驯服Mamba用于体素级3D医学图像分割
Taming Mambas for Voxel Level 3D Medical Image Segmentation
AI总结：
本文提出将基于状态空间模型的Mamba架构引入体素级3D医学图像分割，以线性复杂度实现长程内容推理，解决CNN感受野受限和Transformer内存与数据需求过高的问题。
摘要：
近年来，3D医学分割领域一直由采用卷积神经网络（CNNs）和基于Transformer架构的深度学习模型主导，它们各自具有独特的优势与局限。CNN受限于局部感受野，而Transformer则因其巨大的内存需求以及对数据的高度依赖而受到阻碍，使其不适合在细粒度层面处理3D医学体数据。出于这些原因，全卷积神经网络（如nnUNet）在大型3D医学体数据中分割医学结构时仍然占据主导地位。尽管在开发具有次二次时间和内存复杂度的Transformer变体方面取得了诸多进展，这些模型在基于内容的推理方面仍显不足。最近的突破是Mamba，一种基于状态空间模型（SSMs）的循环神经网络（RNN），在著名的自然语言处理和基因组学基准上的许多长上下文任务（百万长度序列）中超越了Transformer，同时保持线性复杂度。
英文摘要：
Recently, the field of 3D medical segmentation has been dominated by deep learning models employing Convolutional Neural Networks (CNNs) and Transformer-based architectures, each with their distinctive strengths and limitations. CNNs are constrained by a local receptive field, whereas transformers are hindered by their substantial memory requirements as well as they data hungriness, making them not ideal for processing 3D medical volumes at a fine-grained level. For these reasons, fully convolutional neural networks, as nnUNet, still dominate the scene when segmenting medical structures in 3D large medical volumes. Despite numerous advancements towards developing transformer variants with subquadratic time and memory complexity, these models still fall short in content-based reasoning. A recent breakthrough is Mamba, a Recurrent Neural Network (RNN) based on State Space Models (SSMs) outperforming Transformers in many long-context tasks (million-length sequences) on famous natural language processing and genomic benchmarks while keeping a linear complexity.
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。
