言語種別 | 英語 |
---|---|
発行・発表の年月 | 2023/10/01 |
形態種別 | 【論文】研究論文(学術雑誌)<査読あり> |
査読 | 査読あり |
標題 | Development of a novel artificial intelligence algorithm to detect pulmonary nodules on chest radiography. |
執筆形態 | 共著 |
掲載誌名 | Fukushima journal of medical science |
掲載区分 | 国内 |
巻・号・頁 | 60(3),177-183 |
総ページ数 | 7 |
担当範囲 | Deeply involved in everything from algorithm development to verification |
著者・共著者 | ◎Mitsunori Higuchi, Takeshi Nagata, Kohei Iwabuchi, Akira Sano, Hidemasa Maekawa,
Takayuki Idaka, Manabu Yamasaki, Chihiro Seko, Atsushi Sato, Junzo Suzuki, Yoshiyuki Anzai, Takashi Yabuki, Takuro Saito and Hiroyuki Suzuki |
概要 | Background: This study aimed to develop a novel artificial intelligence algorithm to support the detection of pulmonary nodules.
Methods: Data from the Fukushima Health Examination Center and the National Institutes of Health were analyzed and categorized into two types. Type A included both the Fukushima dataset and his NIH dataset, and type B included only the Fukushima dataset. Results: Our AI algorithm had a receiver operating characteristic (ROC) area under the curve (AUC) of 0.74, sensitivity of 0.75, and specificity of 0.60 on the Type A dataset. For type B dataset, the respective values were 0.79, 0.72, and 0.74. The algorithm for both type A and type B datasets outperformed radiologist accuracy and was similar to previous studies. |
researchmap用URL | https://www.jstage.jst.go.jp/article/fms/69/3/69_2023-14/_pdf/-char/en |