based algorithm (CNN-bA) on 100 whole slide images (WSIs) of DAC-NOS from the Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA) dataset. Our model demonstrated high precision, sensitivity, and F1 score across different grading components in about 17.5 h with 19,000 iterations. However, the agreement between the model's grading and that of general pathologists varied, showing the highest agreement for the mitotic count score. These findings suggest that AI has the potential to enhance the accuracy and reproducibility of breast cancer grading, warranting further refinement and validation of this approach.
Collapse
Affiliation(s)
| | - Alon Vigdorovits
- Bihor County Clinical Emergency Hospital, Gh. Doja Street No. 65, 410169 Oradea, Romania
- Center for Research and Innovation in Personalized Medicine of Respiratory Diseases, "Victor Babes" University of Medicine and Pharmacy, Timisoara Eftimie Murgu Sq. No. 2, 300041 Timisoara, Romania
- Victor Babes Institute of Pathology-Next Generation Pathology Research Group, Splaiul Independenţei 99-101, 050096 Bucharest, Romania
| | | | - Ioana-Maria Mihai
- Department of Microscopic Morphology-Morphopatology, ANAPATMOL Research Center, "Victor Babes" University of Medicine and Pharmacy, 300041 Timisoara, Romania
| | - Aura Jurescu
- Department of Microscopic Morphology-Morphopatology, ANAPATMOL Research Center, "Victor Babes" University of Medicine and Pharmacy, 300041 Timisoara, Romania
| | - Adelina Gheju
- Emergency County Hospital Deva, Bulevardul 22 Decembrie 58, 330032 Deva, Romania
| | - Adeline Bucur
- Department of Microscopic Morphology, Discipline of Histology, "Victor Babes" University of Medicine and Pharmacy, Timisoara Eftimie Murgu Sq. No. 2, 300041 Timisoara, Romania
| | - Octavia Oana Harich
- Department of Functional Sciences, "Victor Babes" University of Medicine and Pharmacy, Timisoara Eftimie Murgu Sq. No. 2, 300041 Timisoara, Romania
| | - Gheorghe-Emilian Olteanu
- Center for Research and Innovation in Personalized Medicine of Respiratory Diseases, "Victor Babes" University of Medicine and Pharmacy, Timisoara Eftimie Murgu Sq. No. 2, 300041 Timisoara, Romania
- Faculty of Pharmacy, "Victor Babes" University of Medicine and Pharmacy, Eftimie Murgu Square No. 2, 300041 Timisoara, Romania
- Research Center for Pharmaco-Toxicological Evaluations, Faculty of Pharmacy, "Victor Babes" University of Medicine and Pharmacy, Eftimie Murgu Square No. 2, 300041 Timisoara, Romania
- Center of Expertise for Rare Lung Diseases, Clinical Hospital of Infectious Diseases and Pneumophthisiology "Dr. Victor Babes" Timisoara, Gh. Adam Street No. 13, 300310 Timisoara, Romania
| |
Collapse
|
7
|
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
|
8
|
Wetstein SC, de Jong VMT, Stathonikos N, Opdam M, Dackus GMHE, Pluim JPW, van Diest PJ, Veta M. Deep learning-based breast cancer grading and survival analysis on whole-slide histopathology images. Sci Rep 2022; 12:15102. [PMID: 36068311 PMCID: PMC9448798 DOI: 10.1038/s41598-022-19112-9] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2021] [Accepted: 08/24/2022] [Indexed: 11/10/2022] Open
Abstract
Breast cancer tumor grade is strongly associated with patient survival. In current clinical practice, pathologists assign tumor grade after visual analysis of tissue specimens. However, different studies show significant inter-observer variation in breast cancer grading. Computer-based breast cancer grading methods have been proposed but only work on specifically selected tissue areas and/or require labor-intensive annotations to be applied to new datasets. In this study, we trained and evaluated a deep learning-based breast cancer grading model that works on whole-slide histopathology images. The model was developed using whole-slide images from 706 young (< 40 years) invasive breast cancer patients with corresponding tumor grade (low/intermediate vs. high), and its constituents nuclear grade, tubule formation and mitotic rate. The performance of the model was evaluated using Cohen's kappa on an independent test set of 686 patients using annotations by expert pathologists as ground truth. The predicted low/intermediate (n = 327) and high (n = 359) grade groups were used to perform survival analysis. The deep learning system distinguished low/intermediate versus high tumor grade with a Cohen's Kappa of 0.59 (80% accuracy) compared to expert pathologists. In subsequent survival analysis the two groups predicted by the system were found to have a significantly different overall survival (OS) and disease/recurrence-free survival (DRFS/RFS) (p < 0.05). Univariate Cox hazard regression analysis showed statistically significant hazard ratios (p < 0.05). After adjusting for clinicopathologic features and stratifying for molecular subtype the hazard ratios showed a trend but lost statistical significance for all endpoints. In conclusion, we developed a deep learning-based model for automated grading of breast cancer on whole-slide images. The model distinguishes between low/intermediate and high grade tumors and finds a trend in the survival of the two predicted groups.
