Comparison of Stereotactic Body Radiotherapy and Surgery for Stage I Lung Cancer: A Multidisciplinary Cohort Study Utilizing Propensity Score Overlap Weighting and AI-Based CT Imaging Analysis
Eun Hye Lee, Young Joo Suh, Jong Won Park, Jisu Moon, Sangjoon Park, Chang Geol Lee, Hong In Yoon, Byung Jo Park, Jin Gu Lee, Dae Joon Kim, Seung Hyun Yong, Sang Hoon Lee, Chang Young Lee, Jaeho Cho, Eun Young Kim

TL;DR
This study finds that stereotactic body radiotherapy and surgery are similarly effective for early-stage lung cancer, especially when considering patient-specific factors.
Contribution
The study introduces AI-based CT imaging analysis combined with propensity score overlap weighting to compare SBRT and surgery for lung cancer.
Findings
SBRT and surgery showed no significant differences in 5-year recurrence or survival rates.
AI-based CT analysis identified a solid tumor diameter threshold linked to higher recurrence for both treatments.
Overlap weighting balanced baseline differences, supporting the clinical value of SBRT for ineligible surgical patients.
Abstract
This study compares stereotactic body radiotherapy (SBRT) and surgery in patients with stage I non-small cell lung cancer (NSCLC), using a robust overlap-weighted propensity score approach to address disparities in baseline characteristics. By incorporating artificial intelligence (AI)-based Chest CT features through computer-aided detection (CAD), the study provides a novel analysis of radiological tumor characteristics. No statistically significant differences in outcomes were found between SBRT and surgery, even after stratifying by tumor diameter, lobar location, or pleural attachment. Conducted in South Korea, a country with advanced lung cancer screening practices, the study highlights the clinical value of SBRT, especially for patients with comorbidities or limited surgical options. These findings may support more inclusive and personalized treatment strategies for early-stage…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Click any figure to enlarge with its caption.
Figure 1
Figure 2
Figure 3
Figure 4Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsLung Cancer Diagnosis and Treatment · Radiomics and Machine Learning in Medical Imaging · Advanced Radiotherapy Techniques
