Traumatic Brain Injury Segmentation using an Ensemble of Encoder-decoder Models

Ghanshyam Dhamat; Vaanathi Sundaresan

Home/Archive/arXiv

arXiv · 2509.24684

Traumatic Brain Injury Segmentation using an Ensemble of Encoder-decoder Models

Ghanshyam Dhamat·Vaanathi Sundaresan

View original source ↗Read source document ↗Export metadata ↓

Abstract

The identification and segmentation of moderate-severe traumatic brain injury (TBI) lesions pose a significant challenge in neuroimaging. This difficulty arises from the extreme heterogeneity of these lesions, which vary in size, number, and laterality, thereby complicating downstream image processing tasks such as image registration and brain parcellation, reducing the analytical accuracy. Thus, developing methods for highly accurate segmentation of TBI lesions is essential for reliable neuroimaging analysis. This study aims to develop an effective automated segmentation pipeline to automatically detect and segment TBI lesions in T1-weighted MRI scans. We evaluate multiple approaches to achieve accurate segmentation of the TBI lesions. The core of our pipeline leverages various architectures within the nnUNet framework for initial segmentation, complemented by post-processing strategies to enhance evaluation metrics. Our final submission to the challenge achieved an accuracy of 0.8451, Dice score values of 0.4711 and 0.8514 for images with and without visible lesions, respectively, with an overall Dice score of 0.5973, ranking among the top-6 methods in the AIMS-TBI 2025 challenge. The Python implementation of our pipeline is publicly available.

Explore related subjects

cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Ghanshyam Dhamat, Vaanathi Sundaresan. 2025-09-29. Traumatic Brain Injury Segmentation using an Ensemble of Encoder-decoder Models. https://arxiv.org/abs/2509.24684

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

SSP-GNN: Learning to Track via Bilevel Optimization

We propose a graph-based tracking formulation for multi-object tracking (MOT) where target detections contain kinematic information and re-identification features (attributes). Our method applies a successive shortest paths (SSP) algorithm to a tracking graph defined over a batch of frames. The edge costs in this tracking graph are computed via a message-passing network, a graph neural network (GNN) variant. The parameters of the GNN, and hence, the tracker, are learned end-to-end on a training set of example ground-truth tracks and detections. Specifically, learning takes the form of bilevel optimization guided by our novel loss function. We evaluate our algorithm on simulated scenarios to understand its sensitivity to scenario aspects and model hyperparameters. Across varied scenario complexities, our method compares favorably to a strong baseline.

cs.CV↗

arXiv2026

AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images

Cross-domain cell detection for microscopic images suffers from performance degradation due to distribution shifts across imaging domains. Unsupervised Domain Adaptation (UDA) strategies, attempt to overcome domain sift without requiring annotated data from target. However, requirement of availability of annotated data from the source domain and large-size data from target domain are both challenging limitations for realistic scenarios. This is especially true in medical imaging, where privacy requirements might prevent access to annotated source data, and costly data acquisition restricts extensive sampling of the target domain. To address these challenges, we propose AdaptiveCDM, a modular framework for Source-Free Few-Shot Domain Adaptive Object Detection (SF-FSDAOD) setting, that adapts a pretrained source model using only few labeled target images without accessing source data. AdaptiveCDM combines Resolution-Aware Augmentation (RAug) and Category-Aware Representation Learning (CARL). RAug alleviates the scarcity and class imbalance by augmenting instance balanced training examples, while preserving the scale fidelity and morphological properties of cellular structures. CARL enhances discriminative representation learning by encouraging class-consistent proposals, improving both localization and classification. We also introduce two competitive baselines for proposed setting: Faster-FreeShot and MT-FreeShot. Our approach achieves 40.4/43.4 mAP0.5 on M5 and 67.1/75.5 mAP0.5 on Raabin-WBC under 2-/5-shot adaptation. Despite using only a few labeled target images and no source data, AdaptiveCDM achieves competitive or superior performance compared with SOTA methods under their respective supervision settings. Ablations and qualitative analyses further substantiate the contribution of each component and the effectiveness of AdaptiveCDM in low-data regimes. Code/models will be available.

cs.CV↗

arXiv2026

Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection

Most existing video anomaly detectors rely on RGB frames alone, which limit their ability to capture abrupt or transient motion cues that are critical for identifying anomalous events. We propose Uncertainty Weighted Image Event Fusion (IEF-VAD), a framework that integrates complementary RGB and synthetic motion information through a principled weighting mechanism. The method models the high variance and heavy tailed characteristics of synthetic motion cues with a Student's t likelihood, computes value level inverse variance weights using a Laplace approximation to prevent the image modality from overshadowing motion information, and performs iterative refinement to suppress residual cross modal noise. This formulation provides a more balanced and reliable fusion process compared to cross attention or gating based approaches that often suffer from modality dominance. Without requiring an event camera or frame level annotations, IEF-VAD achieves new state of the art performance on multiple real world anomaly detection benchmarks and remains stable under degradation applied to individual modalities. The results indicate that extracting and integrating complementary motion cues is an effective direction for robust video understanding across diverse environments.

cs.CV↗