多模态独立编码提升医学影像分割精度，优于自监督预训练的Transformer模型。
Multi-encoder nnU-Net outperforms transformer models with self-supervised pretraining
- 用多个独立编码器分别处理不同MRI模态，融合前保留模态特异性特征。
- 在肿瘤分割任务中达到93.72%的Dice系数，超越nnU-Net、SegResNet和Swin UNETR。
- 适合标注数据少、多模态医学影像分割场景，尤其对放射科临床决策有帮助。
本研究针对医学图像分割这一关键任务，旨在自动识别和勾画医学影像中的解剖结构与病灶区域。准确分割对放射学至关重要，可辅助精确定位肿瘤等异常，支持有效诊断、治疗规划及疾病进展监测。肿瘤的大小、形状和位置显著影响临床决策与治疗策略，因此精准分割是放射科工作流的核心。然而，MRI模态差异、图像伪影及标注数据稀缺等因素加剧了分割难度，制约传统模型性能。为此，我们提出一种新型自监督学习的多编码器nnU-Net架构，通过独立编码器分别处理多种MRI模态，在特征融合前捕捉模态特异性信息，从而提升分割精度。该模型在肿瘤分割任务中取得93.72%的Dice相似系数（DSC），优于基础nnU-Net、SegResNet和Swin UNETR。利用各模态独特信息，该架构在标注数据有限情况下仍表现优异，显著提升分割效果。
原文摘要 · Abstract (English)
This study addresses the essential task of medical image segmentation, which involves the automatic identification and delineation of anatomical structures and pathological regions in medical images. Accurate segmentation is crucial in radiology, as it aids in the precise localization of abnormalities such as tumors, thereby enabling effective diagnosis, treatment planning, and monitoring of disease progression. Specifically, the size, shape, and location of tumors can significantly influence clinical decision-making and therapeutic strategies, making accurate segmentation a key component of radiological workflows. However, challenges posed by variations in MRI modalities, image artifacts, and the scarcity of labeled data complicate the segmentation task and impact the performance of traditional models. To overcome these limitations, we propose a novel self-supervised learning Multi-encoder nnU-Net architecture designed to process multiple MRI modalities independently through separate encoders. This approach allows the model to capture modality-specific features before fusing them for the final segmentation, thus improving accuracy. Our Multi-encoder nnU-Net demonstrates exceptional performance, achieving a Dice Similarity Coefficient (DSC) of 93.72%, which surpasses that of other models such as vanilla nnU-Net, SegResNet, and Swin UNETR. By leveraging the unique information provided by each modality, the model enhances segmentation tasks, particularly in scenarios with limited annotated data. Evaluations highlight the effectiveness of this architecture in improving tumor segmentation outcomes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。