Performance of artificial intelligence-based software for the automatic detection of lung lesions on chest radiographs of patients with suspected lung cancer

Atsushi Takamatsu; Midori Ueno; Kotaro Yoshida; Takeshi Kobayashi; Satoshi Kobayashi; Toshifumi Gabata

doi:10.1007/s11604-023-01503-1

Performance of artificial intelligence-based software for the automatic detection of lung lesions on chest radiographs of patients with suspected lung cancer

Jpn J Radiol. 2024 Mar;42(3):291-299. doi: 10.1007/s11604-023-01503-1. Epub 2023 Nov 30.

Authors

Atsushi Takamatsu¹, Midori Ueno¹, Kotaro Yoshida², Takeshi Kobayashi³, Satoshi Kobayashi¹, Toshifumi Gabata¹

Affiliations

¹ Department of Radiology, Kanazawa University Graduate School of Medical Sciences, 13-1 Takaramachi, Kanazawa, Ishikawa, 920-8641, Japan.
² Department of Radiology, Kanazawa University Graduate School of Medical Sciences, 13-1 Takaramachi, Kanazawa, Ishikawa, 920-8641, Japan. kotaro_yoshida@staff.kanazawa-u.ac.jp.
³ Department of Diagnostic and Interventional Radiology, Ishikawa Prefectural Central Hospital, Kanazawa, Ishikawa, 920-8530, Japan.

Abstract

Purpose: This study aimed to evaluate the performance of the commercially available artificial intelligence-based software CXR-AID for the automatic detection of pulmonary nodules on the chest radiographs of patients suspected of having lung cancer.

Materials and methods: This retrospective study included 399 patients with clinically suspected lung cancer who underwent CT and chest radiography within 1 month between June 2020 and May 2022. The candidate areas on chest radiographs identified by CXR-AID were categorized into target (properly detected areas) and non-target (improperly detected areas) areas. The non-target areas were further divided into non-target normal areas (false positives for normal structures) and non-target abnormal areas. The visibility score, characteristics and location of the nodules, presence of overlapping structures, and background lung score and presence of pulmonary disease were manually evaluated and compared between the nodules detected or undetected by CXR-AID. The probability indices calculated by CXR-AID were compared between the target and non-target areas.

Results: Among the 450 nodules detected in 399 patients, 331 nodules detected in 313 patients were visible on chest radiographs during manual evaluation. CXR-AID detected 264 of these 331 nodules with a sensitivity of 0.80. The detection sensitivity increased significantly with the visibility score. No significant correlation was observed between the background lung score and sensitivity. The non-target area per image was 0.85, and the probability index of the non-target area was lower than that of the target area. The non-target normal area per image was 0.24. Larger and more solid nodules exhibited higher sensitivities, while nodules with overlapping structures demonstrated lower detection sensitivities.

Conclusion: The nodule detection sensitivity of CXR-AID on chest radiographs was 0.80, and the non-target and non-target normal areas per image were 0.85 and 0.24, respectively. Larger, solid nodules without overlapping structures were detected more readily by CXR-AID.

Keywords: Artificial intelligence; Automatic detection; Chest radiograph; Deep learning; Lung cancer.

MeSH terms

Artificial Intelligence
Humans
Lung
Lung Neoplasms* / diagnostic imaging
Radiographic Image Interpretation, Computer-Assisted / methods
Radiography
Radiography, Thoracic / methods
Retrospective Studies
Sensitivity and Specificity
Software