Comparing multi-image and image augmentation strategies for deep learning-based prostate segmentation

Samuel Fransson

doi:10.1016/j.phro.2024.100551

Comparing multi-image and image augmentation strategies for deep learning-based prostate segmentation

Phys Imaging Radiat Oncol. 2024 Feb 20:29:100551. doi: 10.1016/j.phro.2024.100551. eCollection 2024 Jan.

Author

Samuel Fransson^{1

2}

Affiliations

¹ Department of Medical Physics, Uppsala University Hospital, Uppsala, Sweden.
² Department of Surgical Sciences, Uppsala University, Uppsala, Sweden.

Abstract

During MR-Linac-based adaptive radiotherapy, multiple images are acquired per patient. These can be applied in training deep learning networks to reduce annotation efforts. This study examined the advantage of using multiple versus single images for prostate treatment segmentation. Findings indicate minimal improvement in DICE and Hausdorff 95% metrics with multiple images. Maximum difference was seen for the rectum in the low data regime, training with images from five patients. Utilizing a 2D U-net resulted in DICE values of 0.80/0.83 when including 1/5 images per patient, respectively. Including more patients in training reduced the difference. Standard augmentation methods remained more effective.

Keywords: Deep-learning; MR-Linac; Prostate; Segmentation.