Comparison of texture-based classification and deep learning for plantar soft tissue histology segmentation.
Comparison of texture-based classification and deep learning for plantar soft tissue histology segmentation.
复制标题
DOI：
10.1016/j.compbiomed.2021.104491
复制
发表时间：
2021-07
影响因子：
7.7
通讯作者：
Ledoux WR
中科院分区：
文献类型：
--
作者：
Brady L;Wang YN;Rombokas E;Ledoux WR
组织形态学测量可用于识别与疾病病理力学相关的微结构变化，特别是糖尿病患者的足底软组织变化。然而，这些测量是耗时的，并且容易受到采样和人为测量误差的影响。我们研究了两种方法来自动分割足底软组织染色与修改后的哈特的弹性蛋白染色的最终目标，随后的形态学分析。第一种方法使用多个纹理和颜色为基础的功能与瓦片式分类。第二种方法使用了从U-Net架构修改而来的卷积神经网络，具有更少的通道维度和额外的下采样步骤。一个混合的颜色和纹理特征，傅立叶减少直方图的均匀改进的对手颜色局部二进制模式（f-IOCLBP），产生了最好的基于特征的分割，但仍然表现出3.6%的平均比修改后的U-Net差。基于纹理的方法对光照和染色强度的变化敏感，并且分割错误通常发生在单个组织的大区域或组织边界处。U-Net能够分割小的、少像素的组织边界，并且通过后处理来清除错误通常是微不足道的。U-Net方法优于手工制作的特征，用于用弹性蛋白的改良哈特染色剂染色的足底软组织的分割。
Histomorphological measurements can be used to identify microstructural changes related to disease pathomechanics, in particular, plantar soft tissue changes with diabetes. However, these measurements are time-consuming and susceptible to sampling and human measurement error. We investigated two approaches to automate segmentation of plantar soft tissue stained with modified Hart’s stain for elastin with the eventual goal of subsequent morphological analysis. The first approach used multiple texture- and color-based features with tile-wise classification. The second approach used a convolutional neural network modified from the U-Net architecture with fewer channel dimensions and additional downsampling steps. A hybrid color and texture feature, Fourier reduced histogram of uniform improved opponent color local binary patterns (f-IOCLBP), yielded the best feature-based segmentation, but still performed 3.6% worse on average than the modified U-Net. The texture-based method was sensitive to changes in illumination and stain intensity, and segmentation errors were often in large regions of single tissues or at tissue boundaries. The U-Net was able to segment small, few-pixel tissue boundaries, and errors were often trivial to clean up with post-processing. A U-Net approach outperforms hand-crafted features for segmentation of plantar soft tissue stained with modified Hart’s stain for elastin.
登录
查看更多内容
影响因子：
5.2
作者：
Bianconi F;Kather JN;Reyes-Aldasoro CC
通讯作者：
Reyes-Aldasoro CC
影响因子：
6
作者：
Komura D;Ishikawa S
通讯作者：
Ishikawa S
影响因子：
3.7
作者：
Li X;Plataniotis KN
通讯作者：
Plataniotis KN
影响因子：
1.1
作者：
Bianconi, Francesco;Bello-Cerezo, Raquel;Napoletano, Paolo
通讯作者：
Napoletano, Paolo
影响因子：
5.2
作者：
Bhattacharjee, Subrata;Kim, Cho-Hee;Choi, Heung-Kook
通讯作者：
Choi, Heung-Kook