arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09465cs.CVcs.AI
收藏

MedMAP:通过对齐促进不完备多模态脑肿瘤分割

MedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment

University of Liverpool(利物浦大学);Duke Kunshan University(昆山杜克大学)

Tianyi Liu, Zhaorui Tan, Muyin Chen, Xi Yang, Haochuan Jiang, Kaizhu Huang

AI总结:

针对临床中MRI模态缺失导致脑肿瘤分割性能受限的问题,提出MedMAP范式,将多模态潜在特征对齐到分布锚点以替代预训练模型,经理论证明和多数据集实验验证可有效提升分割性能。

摘要:

脑肿瘤分割通常基于多模态磁共振成像(MRI)。但在临床实践中,某些MRI模态可能缺失,这带来了更具挑战性的场景。为应对这一难题,知识蒸馏、域自适应和共享潜在空间已成为常见的有效策略。然而,现有研究通常忽略模态间差距,因此无法学习到跨不同模态的重要不变特征表示,这一缺陷进而导致缺失模态模型的性能受限。为改善这些问题,自然视觉分割任务中会使用预训练模型来缩小差距,但医学图像分割任务中往往缺乏可用的优质预训练模型。沿着这一思路,本文提出了一种新范式,将涉及模态的潜在特征对齐到一个明确定义的分布锚点,以此替代预训练模型。作为核心贡献,我们证明该新型训练范式能保证紧致的证据下界,从而从理论上验证了其有效性。在不同骨干网络上开展的大量实验证实,所提范式能够实现不变特征表示,生成的模型可缩小模态差距。采用我们对齐范式的模型在BraTS2018和BraTS2020数据集上均展现出优越性能。

英文摘要:

Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents a more difficult scenario. To cope with this challenge, Knowledge Distillation, Domain Adaption, and Shared Latent Space have emerged as commonly promising strategies. However, recent efforts typically overlook the modality gaps and thus fail to learn important invariant feature representations across different modalities. Such drawback consequently leads to limited performance for missing modality models. To ameliorate these problems, pre-trained models are used in natural visual segmentation tasks to minimize the gaps. However, promising pre-trained models are often unavailable in medical image segmentation tasks. Along this line, in this paper, we propose a novel paradigm that aligns latent features of involved modalities to a well-defined distribution anchor as the substitution of the pre-trained model}. As a major contribution, we prove that our novel training paradigm ensures a tight evidence lower bound, thus theoretically certifying its effectiveness. Extensive experiments on different backbones validate that the proposed paradigm can enable invariant feature representations and produce models with narrowed modality gaps. Models with our alignment paradigm show their superior performance on both BraTS2018 and BraTS2020 datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