학술논문
A Machine Learning Model to Predict the Histology of Retroperitoneal Lymph Node Dissection Specimens.
Document Type
Academic Journal
Author
Nitta S; Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba, Japan.; Kojima T; Department of Urology, Aichi Cancer Center Hospital, Nagoya, Japan; t.kojima@aichi-cc.jp.; Gido M; Department of Intelligent Functional Systems, Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan.; Nakagawa S; Department of Intelligent Functional Systems, Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan.; Kakeya H; Department of Intelligent Functional Systems, Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan.; Kandori S; Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba, Japan.; Kawahara T; Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba, Japan.; Mathis BJ; International Medical Center, University of Tsukuba Affiliated Hospital, Tsukuba, Japan.; Kawai K; Department of Urology, Faculty of Medicine, International University of Health and Welfare Narita Hospital, Narita, Japan.; Negoro H; Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba, Japan.; Nishiyama H; Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba, Japan.
Source
Publisher: International Institute of Anticancer Research Country of Publication: Greece NLM ID: 8102988 Publication Model: Print Cited Medium: Internet ISSN: 1791-7530 (Electronic) Linking ISSN: 02507005 NLM ISO Abbreviation: Anticancer Res Subsets: MEDLINE
Subject
Language
English
Abstract
Background/aim: While post-chemotherapy retroperitoneal lymph node dissection (PC-RPLND) benefits patients with teratoma or viable germ cell tumors (GCT), it becomes overtreatment if necrosis is detected in PC-RPLND specimens. Serum microRNA-371a-3p correctly predicts residual viable GCT with 100% sensitivity; however, prediction of residual teratoma in PC-RPLND specimens using current modalities remains difficult. Therefore, we developed a machine learning model using CT imaging and clinical variables to predict the presence of residual teratoma in PC-RPLND specimens.
Patients and Methods: This study included 58 patients who underwent PC-RPLND between 2005 and 2019 at the University of Tsukuba Hospital. On CT imaging, 155 lymph nodes were identified as regions of interest (ROIs). The ResNet50 algorithm and/or Support Vector Machine (SVM) classification were applied and a nested, 3-fold cross-validation protocol was used to determine classifier accuracy.
Results: PC-RPLND specimen analysis revealed 35 patients with necrosis and 23 patients with residual teratoma, while histology of 155 total ROIs showed necrosis in 84 ROIs and teratoma in 71 ROIs. The ResNet50 algorithm, using CT imaging, achieved a diagnostic accuracy of 80.0%, corresponding to a sensitivity of 67.3%, a specificity of 90.5%, and an AUC of 0.84, whereas SVM classification using clinical variables achieved a diagnostic accuracy of 74.8%, corresponding to a sensitivity of 59.0%, a specificity of 88.1%, and an AUC of 0.84.
Conclusion: Our machine learning models reliably distinguish between necrosis and residual teratoma in clinical PC-RPLND specimens.
(Copyright © 2024 International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved.)
Patients and Methods: This study included 58 patients who underwent PC-RPLND between 2005 and 2019 at the University of Tsukuba Hospital. On CT imaging, 155 lymph nodes were identified as regions of interest (ROIs). The ResNet50 algorithm and/or Support Vector Machine (SVM) classification were applied and a nested, 3-fold cross-validation protocol was used to determine classifier accuracy.
Results: PC-RPLND specimen analysis revealed 35 patients with necrosis and 23 patients with residual teratoma, while histology of 155 total ROIs showed necrosis in 84 ROIs and teratoma in 71 ROIs. The ResNet50 algorithm, using CT imaging, achieved a diagnostic accuracy of 80.0%, corresponding to a sensitivity of 67.3%, a specificity of 90.5%, and an AUC of 0.84, whereas SVM classification using clinical variables achieved a diagnostic accuracy of 74.8%, corresponding to a sensitivity of 59.0%, a specificity of 88.1%, and an AUC of 0.84.
Conclusion: Our machine learning models reliably distinguish between necrosis and residual teratoma in clinical PC-RPLND specimens.
(Copyright © 2024 International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved.)