タニアイ　マキコ   TANIAI Makiko   谷合　麻紀子    所属   医学部 医学科（東京女子医科大学病院）    職種   准教授
論文種別	原著
言語種別	英語
査読の有無	査読なし
表題	Deep learning and digital pathology powers prediction of HCC development in steatotic liver disease
掲載誌名	正式名：Hepatology 略　 称：Hepatology ISSNコード：15273350/02709139
掲載区分	国外
巻・号・頁	81(3),pp.976-989
著者・共著者	NAKATSUKA Takuma, TATEISHI Ryosuke, SATO Masaya, HASHIZUME Natsuka, MAKADA Ami, NAKANO Hiroki, KABEYA Yoshinori, YONAZAWA Sho, IRIE Rie, TSUJIKAWA Hanako, SUMIDA Yoshio, YONEDA Masashi, AKUTA Norio, KAWAGUCHI Takumi, TAKAHASHI Hirokazu, EGUCHI Yuichiro, SEKO Yuya, ITOH Yoshito, MURAKAMI Eisuke, CHAYAMA Kazuaki, TANIAI Makiko, TOKUSHIGE Katsutoshi, OKANOUE Takeshi, SAKAMOTO Michiie, FUJISHIRO Mitsuhiro, KOIKE Kazuhiko
発行年月	2025/03
概要	BACKGROUND AND AIMS:Identifying patients with steatotic liver disease who are at a high risk of developing HCC remains challenging. We present a deep learning (DL) model to predict HCC development using hematoxylin and eosin-stained whole-slide images of biopsy-proven steatotic liver disease.APPROACH AND RESULTS:We included 639 patients who did not develop HCC for ≥7 years after biopsy (non-HCC class) and 46 patients who developed HCC <7 years after biopsy (HCC class). Paired cases of the HCC and non-HCC classes matched by biopsy date and institution were used for training, and the remaining nonpaired cases were used for validation. The DL model was trained using deep convolutional neural networks with 28,000 image tiles cropped from whole-slide images of the paired cases, with an accuracy of 81.0% and an AUC of 0.80 for predicting HCC development. Validation using the nonpaired cases also demonstrated a good accuracy of 82.3% and an AUC of 0.84. These results were comparable to the predictive ability of logistic regression model using fibrosis stage. Notably, the DL model also detected the cases of HCC development in patients with mild fibrosis. The saliency maps generated by the DL model highlighted various pathological features associated with HCC development, including nuclear atypia, hepatocytes with a high nuclear-cytoplasmic ratio, immune cell infiltration, fibrosis, and a lack of large fat droplets.CONCLUSIONS:The ability of the DL model to capture subtle pathological features beyond fibrosis suggests its potential for identifying early signs of hepatocarcinogenesis in patients with steatotic liver disease.
DOI	10.1097/HEP.0000000000000904
PMID	38768142