Uni-Light：一种基于不确定性感知知识蒸馏的超轻量级脑肿瘤分割框架

中文摘要 AI 辅助

从多模态磁共振成像（MRI）中准确进行三维脑肿瘤分割对于临床诊断和治疗计划至关重要。现有的脑肿瘤分割方法通常面临高计算需求的困扰，而当前的轻量级架构往往缺乏在复杂肿瘤区域保持分割保真度的能力。为解决这些问题，我们提出了一种新颖的超轻量级框架（Uni-Light），该框架在显著降低计算开销的同时实现高保真度分割。它结合了多尺度卷积与不确定性感知知识蒸馏方案，引导学生模型关注难以分类的区域，并辅以符号距离场边界损失进行几何约束。在BraTS2023-GLI和MSD-BTS数据集上的实验结果表明，Uni-Light将参数量减少了97.56%，浮点运算量（FLOPs）减少了73.03%，推理内存占用减少了81.58%，同时Dice分数平均超过最先进模型1.47%，在资源受限的临床环境中提供了分割精度与计算效率之间极具竞争力的权衡。这项工作还通过证明教师模型的不确定性可作为数据驱动的监督信号，在不需额外标注的情况下重新优先训练数据分布，推进了医学影像的数据工程。

英文摘要

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.

发表机构

• School of Computer Science, University of Nottingham（诺丁汉大学计算机学院）
• Sharif University of Technology（谢里夫理工大学）
• University of Pittsburgh（匹兹堡大学）

机构由 AI 辅助整理，请以论文原文为准。