DeepPyramid+：使用金字塔视图融合与可变形金字塔感受野的医学图像分割
DeepPyramid+: Medical Image Segmentation using Pyramid View Fusion and Deformable Pyramid Reception
AI总结：
本文提出 DeepPyramid+ 医学图像分割网络，通过 PVF 与 DPR 模块增强多尺度、可变形特征提取，在多模态数据集上显著提升域内与跨域分割性能。
摘要：
语义分割在许多与医学图像和视频分析相关的应用中发挥着关键作用。然而，由于相关类别具有异质性、可变形性、透明性、边界模糊以及各种失真等多样特征，为医学图像和手术视频分割设计神经网络架构颇具挑战性。我们提出了一种网络架构 DeepPyramid+，用于应对医学图像和手术视频分割中遇到的各类挑战。所提出的 DeepPyramid+ 包含两个主要模块，即“Pyramid View Fusion”（PVF，金字塔视图融合）和“Deformable Pyramid Reception”（DPR，可变形金字塔感受野），以解决上述挑战。PVF 在神经网络内复现一种推理过程，与人类视觉系统保持一致，从而增强每个像素位置上相关信息的表示。作为补充，DPR 利用扩张可变形卷积引入形状和尺度自适应的特征提取技术，提升了处理异质类别和可变形形状时的准确性与鲁棒性。在包括子宫内膜异位症视频、MRI 图像、OCT 扫描以及白内障和腹腔镜视频在内的多种数据集上进行的大量实验，证明了 DeepPyramid+ 在应对形状和尺度变化、反射以及模糊退化等各种挑战方面的有效性。DeepPyramid+ 在分割性能上取得显著提升，域内分割的 Dice 系数最高提升 3.65%，跨域分割的 Dice 系数最高提升 17%。在考虑不同骨干网络的情况下，DeepPyramid+ 在多种模态上始终优于最先进网络，展现了其多功能性。
英文摘要：
Semantic Segmentation plays a pivotal role in many applications related to medical image and video analysis. However, designing a neural network architecture for medical image and surgical video segmentation is challenging due to the diverse features of relevant classes, including heterogeneity, deformability, transparency, blunt boundaries, and various distortions. We propose a network architecture, DeepPyramid+, which addresses diverse challenges encountered in medical image and surgical video segmentation. The proposed DeepPyramid+ incorporates two major modules, namely "Pyramid View Fusion" (PVF) and "Deformable Pyramid Reception," (DPR), to address the outlined challenges. PVF replicates a deduction process within the neural network, aligning with the human visual system, thereby enhancing the representation of relative information at each pixel position. Complementarily, DPR introduces shape- and scale-adaptive feature extraction techniques using dilated deformable convolutions, enhancing accuracy and robustness in handling heterogeneous classes and deformable shapes. Extensive experiments conducted on diverse datasets, including endometriosis videos, MRI images, OCT scans, and cataract and laparoscopy videos, demonstrate the effectiveness of DeepPyramid+ in handling various challenges such as shape and scale variation, reflection, and blur degradation. DeepPyramid+ demonstrates significant improvements in segmentation performance, achieving up to a 3.65% increase in Dice coefficient for intra-domain segmentation and up to a 17% increase in Dice coefficient for cross-domain segmentation. DeepPyramid+ consistently outperforms state-of-the-art networks across diverse modalities considering different backbone networks, showcasing its versatility.
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。
