Swin-LiteMedSAM: 面向大规模医学图像数据集的轻量级基于边界框的分割一切模型
Swin-LiteMedSAM: A Lightweight Box-Based Segment Anything Model for Large-Scale Medical Image Datasets
AI总结：
针对现有医学SAM模型计算量大、推理慢的问题，提出轻量级Swin-LiteMedSAM，集成微型Swin Transformer、多类提示与跳跃连接，在CVPR 2024相关挑战赛中兼顾性能与速度，取得第四名。
摘要：
医学成像对疾病的诊断和治疗至关重要，其中医学图像分割作为一项子任务受到高度关注。然而，自动医学图像分割模型通常是任务专属的，难以应对多种场景，例如不同的成像模态和感兴趣区域。随着分割一切模型（Segment Anything Model, SAM）的推出，训练适用于多种临床场景的通用模型已成为可能。近年来，研究者提出了多种医学SAM（Medical SAM, MedSAM）方法，但这些模型往往依赖重型图像编码器来实现高性能，由于其计算需求高、推理速度慢，在实际应用中可能并不实用。为解决这一问题，轻量级MedSAM（LiteMedSAM）可提供可行的解决方案，在实现高性能的同时所需资源更少、耗时更短。\n在本研究中，我们提出了Swin-LiteMedSAM，这是LiteMedSAM的一个新变体。该模型将微型Swin Transformer作为图像编码器集成进来，纳入了多种类型的提示，包括从给定边界框生成的基于框的点和涂鸦，并且在图像编码器与掩码解码器之间建立了跳跃连接。在CVPR 2024的“笔记本上的医学图像分割一切”（Segment Anything in Medical Images on Laptop）挑战赛中，我们的方法在分割性能和速度之间取得了良好的平衡，与赛事主办方提供的LiteMedSAM基线相比，在多种模态上的整体结果有显著提升。我们提出的模型在验证集上取得了0.8678的DSC得分和0.8844的NSD得分；在最终测试集上，其DSC得分为0.8193，NSD得分为0.8461，在挑战赛中获得第四名。
英文摘要：
Medical imaging is essential for the diagnosis and treatment of diseases, with medical image segmentation as a subtask receiving high attention. However, automatic medical image segmentation models are typically task-specific and struggle to handle multiple scenarios, such as different imaging modalities and regions of interest. With the introduction of the Segment Anything Model (SAM), training a universal model for various clinical scenarios has become feasible. Recently, several Medical SAM (MedSAM) methods have been proposed, but these models often rely on heavy image encoders to achieve high performance, which may not be practical for real-world applications due to their high computational demands and slow inference speed. To address this issue, a lightweight version of the MedSAM (LiteMedSAM) can provide a viable solution, achieving high performance while requiring fewer resources and less time. In this work, we introduce Swin-LiteMedSAM, a new variant of LiteMedSAM. This model integrates the tiny Swin Transformer as the image encoder, incorporates multiple types of prompts, including box-based points and scribble generated from a given bounding box, and establishes skip connections between the image encoder and the mask decoder. In the \textit{Segment Anything in Medical Images on Laptop} challenge (CVPR 2024), our approach strikes a good balance between segmentation performance and speed, demonstrating significantly improved overall results across multiple modalities compared to the LiteMedSAM baseline provided by the challenge organizers. Our proposed model achieved a DSC score of \textbf{0.8678} and an NSD score of \textbf{0.8844} on the validation set. On the final test set, it attained a DSC score of \textbf{0.8193} and an NSD score of \textbf{0.8461}, securing fourth place in the challenge.
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。
