DSpace Fukushima Medical University

福島県立医科大学学術成果リポジトリ = Fukushima Medical University Repository >
福島医学会 = The Fukushima Society of Medical Science >
Fukushima Journal of Medical Science >
Vol.69 (2023) >

Please use this identifier to cite or link to this item: http://ir.fmu.ac.jp/dspace/handle/123456789/2199

Files in This Item:

File Description SizeFormat
FksmJMedSci_69_p177.pdf1.73 MBAdobe PDFDownload
Title: Development of a novel artificial intelligence algorithm to detect pulmonary nodules on chest radiography
Authors: Higuchi, Mitsunori
Nagata, Takeshi
Iwabuchi, Kohei
Sano, Akira
Maekawa, Hidemasa
Idaka, Takayuki
Yamasaki, Manabu
Seko, Chihiro
Sato, Atsushi
Suzuki, Junzo
Anzai, Yoshiyuki
Yabuki, Takashi
Saito, Takuro
Suzuki, Hiroyuki
Affiliation: 会津医療センター外科学講座
呼吸器外科学講座
Source title: Fukushima Journal of Medical Science
Volume: 69
Issue: 3
Start page: 177
End page: 183
Issue Date: 2023
Abstract: Background: In this study, we aimed to develop a novel artificial intelligence (AI) algorithm to support pulmonary nodule detection, which will enable physicians to efficiently interpret chest radiographs for lung cancer diagnosis. Methods: We analyzed chest X-ray images obtained from a health examination center in Fukushima and the National Institutes of Health (NIH) Chest X-ray 14 dataset. We categorized these data into two types: type A included both Fukushima and NIH datasets, and type B included only the Fukushima dataset. We also demonstrated pulmonary nodules in the form of a heatmap display on each chest radiograph and calculated the positive probability score as an index value. Results: Our novel AI algorithms had a receiver operating characteristic (ROC) area under the curve (AUC) of 0.74, a sensitivity of 0.75, and a specificity of 0.60 for the type A dataset. For the type B dataset, the respective values were 0.79, 0.72, and 0.74. The algorithms in both the type A and B datasets were superior to the accuracy of radiologists and similar to previous studies. Conclusions: The proprietary AI algorithms had a similar accuracy for interpreting chest radiographs when compared with previous studies and radiologists. Especially, we could train a high quality AI algorithm, even with our small type B data set. However, further studies are needed to improve and further validate the accuracy of our AI algorithm.
Publisher: The Fukushima Society of Medical Science
Publisher (Alternative foam): 福島医学会
language: eng
URI: http://ir.fmu.ac.jp/dspace/handle/123456789/2199
Full text URL: http://ir.fmu.ac.jp/dspace/bitstream/123456789/2199/1/FksmJMedSci_69_p177.pdf
ISSN: 0016-2590
2185-4610
DOI: 10.5387/fms.2023-14
PubMed ID: 37853640
Related Page: https://doi.org/10.5387/fms.2023-14
Rights: © 2023 The Fukushima Society of Medical Science. This article is licensed under a Creative Commons [Attribution-NonCommercial-ShareAlike 4.0 International] license.
Rights: https://creativecommons.org/licenses/by-nc-sa/4.0/
Appears in Collections:Vol.69 (2023)

Files in This Item:

File Description SizeFormat
FksmJMedSci_69_p177.pdf1.73 MBAdobe PDFDownload

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

DSpace Software Copyright © 2002-2007 MIT and Hewlett-Packard