ESTRO 2023 - Abstract Book

S1356

Digital Posters

ESTRO 2023

Conclusion Data curation had a significant impact on model performance, and on the evaluation of model performance. The model based on curated data had a substantially higher precision and accuracy than the model based on clinical data. Our results emphasize the importance of data curation in DL.

PO-1655 Multi-center auto-segmentation model for internal mammary nodes using clinical data: A DBCG study

E.R. Skarsø 1,2 , L.H. Refsgaard 3 , L. Hindhede Refsgaard 2 , A. Saini 4 , E.L. Lorenzen 5 , E. Maae 6 , E. Yates 7 , I. Jensen 8 , K. Andersen 9 , K. Boye 10 , L.W. Matthiessen 9 , M. Maraldo 10 , M. Berg 6 , M.H. Nielsen 11 , M. Møller 8 , S.A. Al-Rawi 4 , B. Offersen 3,7,1,2 , S.S. Korreman 7,1,2 1 Aarhus University Hospital, Danish Center for Particle Therapy, Aarhus, Denmark; 2 Aarhus University, Department of Clinical medicine, Aarhus, Denmark; 3 Aarhus University Hospital, Department of Experimental Clinical Oncology, Aarhus, Denmark; 4 Zealand University Hospital, Department of Clinical Oncology and Palliative Care, Næstved, Denmark; 5 Odense University Hospital, Laboratory of Radiation Physics, Odense, Denmark; 6 Vejle Hospital, University Hospital of Southern Denmark, Department of Oncology, Vejle, Denmark; 7 Aarhus University Hospital, Department of Oncology, Aarhus, Denmark; 8 Aalborg University Hospital, Department of Oncology, Aalborg, Denmark; 9 Herlev and Gentofte Hospital, Department of Oncology, Herlev, Denmark; 10 Copenhagen University Hospital – Rigshospitalet, Department of Oncology, Copenhagen, Denmark; 11 Odense University Hospital, Department of Oncology, Odense, Denmark Purpose or Objective National standardization of breast cancer (BC) radiotherapy (RT) is desirable, and a generalizable auto-segmentation model to delineate target structures can help achieve this. We developed a deep learning (DL) based segmentation model for internal mammary lymph nodes (CTVn_IMN) for left-sided BC patients. The model was trained on national real world clinical delineations, all adhering to the Danish Breast Cancer Group (DBCG) guidelines. Materials and Methods We included clinical CTVn_IMN delineations (mean volume 9.2 cm3) and CT scans (slice thickness 2-3mm) from a total of 778 high-risk left-sided BC patients treated with adjuvant RT in all seven centres in the nation during 2015-16. Delineations were crudely sorted to eliminate obvious deviations from guidelines: Delineations extending beyond costa 3 caudally and with a width outside the interval [6.6mm;24mm] were removed. The cropped CT scans and CTVn_IMN delineations were used as input in a 3D full resolution nnUNet with five-fold (1000 epochs) cross-validation and default parameters. Clinical delineations were used as ground truth. We report Dice coefficient (DSC), Hausdorff distance 95th percentile (HD95) and average surface distance (MSD) between predictions and clinical ground truth on the test set using evaluation functions in nnUNet. In addition, the difference in cranial and caudal extension was measured as number of slices. Results A total of 424 patients were excluded during the sorting procedure, leaving 319/35 patients to train/test the model. The model performed with a median DSC = 0.70, HD95 distance = 4.83mm and MSD = 1.45mm, figure 1. The largest variation between ground truth and predictions were in the caudal extension, varying up to 18 slices, figure 2. The lowest DSC scored patients, showed large disagreements in both cranial and caudal part of the CTVn_IMN. Also, the ground truth was wider than the prediction, see figure 1, patient 1. However, from a clinical perspective, these two DL- Patients were randomly split into a training set (90%) and a test set (10%). The CT scans were cropped to the posterior and caudal part of the heart and cranial part of the lungs.