Improving the Generalizability of Deep Learning for T2-Lesion Segmentation of Gliomas in the Post-Treatment Setting

TL;DR

This paper improves deep learning models for tracking brain tumor changes after treatment by using mixed data and new techniques to better segment T2-lesions in MRI scans.

Contribution

The study introduces data mixing, transfer learning, and spatial regularization to enhance T2-lesion segmentation in post-treatment glioma MRI scans.

Findings

Including 26% treated patients in training improved performance by 13.9%.

Fine-tuning with treated glioma data improved sensitivity by 2.5% compared to data mixing.

Spatial regularization improved performance metrics like HD, Dice, and sensitivity when used with transfer learning.

Abstract

Although fully automated volumetric approaches for monitoring brain tumor response have many advantages, most available deep learning models are optimized for highly curated, multi-contrast MRI from newly diagnosed gliomas, which are not representative of post-treatment cases in the clinic. Improving segmentation for treated patients is critical to accurately tracking changes in response to therapy. We investigated mixing data from newly diagnosed (n = 208) and treated (n = 221) gliomas in training, applying transfer learning (TL) from pre- to post-treatment imaging domains, and incorporating spatial regularization for T2-lesion segmentation using only T2 FLAIR images as input to improve generalization post-treatment. These approaches were evaluated on 24 patients suspected of progression who had received prior treatment. Including 26% of treated patients in training improved performance by 13.9%, and including more treated and untreated patients resulted in minimal changes. Fine-tuning with treated glioma improved sensitivity compared to data mixing by 2.5% (p < 0.05), and spatial regularization further improved performance when used with TL by 95th HD, Dice, and sensitivity (6.8%, 0.8%, 2.2%; p < 0.05). While training with ≥60 treated patients yielded the majority of performance gain, TL and spatial regularization further improved T2-lesion segmentation to treated gliomas using a single MR contrast and minimal processing, demonstrating clinical utility in response assessment.

Figures