Standardized Classification of Lung Adenocarcinoma Subtypes and Improvement of Grading Assessment Through Deep Learning.

Autor:	Lami K; Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan., Ota N; Systems Research & Development Center, Technology Bureau, NS Solutions Corp., Yokohama, Japan., Yamaoka S; Systems Research & Development Center, Technology Bureau, NS Solutions Corp., Yokohama, Japan., Bychkov A; Department of Pathology, Kameda Medical Center, Kamogawa, Japan., Matsumoto K; Department of Surgical Oncology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan., Uegami W; Department of Pathology, Kameda Medical Center, Kamogawa, Japan., Munkhdelger J; Department of Pathology, Kameda Medical Center, Kamogawa, Japan., Seki K; Department of Pathology, Kameda Medical Center, Kamogawa, Japan., Sukhbaatar O; Department of Pathology, Kameda Medical Center, Kamogawa, Japan., Attanoos R; Department of Cellular Pathology, Cardiff University, Cardiff, United Kingdom., Berezowska S; Department of Laboratory Medicine and Pathology, Institute of Pathology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland., Brcic L; Diagnostic and Research Institute of Pathology, Medical University of Graz, Graz, Austria., Cavazza A; Unit of Pathologic Anatomy, Azienda USL/IRCCS di Reggio Emilia, Reggio Emilia, Italy., English JC; Department of Pathology, Vancouver General Hospital, Vancouver, British Columbia, Canada., Fabro AT; Department of Pathology and Legal Medicine, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, Brazil., Ishida K; Department of Pathology, Kansai Medical University, Hirakata City, Japan., Kashima Y; Department of Pathology, Hyogo Prefectural Awaji Medical Center, Sumoto City, Japan., Kitamura Y; Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan; N Lab Co. Ltd., Nagasaki, Japan., Larsen BT; Department of Laboratory Medicine and Pathology, Mayo Clinic, Scottsdale, Arizona., Marchevsky AM; Department of Pathology, Cedars-Sinai Medical Center, Los Angeles, California., Miyazaki T; Department of Surgical Oncology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan., Morimoto S; Innovation Platform & Office for Precision Medicine, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan., Ozasa M; Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan., Roden AC; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota., Schneider F; Department of Pathology and Laboratory Medicine, Emory University, Atlanta, Georgia., Smith ML; Department of Laboratory Medicine and Pathology, Mayo Clinic, Scottsdale, Arizona., Tabata K; Department of Pathology, Kagoshima University Graduate School of Medical and Dental Sciences, Kagoshima, Japan., Takano AM; Department of Anatomical Pathology, Singapore General Hospital, Singapore., Tanaka T; Department of Diagnostic Pathology, Kobe University Hospital, Kobe, Japan., Tsuchiya T; Department of Surgical Oncology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan., Nagayasu T; Department of Surgical Oncology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan., Sakanashi H; Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan., Fukuoka J; Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan; Department of Pathology, Kameda Medical Center, Kamogawa, Japan. Electronic address: fukuokaj@nagasaki-u.ac.jp.
Jazyk:	angličtina
Zdroj:	The American journal of pathology [Am J Pathol] 2023 Dec; Vol. 193 (12), pp. 2066-2079. Date of Electronic Publication: 2023 Aug 05.
DOI:	10.1016/j.ajpath.2023.07.002
Abstrakt:	The histopathologic distinction of lung adenocarcinoma (LADC) subtypes is subject to high interobserver variability, which can compromise the optimal assessment of patient prognosis. Therefore, this study developed convolutional neural networks capable of distinguishing LADC subtypes and predicting disease-specific survival, according to the recently established LADC tumor grades. Consensus LADC histopathologic images were obtained from 17 expert pulmonary pathologists and one pathologist in training. Two deep learning models (AI-1 and AI-2) were trained to predict eight different LADC classes. Furthermore, the trained models were tested on an independent cohort of 133 patients. The models achieved high precision, recall, and F1 scores exceeding 0.90 for most of the LADC classes. Clear stratification of the three LADC grades was reached in predicting the disease-specific survival by the two models, with both Kaplan-Meier curves showing significance (P = 0.0017 and 0.0003). Moreover, both trained models showed high stability in the segmentation of each pair of predicted grades with low variation in the hazard ratio across 200 bootstrapped samples. These findings indicate that the trained convolutional neural networks improve the diagnostic accuracy of the pathologist and refine LADC grade assessment. Thus, the trained models are promising tools that may assist in the routine evaluation of LADC subtypes and grades in clinical practice. (Copyright © 2023 American Society for Investigative Pathology. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu