Papers for

radiology device developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Brain metastasis tool improves detection of rare brain surgery cavities

CarveMix-RC: Addressing Rare-Class Imbalance Through Lesion-Aware Synthetic Augmentation for Brain Metastasis Segmentation

Abstract: Accurate segmentation of post-treatment brain metastases is essential for treatment planning, longitudinal disease monitoring, and quantitative assessment of therapeutic response. The BraTS-MET 2026 Task 1 challenge introduces a clinically relevant segmentation problem involving four anatomically distinct tumor subregions: non-enhancing tumor core (NETC), surrounding non-enhancing FLAIR hyperintensity (SNFH), enhancing tumor (ET), and the resection cavity (RC). Among these, RC segmentation is particularly challenging because of its low prevalence, heterogeneous postoperative appearance, and lesion-wise evaluation protocol, leading conventional segmentation networks to prioritize dominant tumor classes during optimization. The proposed nnU-Net-based framework explicitly addresses RC segmentation through four complementary components: (i) RC-weighted Dice and Cross-Entropy optimization to alleviate class imbalance, (ii) anatomically consistent cavity augmentation to increase the diversity of postoperative cavity appearances, (iii) a residual encoder architecture for enhanced multi-scale feature learning, and (iv) lesion-aware morphological post-processing to suppress false-positive cavity predictions while preserving anatomically plausible structures. The framework is evaluated on the BraTS-MET 2026 Task 1 online validation benchmark. Among the evaluated configurations, the ensemble model (Residual Encoder nnU-Net + nnU-Net + RC-aware CarveMix) achieves the best performance, with lesion-wise Dice scores of 0.732, 0.752, 0.708, and 0.575 and corresponding NSD scores of 0.794, 0.798, 0.727, and 0.474 for ET, TC, WT, and RC, respectively. These experimental results show that integrating RC-aware optimization, anatomically consistent augmentation, and lesion-aware post-processing provides an effective strategy for improving rare resection cavity segmentation in post-treatment brain metastases.

Mon 28 SeptComputer Vision and Pattern RecognitionArtificial Intelligence
The gist
Accurately identifying different parts of brain tumors after treatment is important for doctors to plan further care. One part called the resection cavity, which is where surgery removed the tumor, is hard to find because it appears less often and looks different in each patient. The authors created a specialized computer tool that uses new ways to train and improve itself, focusing on finding the resection cavity better than before. Their method also uses smart ways to add fake examples and clean up results to reduce mistakes. They tested their system on a public challenge and showed better accuracy in detecting these rare surgical cavities.
Open → 2609.35195v1