雑誌文献を検索します。書籍を検索する際には「書籍検索」を選択してください。

検索

書誌情報 詳細検索 by 医中誌

Japanese

Current status and perspectives of AI-based radiomics:explainability of features Hidetaka Arimura 1 1Division of Medical Quantum Science, Department of Health Sciences Graduate School of Medicine, Kyushu University Keyword: レディオミクス , 説明可能性 , 画像特徴量 pp.809-816
Published Date 2024/11/10
DOI https://doi.org/10.18888/rp.0000002789
  • Abstract
  • Look Inside
  • Reference

Radiomics can be a black box because we have faced many “good” results, the reasons for which have not been explained for radiomics predictions. This review addresses the histogram, texture, and topology features among engineered features in radiomics, which are considered to have a relatively better explainability. The authors included features that they developed on their own, which they believed to be explainable. The authors introduced some studies on radiomics that, in their opinion, attempted to explain the reasons for the predictions. Finally, we discuss the current problems in radiomics and provide perspectives on radiomics.


Copyright © 2024, KANEHARA SHUPPAN Co.LTD. All rights reserved.

基本情報

電子版ISSN 印刷版ISSN 0009-9252 金原出版

関連文献

もっと見る

文献を共有