Japanese
English
- 有料閲覧
- Abstract 文献概要
- 1ページ目 Look Inside
- 参考文献 Reference
要旨●近年,深層学習によって画像認識における人工知能(AI)アルゴリズムは大幅な進歩を遂げており,筆者らの胃癌転移リンパ節のHE染色標本におけるAI病理診断研究でも,AUCが0.99以上と良好な結果が得られている.AI病理診断に関しては,これまでに乳癌転移リンパ節診断や胃・大腸の腺腫・癌の生検組織診断などでその有用性が報告されてきたが,克服すべき課題も存在する.
Recently, AI(artificial intelligence)based on deep learning has demonstrated excellent outcomes in various automated image-recognition algorithms. Our study on the performances of deep learning-based algorithm for the detection of gastric cancer metastasis in hematoxylin and eosin-stained tissue sections of lymph nodes achieved an area under the receiver operating characteristic curve(AUC)of >0.99. Similar AI algorithms to detect breast cancer metastasis in lymph nodes or to classify adenocarcinoma, adenoma, and non-neoplastic tissues in gastrointestinal biopsy histology have been studied and showed good applicability. However, some challenges exist in the introduction of AI-based pathological diagnosis in daily practice.
Copyright © 2021, Igaku-Shoin Ltd. All rights reserved.