# An International Inter-Consortium Validation of Knowledge-Based Plan Prediction Modeling for Whole Breast Radiotherapy Treatment

## TL;DR

This study shows that radiation treatment planning models can be shared across countries, improving cancer care collaboration and consistency.

## Contribution

The study validates the cross-institutional transferability of knowledge-based planning models for breast radiotherapy.

## Key findings

- Most models accurately predicted lung doses across different patient groups.
- Predicted doses aligned closely with clinical data in 88.7% to 92.3% of cases.
- 6 out of 10 models maintained consistent performance in external testing.

## Abstract

This study explores whether treatment planning models developed in one country can be effectively used in another, helping to improve and share expertise in cancer radiotherapy. The researchers focused on right whole breast radiation treatments, creating multiple models from a large national group and testing them on patients from a different international group. The analysis examined how accurately the models predicted radiation doses to key organs, such as the lungs, and whether these predictions aligned with actual clinical data. The findings showed that most models worked well across different patient groups, with good accuracy in predicting lung doses. This suggests that knowledge-based planning models can be reliably shared between institutions, potentially saving time, improving treatment quality, and reducing variability in patient care. Such model sharing could strengthen collaboration between centers and accelerate advancements in radiotherapy planning worldwide.

Background: Knowledge-based (KB) planning is a promising approach to model prior planning experience and optimize radiotherapy. To enable the sharing of models across institutions, their transferability must be evaluated. This study aimed to validate KB prediction models developed by a national consortium using data from another multi-institutional consortium in a different country. Methods: Ten right whole breast tangential field (RWB-TF) models were built within the national consortium. A cohort of 20 patients from the external consortium was used for testing. Transferability was defined when the ipsilateral (IPSI) lung first principal component (PC1) was within the 10th–90th percentile of the training set. Predicted dose–volume parameters were compared with clinical dose–volume histograms (cDVHs). Results: Planning target volume (PTV) coverage strategies were comparable between the two consortia, even though significant volume differences were observed for the PTV and contralateral breast (p = 0.002 and p = 0.02, respectively). For the IPSI lung, the standard deviation of predicted mean dose/V20 Gy was 1.13 Gy/2.9% in the external consortium versus 0.55 Gy/1.6% in the training consortium. Differences between the cDVH and the predicted IPSI lung mean dose and the volume receiving more than 20 Gy (V20 Gy) were <2 Gy and <5% in 88.7% and 92.3% of cases, respectively. PC1 values fell within the 10th–90th percentile for ≥90% of patients in 6/10 models and 65–85% for the remaining 4. Conclusions: This study demonstrates the feasibility of applying RWB-TF KB models beyond the consortium in which they were developed, supporting broader clinical implementation. This retrospective study was supported by AIRC (Associazione Italiana per la Ricerca sul Cancro) and registered on ClinicalTrials.gov (NCT06317948, 12 March 2024).