Effectiveness of artificial intelligence for detecting operable lung cancer on chest radiographs

Q: What was the main goal of the study?

To evaluate the effectiveness of AI-based CXR analysis for detecting operable lung cancers.

Q: How were AI detections validated in this research?

Preoperative CXRs were analyzed using commercial AI software, and CT served as the reference standard to determine nodule characteristics.

Q: What factors were associated with improved AI detection?

Detection was significantly associated with upper-zone and peripheral nodule locations, and with solid lesion diameter.

Sep 21, 2026

Uploaded by Valentina

Investigate whether artificial intelligence (AI)-based analysis of chest radiographs (CXRs) can effectively detect operable lung cancer. Retrospective data include patients undergoing lung cancer surgery at two referral hospitals from March 2020 to February 2021, using commercial AI lesion detection with CT as the reference for nodule characteristics. AI sensitivity reached 57.7%, identifying 86% of visible CXR lung cancers, with detection increasing by stage and tumor size. Performance was higher for upper-zone, peripheral-region, and solid lesions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Background

Methods

Results

Conclusions

Introduction

Highlight box

Key findings

What is known and what is new

Effectiveness of artificial intelligence for detecting operable lung cancer on chest radiographs Hyun Joo Shin1\#, Se Hyun Kwak2\#, KyeongYeon Kim2, Na Young Kim3, Kyungsun Nam3, Young Jin Kim3, Eun-Kyung Kim1, Young Joo Suh3*^, Eun Hye Lee2*^ 1Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Republic of Korea; 2Division of Pulmonology, Allergy and Critical Care Medicine, Department of Internal Medicine, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Republic of Korea; 3Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea Contributions: (I) Conception and design: HJ Shin, SH Kwak, YJ Suh, EH Lee; (II) Administrative support: All authors; (III) Provision of study materials or patients: HJ Shin, SH Kwak, YJ Suh, EH Lee; (IV) Collection and assembly of data: HJ Shin, SH Kwak, KY Kim, NY Kim, K Nam, YJ Suh, EH Lee; (V) Data analysis and interpretation: HJ Shin, SH Kwak, YJ Suh, EH Lee; (VI) Manuscript writing: All authors; (VII) Final approval of manuscript: All authors. \#These authors contributed equally to this work as co-first authors. *These authors contributed equally to this work. Correspondence to: Young Joo Suh, MD, PhD. Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Severance Hospital, Yonsei University College of Medicine, 50-1, Yonsei-ro, Seodaemun-gu, Seoul 03722, Republic of Korea. Email: [rongzusuh@gmail.com](rongzusuh@gmail.com); Eun Hye Lee, MD, PhD. Division of Pulmonology, Allergy and Critical Care Medicine, Department of Internal Medicine, Yongin Severance Hospital, Yonsei University College of Medicine, 363, Dongbaekjukjeon-daero, Giheung-gu, Yongin-si, Gyeonggi-do 16995, [South Korea. Email: hieunhye@yuhs.ac](South Korea. Email: hieunhye@yuhs.ac). Background: Despite the importance of early diagnosis of lung cancer and wide availability of chest radiography, the detection of operable stage lung cancer on chest radiographs (CXRs) remains challenging. This study aimed to investigate the effectiveness of artificial intelligence (AI)-based CXR analysis for detecting operable lung cancers. Methods: Patients who underwent lung cancer surgery at two referral hospitals between March 2020 and February 2021 were retrospectively included in this study. Preoperative CXRs of the patients were analyzed using commercial AI-based lesion detection software, and the results of lesion location and types obtained using the software were reviewed by radiologists and pulmonologists, with computed tomography (CT) as a reference standard for determining nodule characteristics. Factors influencing AI detection of lung cancer on CXR were assessed using logistic regression analysis. Results: Among the 594 patients who underwent surgery for lung cancer (median age: 65 years, 51.3% male), the sensitivity of AI for detecting lung cancer on CXR was 57.7%, and it identified 86% of CXRvisible lung cancers. Detection rates of lung cancer by AI increased according to the disease stage: 42.5% for stage IA, 86.3% for stage IB, and 90.9% for stages II–III. The detection rate increased to over 60% from stage IA2 onwards when tumor size exceeded 1 cm. Regarding lesion type on CT, 8.3%, 46.8%, and 77.3% of non-solid, part-solid, and solid nodules, respectively, were detected by AI. Multivariable analysis showed that nodule location in the upper zone [odds ratio (OR) 2.78, P<0.001], peripheral region (OR 4.59, P<0.001), and solid lesion diameter (OR 1.20, P<0.001) were significantly associated with AI detection of lung cancer. ^ ORCID: Young Joo Suh, 0000-0002-2078-5832; Eun Hye Lee, 0000-0003-2570-3442. © AME Publishing Company. Transl Lung Cancer R

FAQs

What was the main goal of the study?

To evaluate the effectiveness of AI-based CXR analysis for detecting operable lung cancers.

How were AI detections validated in this research?

Preoperative CXRs were analyzed using commercial AI software, and CT served as the reference standard to determine nodule characteristics.

What factors were associated with improved AI detection?

Detection was significantly associated with upper-zone and peripheral nodule locations, and with solid lesion diameter.

Sep 21, 2026

Uploaded by Valentina