结合视觉先验的特征重配置用于医学病灶分割
Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation
浏览论文内容
中文总结 AI 辅助
本文提出结合视觉先验的特征重配置框架FreNet，通过隐式先验神经网络（IPNN）和双域特征重配置（DFR）模块解决医学病灶分割的背景干扰与形态多样问题，在9个基准数据集上优于SOTA方法。
中文摘要 AI 辅助
医学图像中的病灶分割在临床诊断和治疗规划中发挥着关键作用。尽管已取得显著进展，但病灶分割仍面临两大核心挑战：（1）复杂的背景干扰；（2）病灶形态的多样性。现有的基于编码器-解码器的方法主要聚焦于增强特征提取或重新设计解码策略，然而这些方法在编码阶段缺乏早期先验引导和特征重配置，限制了其应对上述挑战的有效性。为解决这些局限，本文提出了FreNet，一种结合视觉先验的特征重配置框架，该框架在编码前执行像素级重配置，并在编码过程中执行特征级重配置，以实现精确的医学病灶分割。为抑制背景响应，本文提出了隐式先验神经网络（IPNN），该网络对连续空间场进行建模，并利用来自SAM的视觉先验在编码阶段前对输入图像进行重配置。为更好地应对多样的病灶形态，本文设计了双域特征重配置（DFR）模块，用于在编码阶段逐步重配置骨干网络特征。在DFR模块中，频率解耦模块（FDM）在频域中对骨干网络特征进行解耦，以增强前景与背景的可区分性；空间定位模块（SLM）则在频率解耦后对特征进行空间重定位，提升空间稳定性。在涵盖三种成像模态的9个医学图像分割基准上开展的大量实验表明，FreNet的性能显著优于当前最优（SOTA）方法。在极具挑战性的ETIS数据集上，本文方法较SOTA方法实现了5.0%的Dice指标提升，较SAM实现了7.2%的Dice指标提升。
英文摘要
Lesion segmentation in medical images plays a critical role in clinical diagnosis and treatment planning. Despite significant advances, lesion segmentation remains challenging due to two major factors: (1) complex background interference; (2) diverse lesion morphology. Existing encoder-decoder based methods mainly focus on enhancing feature extraction or redesigning decoding strategies. However, they lack early prior guidance and feature reconfiguration during the encoding stage, limiting their effectiveness in handling these challenges. To address these limitations, we propose FreNet, a feature reconfiguration framework with visual priors, which performs pixel-level reconfiguration before encoding and feature-level reconfiguration during encoding for precise medical lesion segmentation. To suppress background responses, we propose an Implicit Prior Neural Network (IPNN), which models a continuous spatial field and leverages visual prior from SAM to reconfigure input image before encoding stage. To better handle diverse lesion morphology, we design a Dual-domain Feature Reconfiguration (DFR) module to progressively reconfigure backbone features during encoding stage. Within DFR, the Frequency Decoupling Module (FDM) decouples backbone features in frequency domain to enhance foreground-background discriminability, while the Spatial Localization Module (SLM) spatially relocates and improving spatial stability after frequency decoupling. Extensive experiments on 9 medical image segmentation benchmarks across three imaging modalities demonstrate that FreNet significantly outperforms state-of-the-art (SOTA) methods. On the challenging ETIS dataset, our method achieves Dice improvements of 5.0% over SOTA method and 7.2% over SAM.
发表机构
- School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。
