Evaluating Danish Breast Cancer Group locoregional radiotherapy guideline adherence in clinical treatment data 2008-2016: The DBCG RT Nation study.

BACKGROUND AND PURPOSE: Guideline adherence in radiotherapy is crucial for maintaining treatment quality and consistency, particularly in non-trial patient settings where most treatments occur. The study aimed to assess the impact of guideline changes on treatment planning practices and compare manual registry data accuracy with treatment planning data. MATERIALS AND METHODS: This study utilised the DBCG RT Nation cohort, a collection of breast cancer radiotherapy data in Denmark, to evaluate adherence to guidelines from 2008 to 2016. The cohort included 7448 high-risk breast cancer patients. National guideline changes included, fractionation, introduction of respiratory gating, irradiation of the internal mammary lymph nodes, use of the simultaneous integrated boost technique and inclusion of the Left Anterior Descending coronary artery in delineation practice. Methods for structure name mapping, laterality detection, detection of temporal changes in population mean lung volume, and dose evaluation were presented and applied. Manually registered treatment characteristic data was obtained from the Danish Breast Cancer Database for comparison. RESULTS: The study found immediate and consistent adherence to guideline changes across Danish radiotherapy centres. Treatment practices before guideline implementation were documented and showed a variation among centres. Discrepancies between manual registry data and actual treatment planning data were as high as 10% for some measures. CONCLUSION: National guideline changes could be detected in the routine treatment data, with a high degree of compliance and short implementation time. Data extracted from treatment planning data files provides a more accurate and detailed characterisation of treatments and guideline adherence than medical register data.

End-to-end framework for automated collection of large multicentre radiotherapy datasets demonstrated in a Danish Breast Cancer Group cohort.

Large Digital Imaging and Communications in Medicine (DICOM) datasets are key to support research and the development of machine learning technology in radiotherapy (RT). However, the tools for multi-centre data collection, curation and standardisation are not readily available. Automated batch DICOM export solutions were demonstrated for a multicentre setup. A Python solution, Collaborative DICOM analysis for RT (CORDIAL-RT) was developed for curation, standardisation, and analysis of the collected data. The setup was demonstrated in the DBCG RT-Nation study, where 86% (n = 7748) of treatments in the inclusion period were collected and quality assured, supporting the applicability of the end-to-end framework.

Development of a national deep learning-based auto-segmentation model for the heart on clinical delineations from the DBCG RT nation cohort.

BACKGROUND: This study aimed at investigating the feasibility of developing a deep learning-based auto-segmentation model for the heart trained on clinical delineations. MATERIAL AND METHODS: This study included two different datasets. The first dataset contained clinical heart delineations from the DBCG RT Nation study (1,561 patients). The second dataset was smaller (114 patients), but with corrected heart delineations. Before training the model on the clinical delineations an outlier-detection was performed, to remove cases with gross deviations from the delineation guideline. No outlier detection was performed for the dataset with corrected heart delineations. Both models were trained with a 3D full resolution nnUNet. The models were evaluated with the dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and Mean Surface Distance (MSD). The difference between the models were tested with the Mann-Whitney U-test. The balance of dataset quantity versus quality was investigated, by stepwise reducing the cohort size for the model trained on clinical delineations. RESULTS: During the outlier-detection 137 patients were excluded from the clinical cohort due to non-compliance with delineation guidelines. The model trained on the curated clinical cohort performed with a median DSC of 0.96 (IQR 0.94-0.96), median HD95 of 4.00 mm (IQR 3.00 mm-6.00 mm) and a median MSD of 1.49 mm (IQR 1.12 mm-2.02 mm). The model trained on the dedicated and corrected cohort performed with a median DSC of 0.95 (IQR 0.93-0.96), median HD95 of 5.65 mm (IQR 3.37 mm-8.62 mm) and median MSD of 1.63 mm (IQR 1.35 mm-2.11 mm). The difference between the two models were found non-significant for all metrics (p > 0.05). Reduction of cohort size showed no significant difference for all metrics (p > 0.05). However, with the smallest cohort size, a few outlier structures were found. CONCLUSIONS: This study demonstrated a deep learning-based auto-segmentation model trained on curated clinical delineations which performs on par with a model trained on dedicated delineations, making it easier to develop multi-institutional auto-segmentation models.

The potential benefits from respiratory gating for breast cancer patients regarding target coverage and dose to organs at risk when applying strict dose limits to the heart: results from the DBCG HYPO trial.

PURPOSE: The potential benefits from respiratory gating (RG) compared to free-breathing (FB) regarding target coverage and dose to organs at risk for breast cancer patients receiving post-operative radiotherapy (RT) in the DBCG HYPO multicentre trial are reported. MATERIAL AND METHODS: Patients included in the DBCG HYPO trial were randomized between 50 Gy in 25 fractions (normofractionated) versus 40 Gy in 15 fractions (hypofractionated). A tangential forward field-in-field dose planning technique was used to cover the clinical target volume (CTV) with the intent to limit dose to the left anterior descending coronary artery (LADCA) to 20 Gy and 17 Gy in the normo- and hypofractionated arms, respectively. Treatment plan data for 1327 patients from four Danish centres was retrospectively analyzed. FB right-sided patients served as control group for the left-sided patients regarding CTV V95% (relative volume receiving at least 95% of the prescribed dose), mean heart dose (MHD) and mean lung dose (MLD). RESULTS: Median CTV V95% was for FB right-sided, FB left-sided and RG left-sided patients 94.6, 92.6 and 94.7% for normofractionated therapy, respectively, and 94.6, 91.8 and 94.4% for hypofractionated therapy and did not differ significantly for RG left-sided plans compared to FB right-sided in either study arm. CTV V95% was significantly lower for FB versus RG for left-sided plans in both arms. Median MHD was 0.7, 1.8 and 1.5 Gy (normofractionated therapy) versus 0.6, 1.5 and 1.2 Gy (hypofractionated therapy), respectively. The corresponding median MLD was 9.0, 8.3 and 7.3 Gy versus 7.3, 6.4 and 5.8 Gy, respectively. CONCLUSIONS: RG for left-sided breast cancer patients ensured similar CTV V95% as for FB right-sided patients. MLD was lower for RG due to the increased lung volume. MHD was generally low due to strict protocol-defined maximum dose to LADCA, but for left-sided patients RG led to significantly lower MHD.