Manabu Takamatsu1, Noriko Yamamoto2, Hiroshi Kawachi2, Akiko Chino3, Shoichi Saito3, Masashi Ueno4, Yuichi Ishikawa2, Yutaka Takazawa2, Kengo Takeuchi2. 1. Division of Pathology, The Cancer Institute; Department of Pathology, The Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan. Electronic address: manabu.takamatsu@jfcr.or.jp. 2. Division of Pathology, The Cancer Institute; Department of Pathology, The Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan. 3. Department of Endoscopy, The Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan. 4. Department of Colorectal Surgery, The Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan.
Abstract
BACKGROUND AND OBJECTIVES: Prediction of lymph node metastasis (LNM) for early colorectal cancer (CRC) is critical for determining treatment strategies after endoscopic resection. Some histologic parameters for predicting LNM have been established, but evaluator error and inter-observer disagreement are unsolved issues. Here we describe an LNM prediction algorithm for submucosal invasive (T1) CRC based on machine learning. METHODS: We conducted a retrospective single-institution study of 397 T1 CRCs. Several morphologic parameters were extracted from whole slide images of cytokeratin immunohistochemistry using Image J. A random forest algorithm for a training dataset (n = 277) was executed and used to predict LNM for the test dataset (n = 120). The results were compared with conventional histologic evaluation of hematoxylin-eosin staining. RESULTS: Machine learning showed better LNM predictive ability than the conventional method on some datasets. Cross validation revealed no significant difference between the methods. Machine learning resulted in fewer false-negative cases than the conventional method. CONCLUSIONS: Machine learning on whole slide images is a potential alternative for determining treatment strategies for T1 CRC.
BACKGROUND AND OBJECTIVES: Prediction of lymph node metastasis (LNM) for early colorectal cancer (CRC) is critical for determining treatment strategies after endoscopic resection. Some histologic parameters for predicting LNM have been established, but evaluator error and inter-observer disagreement are unsolved issues. Here we describe an LNM prediction algorithm for submucosal invasive (T1) CRC based on machine learning. METHODS: We conducted a retrospective single-institution study of 397 T1 CRCs. Several morphologic parameters were extracted from whole slide images of cytokeratin immunohistochemistry using Image J. A random forest algorithm for a training dataset (n = 277) was executed and used to predict LNM for the test dataset (n = 120). The results were compared with conventional histologic evaluation of hematoxylin-eosin staining. RESULTS: Machine learning showed better LNM predictive ability than the conventional method on some datasets. Cross validation revealed no significant difference between the methods. Machine learning resulted in fewer false-negative cases than the conventional method. CONCLUSIONS: Machine learning on whole slide images is a potential alternative for determining treatment strategies for T1 CRC.
Authors: Min Seob Kwak; Hun Hee Lee; Jae Min Yang; Jae Myung Cha; Jung Won Jeon; Jin Young Yoon; Ha Il Kim Journal: Front Oncol Date: 2021-01-13 Impact factor: 6.244
Authors: Ji Hyun Ahn; Min Seob Kwak; Hun Hee Lee; Jae Myung Cha; Hyun Phil Shin; Jung Won Jeon; Jin Young Yoon Journal: Front Oncol Date: 2021-03-25 Impact factor: 6.244
Authors: Jeonghyun Kang; Yoon Jung Choi; Im-Kyung Kim; Hye Sun Lee; Hogeun Kim; Seung Hyuk Baik; Nam Kyu Kim; Kang Young Lee Journal: Cancer Res Treat Date: 2020-12-29 Impact factor: 4.679
Authors: Okechinyere J Achilonu; June Fabian; Brendan Bebington; Elvira Singh; M J C Eijkemans; Eustasius Musenge Journal: Front Public Health Date: 2021-07-07