Background Accurate segmentation of lung cancer lesions in computed tomography (CT) is essential for precise diagnosis, personalized therapy planning, and treatment response assessment. While automatic segmentation of the primary lung lesion has been widely studied, the ability to segment multiple lesions per patient remains underexplored. In this study, we address this gap by introducing a novel, automated approach for multi-instance segmentation of lung cancer lesions, leveraging a heterogeneous cohort with real-world multicenter data. Materials and methods We analyzed 1,081 retrospectively collected CT scans with 5,322 annotated lesions (4.92 ± 13.05 lesions per scan). The cohort was stratified into training (n = 868) and testing (n = 213) subsets. We developed an automated three-step pipeline, including thoracic bounding box extraction, multi-instance lesion segmentation, and false positive reduction via a novel multiscale cascade classifier to filter spurious and non-lesion candidates. Results On the independent test set, our method achieved a Dice similarity coefficient of 76% for segmentation and a lesion detection sensitivity of 85%. When evaluated on an external dataset of 188 real-world cases, it achieved a Dice similarity coefficient of 73%, and a lesion detection sensitivity of 85%. Conclusion Our approach accurately detected and segmented multiple lung cancer lesions per patient on CT scans, demonstrating robustness across an independent test set and an external real-world dataset. Relevance statement AI-driven segmentation comprehensively captures lesion burden, enhancing lung cancer assessment and disease monitoring Key Points <UnorderedList Mark="Bullet"> <ItemContent> Automatic multi-instance lung cancer lesion segmentation is underexplored yet crucial for disease assessment. </ItemContent> <ItemContent> Developed a deep learning-based segmentation pipeline trained on multi-center real-world data, which reached 85% sensitivity at external validation. </ItemContent> <ItemContent> Thoracic bounding box and false positive reduction techniques improved the pipeline’s segmentation performance. </ItemContent> </UnorderedList> Graphical Abstract

Advancing deep learning-based segmentation for multiple lung cancer lesions in real-world multicenter CT scans

期刊论文
出版模式：

开放获取
发表日期：

2025年8月18日

查看全文

Xavier Rafael-Palou,
Ana Jimenez-Pastor,
Luis Martí-Bonmatí,
Carlos F. Muñoz-Nuñez,
Mario Laudazi,
Ángel Alberich-Bayarri

摘要

Background

Accurate segmentation of lung cancer lesions in computed tomography (CT) is essential for precise diagnosis, personalized therapy planning, and treatment response assessment. While automatic segmentation of the primary lung lesion has been widely studied, the ability to segment multiple lesions per patient remains underexplored. In this study, we address this gap by introducing a novel, automated approach for multi-instance segmentation of lung cancer lesions, leveraging a heterogeneous cohort with real-world multicenter data.

Materials and methods

We analyzed 1,081 retrospectively collected CT scans with 5,322 annotated lesions (4.92 ± 13.05 lesions per scan). The cohort was stratified into training (n = 868) and testing (n = 213) subsets. We developed an automated three-step pipeline, including thoracic bounding box extraction, multi-instance lesion segmentation, and false positive reduction via a novel multiscale cascade classifier to filter spurious and non-lesion candidates.

Results

On the independent test set, our method achieved a Dice similarity coefficient of 76% for segmentation and a lesion detection sensitivity of 85%. When evaluated on an external dataset of 188 real-world cases, it achieved a Dice similarity coefficient of 73%, and a lesion detection sensitivity of 85%.

Conclusion

Our approach accurately detected and segmented multiple lung cancer lesions per patient on CT scans, demonstrating robustness across an independent test set and an external real-world dataset.

Relevance statement

AI-driven segmentation comprehensively captures lesion burden, enhancing lung cancer assessment and disease monitoring

Key Points

Automatic multi-instance lung cancer lesion segmentation is underexplored yet crucial for disease assessment.

Developed a deep learning-based segmentation pipeline trained on multi-center real-world data, which reached 85% sensitivity at external validation.

Thoracic bounding box and false positive reduction techniques improved the pipeline’s segmentation performance.

Graphical Abstract