Collapse
Affiliation(s)
- Suzanne C Wetstein
- Medical Image Analysis Group, Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 5, 5612 AE, Eindhoven, The Netherlands
| | - Vincent M T de Jong
- Department of Molecular Pathology, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands
| | - Nikolas Stathonikos
- Department of Pathology, University Medical Center Utrecht, University Utrecht, Utrecht, The Netherlands
| | - Mark Opdam
- Department of Molecular Pathology, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands
| | - Gwen M H E Dackus
- Department of Molecular Pathology, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands
- Department of Pathology, University Medical Center Utrecht, University Utrecht, Utrecht, The Netherlands
| | - Josien P W Pluim
- Medical Image Analysis Group, Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 5, 5612 AE, Eindhoven, The Netherlands
| | - Paul J van Diest
- Department of Pathology, University Medical Center Utrecht, University Utrecht, Utrecht, The Netherlands
| | - Mitko Veta
- Medical Image Analysis Group, Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 5, 5612 AE, Eindhoven, The Netherlands.
| |
Collapse
|
9
|
Cho BJ, Kim JW, Park J, Kwon GY, Hong M, Jang SH, Bang H, Kim G, Park ST. Automated Diagnosis of Cervical Intraepithelial Neoplasia in Histology Images via Deep Learning. Diagnostics (Basel) 2022; 12:diagnostics12020548. [PMID: 35204638 PMCID: PMC8871214 DOI: 10.3390/diagnostics12020548] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Revised: 02/05/2022] [Accepted: 02/17/2022] [Indexed: 02/04/2023] Open
Abstract
Artificial intelligence has enabled the automated diagnosis of several cancer types. We aimed to develop and validate deep learning models that automatically classify cervical intraepithelial neoplasia (CIN) based on histological images. Microscopic images of CIN3, CIN2, CIN1, and non-neoplasm were obtained. The performances of two pre-trained convolutional neural network (CNN) models adopting DenseNet-161 and EfficientNet-B7 architectures were evaluated and compared with those of pathologists. The dataset comprised 1106 images from 588 patients; images of 10% of patients were included in the test dataset. The mean accuracies for the four-class classification were 88.5% (95% confidence interval [CI], 86.3–90.6%) by DenseNet-161 and 89.5% (95% CI, 83.3–95.7%) by EfficientNet-B7, which were similar to human performance (93.2% and 89.7%). The mean per-class area under the receiver operating characteristic curve values by EfficientNet-B7 were 0.996, 0.990, 0.971, and 0.956 in the non-neoplasm, CIN3, CIN1, and CIN2 groups, respectively. The class activation map detected the diagnostic area for CIN lesions. In the three-class classification of CIN2 and CIN3 as one group, the mean accuracies of DenseNet-161 and EfficientNet-B7 increased to 91.4% (95% CI, 88.8–94.0%), and 92.6% (95% CI, 90.4–94.9%), respectively. CNN-based deep learning is a promising tool for diagnosing CIN lesions on digital histological images.
Collapse
Affiliation(s)
- Bum-Joo Cho
- Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang 14068, Korea;
- Department of Ophthalmology, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang 14068, Korea
- Correspondence: (B.-J.C.); (J.-W.K.)
| | - Jeong-Won Kim
- Department of Pathology, Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07441, Korea;
- Correspondence: (B.-J.C.); (J.-W.K.)
| | - Jungkap Park
- Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang 14068, Korea;
| | | | - Mineui Hong
- Department of Pathology, Chung-Ang University Hospital, Chung-Ang University College of Medicine, Seoul 06973, Korea;
| | - Si-Hyong Jang
- Department of Pathology, Soonchunhyang University Cheonan Hospital, Soonchunhyang University College of Medicine, Cheonan 31151, Korea;
| | - Heejin Bang
- Department of Pathology, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul 05030, Korea;
| | - Gilhyang Kim
- Department of Pathology, Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07441, Korea;
| | - Sung-Taek Park
- Department of Obstetrics and Gynecology, Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07441, Korea;
| |
Collapse
|
10
|
A deep learning model for breast ductal carcinoma in situ classification in whole slide images. Virchows Arch 2022; 480:1009-1022. [PMID: 35076741 DOI: 10.1007/s00428-021-03241-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 11/12/2021] [Accepted: 11/20/2021] [Indexed: 02/06/2023]
Abstract
The pathological differential diagnosis between breast ductal carcinoma in situ (DCIS) and invasive ductal carcinoma (IDC) is of pivotal importance for determining optimum cancer treatment(s) and clinical outcomes. Since conventional diagnosis by pathologists using microscopes is limited in terms of human resources, it is necessary to develop new techniques that can rapidly and accurately diagnose large numbers of histopathological specimens. Computational pathology tools which can assist pathologists in detecting and classifying DCIS and IDC from whole slide images (WSIs) would be of great benefit for routine pathological diagnosis. In this paper, we trained deep learning models capable of classifying biopsy and surgical histopathological WSIs into DCIS, IDC, and benign. We evaluated the models on two independent test sets (n= 1382, n= 548), achieving ROC areas under the curves (AUCs) up to 0.960 and 0.977 for DCIS and IDC, respectively.
