文献

J-GLOBAL ID：202202295633857927   整理番号：22A1094280

COPDの同定と重症度病期分類のための新しいCTベースラジオミクス特徴解析【JST・京大機械翻訳】

A Novel CT-Based Radiomics Features Analysis for Identification and Severity Staging of COPD

著者 (49件)： Li Zongli (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Chao-Yang Hospital, Capital Medical University, No 8 Gongti South Road, Beijing, 100020, People’s Republic of China) ,  Li Zongli (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Institute of Respiratory Medicine, Beijing, People’s Republic of China) ,  Li Zongli (Department of Pulmonary and Critical Care Medicine (Z.L., Z.Z.), Shijingshan Teaching Hospital of Capital Medical University, Beijing Shijingshan Hospital, Beijing, China) ,  Li Zongli (Department of Enterprise, Beijing e-Hualu Information Technology Corporation Limited (L. L.), Beijing, China) ,  Li Zongli (Dongsheng Science and Technology Park (X.Y.), Huiying Medical Technology Co., Ltd, Beijing, China) ,  Li Zongli (Department of Respiratory (X.L.), Third Affiliated Hospital of Jinzhou Medical University, Jinzhou, Liaoning, China) ,  Li Zongli (Department of Radiology (Y.G.), Beijing Chao-Yang Hospital, Capital Medical University, Beijing, People’s Republic of China) ,  Liu Ligong (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Chao-Yang Hospital, Capital Medical University, No 8 Gongti South Road, Beijing, 100020, People’s Republic of China) ,  Liu Ligong (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Institute of Respiratory Medicine, Beijing, People’s Republic of China) ,  Liu Ligong (Department of Pulmonary and Critical Care Medicine (Z.L., Z.Z.), Shijingshan Teaching Hospital of Capital Medical University, Beijing Shijingshan Hospital, Beijing, China) ,  Liu Ligong (Department of Enterprise, Beijing e-Hualu Information Technology Corporation Limited (L. L.), Beijing, China) ,  Liu Ligong (Dongsheng Science and Technology Park (X.Y.), Huiying Medical Technology Co., Ltd, Beijing, China) ,  Liu Ligong (Department of Respiratory (X.L.), Third Affiliated Hospital of Jinzhou Medical University, Jinzhou, Liaoning, China) ,  Liu Ligong (Department of Radiology (Y.G.), Beijing Chao-Yang Hospital, Capital Medical University, Beijing, People’s Republic of China) ,  Zhang Zuoqing (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Chao-Yang Hospital, Capital Medical University, No 8 Gongti South Road, Beijing, 100020, People’s Republic of China) ,  Zhang Zuoqing (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Institute of Respiratory Medicine, Beijing, People’s Republic of China) ,  Zhang Zuoqing (Department of Pulmonary and Critical Care Medicine (Z.L., Z.Z.), Shijingshan Teaching Hospital of Capital Medical University, Beijing Shijingshan Hospital, Beijing, China) ,  Zhang Zuoqing (Department of Enterprise, Beijing e-Hualu Information Technology Corporation Limited (L. L.), Beijing, China) ,  Zhang Zuoqing (Dongsheng Science and Technology Park (X.Y.), Huiying Medical Technology Co., Ltd, Beijing, China) ,  Zhang Zuoqing (Department of Respiratory (X.L.), Third Affiliated Hospital of Jinzhou Medical University, Jinzhou, Liaoning, China) ,  Zhang Zuoqing (Department of Radiology (Y.G.), Beijing Chao-Yang Hospital, Capital Medical University, Beijing, People’s Republic of China) ,  Yang Xuhong (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Chao-Yang Hospital, Capital Medical University, No 8 Gongti South Road, Beijing, 100020, People’s Republic of China) ,  Yang Xuhong (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Institute of Respiratory Medicine, Beijing, People’s Republic of China) ,  Yang Xuhong (Department of Pulmonary and Critical Care Medicine (Z.L., Z.Z.), Shijingshan Teaching Hospital of Capital Medical University, Beijing Shijingshan Hospital, Beijing, China) ,  Yang Xuhong (Department of Enterprise, Beijing e-Hualu Information Technology Corporation Limited (L. L.), Beijing, China) ,  Yang Xuhong (Dongsheng Science and Technology Park (X.Y.), Huiying Medical Technology Co., Ltd, Beijing, China) ,  Yang Xuhong (Department of Respiratory (X.L.), Third Affiliated Hospital of Jinzhou Medical University, Jinzhou, Liaoning, China) ,  Yang Xuhong (Department of Radiology (Y.G.), Beijing Chao-Yang Hospital, Capital Medical University, Beijing, People’s Republic of China) ,  Li Xuanyi (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Chao-Yang Hospital, Capital Medical University, No 8 Gongti South Road, Beijing, 100020, People’s Republic of China) ,  Li Xuanyi (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Institute of Respiratory Medicine, Beijing, People’s Republic of China) ,  Li Xuanyi (Department of Pulmonary and Critical Care Medicine (Z.L., Z.Z.), Shijingshan Teaching Hospital of Capital Medical University, Beijing Shijingshan Hospital, Beijing, China) ,  Li Xuanyi (Department of Enterprise, Beijing e-Hualu Information Technology Corporation Limited (L. L.), Beijing, China) ,  Li Xuanyi (Dongsheng Science and Technology Park (X.Y.), Huiying Medical Technology Co., Ltd, Beijing, China) ,  Li Xuanyi (Department of Respiratory (X.L.), Third Affiliated Hospital of Jinzhou Medical University, Jinzhou, Liaoning, China) ,  Li Xuanyi (Department of Radiology (Y.G.), Beijing Chao-Yang Hospital, Capital Medical University, Beijing, People’s Republic of China) ,  Gao Yanli (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Chao-Yang Hospital, Capital Medical University, No 8 Gongti South Road, Beijing, 100020, People’s Republic of China) ,  Gao Yanli (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Institute of Respiratory Medicine, Beijing, People’s Republic of China) ,  Gao Yanli (Department of Pulmonary and Critical Care Medicine (Z.L., Z.Z.), Shijingshan Teaching Hospital of Capital Medical University, Beijing Shijingshan Hospital, Beijing, China) ,  Gao Yanli (Department of Enterprise, Beijing e-Hualu Information Technology Corporation Limited (L. L.), Beijing, China) ,  Gao Yanli (Dongsheng Science and Technology Park (X.Y.), Huiying Medical Technology Co., Ltd, Beijing, China) ,  Gao Yanli (Department of Respiratory (X.L.), Third Affiliated Hospital of Jinzhou Medical University, Jinzhou, Liaoning, China) ,  Gao Yanli (Department of Radiology (Y.G.), Beijing Chao-Yang Hospital, Capital Medical University, Beijing, People’s Republic of China) ,  Huang Kewu (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Chao-Yang Hospital, Capital Medical University, No 8 Gongti South Road, Beijing, 100020, People’s Republic of China) ,  Huang Kewu (Department of Pulmonary and Critical Care Medicine (Z.L., K.H.), Beijing Institute of Respiratory Medicine, Beijing, People’s Republic of China) ,  Huang Kewu (Department of Pulmonary and Critical Care Medicine (Z.L., Z.Z.), Shijingshan Teaching Hospital of Capital Medical University, Beijing Shijingshan Hospital, Beijing, China) ,  Huang Kewu (Department of Enterprise, Beijing e-Hualu Information Technology Corporation Limited (L. L.), Beijing, China) ,  Huang Kewu (Dongsheng Science and Technology Park (X.Y.), Huiying Medical Technology Co., Ltd, Beijing, China) ,  Huang Kewu (Department of Respiratory (X.L.), Third Affiliated Hospital of Jinzhou Medical University, Jinzhou, Liaoning, China) ,  Huang Kewu (Department of Radiology (Y.G.), Beijing Chao-Yang Hospital, Capital Medical University, Beijing, People’s Republic of China)
資料名： Academic Radiology  (Academic Radiology)
巻： 29  号： 5  ページ： 663-673  発行年： 2022年 
JST資料番号： W3289A  ISSN： 1076-6332  資料種別： 逐次刊行物 (A)
記事区分： 原著論文  発行国： オランダ (NLD)  言語： 英語 (EN)

抄録/ポイント： 目的:慢性閉塞性肺疾患(COPD)の同定と重症度分類における胸部コンピュータ断層撮影(CT)に基づくラジノミクスの役割を評価する。この後向き分析は322人の参加者(249人のCOPD患者と73人の対照被験者)を含んだ。全体で,1395の胸部CTベースのラジノミクス特徴を各参加者のCT画像から抽出した。分散閾値,選択K最良法,および最小絶対収縮と選択オペレータ(LASSO)を含む3つの特徴選択法,およびサポートベクターマシン(SVM)とロジスティック回帰(LR)を含む2つの分類方法を,COPDの同定と重症度分類として使用した。性能をAUC,精度,感度,特異性,精度,およびF1スコアで比較した。38と10の特徴を,それぞれ,COPDの検出と段階のためのラジノミクスモデルを構築するために選択した。COPD識別のために,SVM分類装置は,0.992と0.970のAUCを達成し,一方,LR分類装置は,訓練セットと試験セットにおいて,それぞれ,0.993と0.972のAUCを達成した。COPDの重症度分類のために,上記の2つの機械学習分類器は,より重度(GOLD3+GOLD4)グループから,より重症度の少ない(GOLD1+GOLD2)グループをよりよく区別することができた。SVMとLRのAUCは訓練セットで0.907と0.903であり,試験セットで0.799と0.797であった。本研究は,COPD同定と重症度分類に使用できる胸部CT画像に基づく新しいラジノミクスアプローチと,構築したラドミクスモデルが許容できる性能を示したことを示した。Copyright 2022 Elsevier B.V., Amsterdam. All rights reserved. Translated from English into Japanese by JST.【JST・京大機械翻訳】

シソーラス用語： オペレータ ,  *分類 ,  *解析 ,  分類装置 ,  特徴選択 ,  人間 ,  断層画像 ,  機械学習 ,  *慢性閉塞性肺疾患 ,  サポートベクトルマシン
準シソーラス用語： 被験者 ,  ロジスティック回帰分析 ,  CT画像 ,  胸部CT ,  *病期分類 ,  重症度分類 ,  胸部CT画像 ,  *特徴解析 ,  *重症度 , 【Automatic Indexing@JST】

著者キーワード (5件)： ラジオミクス ,  COPD ,  同定 ,  重症度病期分類 ,  CT

分類 (2件)： 呼吸器の診断  (GI02000S) ,  放射線を利用した診断  (GC04020K)

タイトルに関連する用語 (7件)： COPD ,  同定 ,  重症度 ,  病期分類 ,  CT ,  ラジオミクス ,  特徴解析