The automatic segmentation of cardiac structures can transform the way we evaluate dose limits for radiotherapy in the left breast
Introduction: Radiotherapy is essential in the treatment of breast cancer, and precision in dose assessment is crucial to minimize side effects. Traditionally, anatomical structures are manually delineated, a time-consuming process subject to variability. Automatic segmentation emerges as a promisin...
Saved in:
| Main Author: | |
|---|---|
| Format: | Online |
| Language: | Portuguese |
| Published: |
Universidade Estadual de Campinas
2026
|
| Subjects: | |
| Online Access: | https://econtents.sbu.unicamp.br/inpec/index.php/saberes/article/view/20371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Introduction: Radiotherapy is essential in the treatment of breast cancer, and precision in dose assessment is crucial to minimize side effects. Traditionally, anatomical structures are manually delineated, a time-consuming process subject to variability. Automatic segmentation emerges as a promising alternative. In the radiotherapy treatment of the left breast, the RTOG 1005 protocol emphasizes the importance of cardiac delineation and the need to minimize cardiac exposure to radiation. Objective: This study aims to evaluate dose distribution in auto-segmented substructures and establish models to correlate them with the dose in the cardiac area. Methodology: We used TotalSegmentator and Limbus AI for the automatic segmentation of anatomical structures. The relationship between the volume of the cardiac area and organs at risk was evaluated using log-linear regression. Results: The mean dose distribution was significant for the left anterior descending (LAD) coronary artery, heart, and left ventricle, with greater variability in absolute volumetric assessment. We present log-linear regression models to estimate dose constraint parameters, highlighting a higher number of highly correlated comparisons for absolute dose-volume assessment. Conclusion: Dose-volume assessment protocols in patients with left breast cancer generally neglect cardiac substructures. However, automatic tools can overcome these technical difficulties. This study correlates the dose in the cardiac area with doses in specific substructures and suggests limits for planning evaluation, indicating a benefit in reporting absolute dose-volume limits for future cause-and-effect assessments. |
|---|---|
| ISSN: | 2447-9411 |