Collapse
|
11
|
Yousif M, van Diest PJ, Laurinavicius A, Rimm D, van der Laak J, Madabhushi A, Schnitt S, Pantanowitz L. Artificial intelligence applied to breast pathology. Virchows Arch 2021; 480:191-209. [PMID: 34791536 DOI: 10.1007/s00428-021-03213-3] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2021] [Revised: 09/12/2021] [Accepted: 09/27/2021] [Indexed: 12/12/2022]
Abstract
The convergence of digital pathology and computer vision is increasingly enabling computers to perform tasks performed by humans. As a result, artificial intelligence (AI) is having an astoundingly positive effect on the field of pathology, including breast pathology. Research using machine learning and the development of algorithms that learn patterns from labeled digital data based on "deep learning" neural networks and feature-engineered approaches to analyze histology images have recently provided promising results. Thus far, image analysis and more complex AI-based tools have demonstrated excellent success performing tasks such as the quantification of breast biomarkers and Ki67, mitosis detection, lymph node metastasis recognition, tissue segmentation for diagnosing breast carcinoma, prognostication, computational assessment of tumor-infiltrating lymphocytes, and prediction of molecular expression as well as treatment response and benefit of therapy from routine H&E images. This review critically examines the literature regarding these applications of AI in the area of breast pathology.
Collapse
Affiliation(s)
- Mustafa Yousif
- Department of Pathology, University of Michigan, Ann Arbor, MI, USA.
- Department of Pathology, Vanderbilt University Medical Center, Nashville, TN, USA.
| | - Paul J van Diest
- Department of Pathology, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Arvydas Laurinavicius
- Department of Pathology, Pharmacology and Forensic Medicine, Faculty of Medicine, Vilnius University, and National Center of Pathology, Affiliate of Vilnius University Hospital Santaros Klinikos, Vilnius, Lithuania
| | - David Rimm
- Department of Pathology, Yale University School of Medicine, New Haven, CT, USA
| | - Jeroen van der Laak
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Anant Madabhushi
- Department of Biomedical Engineering, Case Western Reserve University, and Louis Stokes Cleveland Veterans Administration Medical Center, Cleveland, OH, USA
- Louis Stokes Cleveland Veterans Administration Medical Center, Cleveland, OH, USA
| | - Stuart Schnitt
- Department of Pathology, Brigham and Women's Hospital and Harvard Medical School, Breast Oncology Program, Dana-Farber/Brigham and Women's Cancer Center, Boston, MA, USA
| | | |
Collapse
|
12
|
Kanavati F, Tsuneki M. Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning. Cancers (Basel) 2021; 13:cancers13215368. [PMID: 34771530 PMCID: PMC8582388 DOI: 10.3390/cancers13215368] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Revised: 10/22/2021] [Accepted: 10/23/2021] [Indexed: 12/12/2022] Open
Abstract
Simple Summary In this study, we have trained deep learning models using transfer learning and weakly-supervised learning for the classification of breast invasive ductal carcinoma (IDC) in whole slide images (WSIs). We evaluated the models on four test sets: one biopsy (n = 522) and three surgical (n = 1129) achieving AUCs in the range 0.95 to 0.99. We have also compared the trained models to existing pre-trained models on different organs for adenocarcinoma classification and they have achieved lower AUC performances in the range 0.66 to 0.89 despite adenocarcinoma exhibiting some structural similarity to IDC. Therefore, performing fine-tuning on the breast IDC training set was beneficial for improving performance. The results demonstrate the potential use of such models to aid pathologists in clinical practice. Abstract Invasive ductal carcinoma (IDC) is the most common form of breast cancer. For the non-operative diagnosis of breast carcinoma, core needle biopsy has been widely used in recent years for the evaluation of histopathological features, as it can provide a definitive diagnosis between IDC and benign lesion (e.g., fibroadenoma), and it is cost effective. Due to its widespread use, it could potentially benefit from the use of AI-based tools to aid pathologists in their pathological diagnosis workflows. In this paper, we trained invasive ductal carcinoma (IDC) whole slide image (WSI) classification models using transfer learning and weakly-supervised learning. We evaluated the models on a core needle biopsy (n = 522) test set as well as three surgical test sets (n = 1129) obtaining ROC AUCs in the range of 0.95–0.98. The promising results demonstrate the potential of applying such models as diagnostic aid tools for pathologists in clinical practice.
Collapse
|