Uni-Light: An Ultra-Lightweight Framework via Uncertainty-Aware Knowledge Distillation for Brain Tumour Segmentation

• URL: http://arxiv.org/abs/2609.06729v2
• Date: Fri, 11 Sep 2026 07:40:12 GMT
• Title: Uni-Light: An Ultra-Lightweight Framework via Uncertainty-Aware Knowledge Distillation for Brain Tumour Segmentation
• Abstract summary: Existing brain tumour segmentation methods often suffer from heavy computational demands.<n>We propose a novel ultra-lightweight framework (Uni-Light) that achieves high-fidelity segmentation.<n>Uni-Light reduces parameters by 97.56%, floating-point operations (FLOPs) by 73.03%, and inference memory footprint by 81.58%.
• Score: 0.13980986259786224
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate 3D brain tumour segmentation from multi-modal Magnetic Resonance Imaging (MRI) is essential for clinical diagnosis and treatment planning. Existing brain tumour segmentation methods often suffer from heavy computational demands, while current lightweight architectures frequently lack the capacity to maintain segmentation fidelity in complex tumour regions. To address these issues, we propose a novel ultra-lightweight framework (Uni-Light) that achieves high-fidelity segmentation with substantially reduced computational overhead. It combines multi-scale convolutions with an uncertainty-aware knowledge distillation scheme that directs the student model toward hard-to-classify regions, complemented by a Signed Distance Field boundary loss for geometric constraints. Experimental results on BraTS2023-GLI and MSD-BTS datasets demonstrate that Uni-Light reduces parameters by 97.56%, floating-point operations (FLOPs) by 73.03%, and inference memory footprint by 81.58%, while surpassing the state-of-the-art model by an average of 1.47% in Dice score, offering a highly competitive trade-off between segmentation accuracy and computational efficiency in resource-constrained clinical settings. This work also advances data engineering for medical imaging by demonstrating that teacher model uncertainty can be exploited as a data-driven supervisory signal, re-prioritising the training data distribution without requiring additional annotation.

Related papers

• ResNet-34 with Lightweight Decoder for Accurate and Efficient Segmentation of Fetal Brain MRI [3.3745145603015985]
  This research introduces a novel deep learning model that combines a ResNet-34 encoder with a lightweight decoder.<n>It is trained and validated on the FeTA dataset using 5-fold cross-validation.<n>It achieves an average Accuracy of 97.37% with a mean Dice Similarity Coefficient (DSC) of 90.33%, mean Intersection over Union (IoU) of 86.93%, and Precision of 90.83%.
  arXiv  Detail & Related papers  (2026-05-31T15:25:37Z)
• D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities [54.87947751720332]
  We propose a novel segmentation model D3Seg to maintain stable performance under missing-modality settings.<n>The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing modality configurations.
  arXiv  Detail & Related papers  (2026-05-21T09:55:42Z)
• UniField: A Unified Field-Aware MRI Enhancement Framework [45.03230466428695]
  methodname is a unified framework integrating multiple modalities and enhancement tasks.<n>We exploit comprehensive 3D volumetric information by leveraging pre-trained 3D foundation models.<n>We organize and publicly release a comprehensive paired multi-field MRI dataset.
  arXiv  Detail & Related papers  (2026-03-10T05:45:12Z)
• Advancing Brain Tumor Segmentation via Attention-based 3D U-Net Architecture and Digital Image Processing [0.0]
  This study aims to enhance the performance of brain tumor segmentation, ultimately improving the reliability of diagnosis.<n>The proposed model is thoroughly evaluated and assessed on the BraTS 2020 dataset using various performance metrics to accomplish this goal.
  arXiv  Detail & Related papers  (2025-10-21T22:11:19Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• Resource-Efficient Glioma Segmentation on Sub-Saharan MRI [4.522693679811991]
  This study introduces a robust and computationally efficient deep learning framework tailored for resource-quality settings.<n>We leveraged a 3D Attention UNet architecture augmented with residual blocks and enhanced through transfer learning from pre-trained weights on the BraTS-Africa dataset.<n>Our model was evaluated on 95 MRI cases from the BraTS-Africa dataset, a benchmark for glioma segmentation in SSA MRI data.
  arXiv  Detail & Related papers  (2025-09-11T13:52:47Z)
• InfLocNet: Enhanced Lung Infection Localization and Disease Detection from Chest X-Ray Images Using Lightweight Deep Learning [0.5242869847419834]
  This paper presents a novel, lightweight deep learning based segmentation-classification network. It is designed to enhance the detection and localization of lung infections using chest X-ray images. Our model achieves remarkable results with an Intersection over Union (IoU) of 93.59% and a Dice Similarity Coefficient (DSC) of 97.61% in lung area segmentation.
  arXiv  Detail & Related papers  (2024-08-12T19:19:23Z)
• Unveiling Incomplete Modality Brain Tumor Segmentation: Leveraging Masked Predicted Auto-Encoder and Divergence Learning [6.44069573245889]
  Brain tumor segmentation remains a significant challenge, particularly in the context of multi-modal magnetic resonance imaging (MRI) We propose a novel strategy, which is called masked predicted pre-training, enabling robust feature learning from incomplete modality data. In the fine-tuning phase, we utilize a knowledge distillation technique to align features between complete and missing modality data, simultaneously enhancing model robustness.
  arXiv  Detail & Related papers  (2024-06-12T20:35:16Z)
• LATUP-Net: A Lightweight 3D Attention U-Net with Parallel Convolutions for Brain Tumor Segmentation [7.1789008189318455]
  LATUP-Net is a lightweight 3D ATtention U-Net with Parallel convolutions. It is specifically designed to reduce computational requirements significantly while maintaining high segmentation performance. It achieves promising segmentation performance: the average Dice scores for the whole tumor, tumor core, and enhancing tumor on the BraTS 2020 dataset are 88.41%, 83.82%, and 73.67%, and on the BraTS 2021 dataset, they are 90.29%, 89.54%, and 83.92%, respectively.
  arXiv  Detail & Related papers  (2024-04-09T00:05:45Z)
• Leveraging Frequency Domain Learning in 3D Vessel Segmentation [50.54833091336862]
  In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models. We show that our novel network achieves remarkable dice performance (84.37% on ASACA500 and 80.32% on ImageCAS) in tubular vessel segmentation tasks.
  arXiv  Detail & Related papers  (2024-01-11T19:07:58Z)
• EMT-NET: Efficient multitask network for computer-aided diagnosis of breast cancer [58.720142291102135]
  We propose an efficient and light-weighted learning architecture to classify and segment breast tumors simultaneously. We incorporate a segmentation task into a tumor classification network, which makes the backbone network learn representations focused on tumor regions. The accuracy, sensitivity, and specificity of tumor classification is 88.6%, 94.1%, and 85.3%, respectively.
  arXiv  Detail & Related papers  (2022-01-13T05:24:40Z)
• Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso [102.84915019938413]
  Non-invasive techniques like magnetoencephalography (MEG) or electroencephalography (EEG) offer promise of non-invasive techniques. The problem of source localization, or source imaging, poses however a high-dimensional statistical inference challenge. We propose an ensemble of desparsified multi-task Lasso (ecd-MTLasso) to deal with this problem.
  arXiv  Detail & Related papers  (2020-09-29T21:17:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.