| 邵党国,黄俊辉,徐慧.基于多尺度空洞分离卷积的U-Net分割前列腺图像[J].光电子激光,2022,33(5):554~560 |
| 基于多尺度空洞分离卷积的U-Net分割前列腺图像 |
| Segmentation of prostate image based on U-Net of multi-scale dilated separable convolution |
| 投稿时间：2021-06-20 |
| DOI： |
| 中文关键词: 数字图像处理 空洞可分离卷积 多尺度特征提取 通道注意力 图像分割 |
| 英文关键词:digital image processing dilated separable convolution multi-scale feature extraction channel attention image segmentation |
| 基金项目:国家博士后面上科学基金(2016M592894XB)、云南省基础研究面上专项 (202001AT070047)资助项目 (1.昆明理工大学 信息工程与自动化学院,云南 昆明 650500； 2.昆明医科大学 第一附属 医院,云南 昆明 650500) |
|
| 摘要点击次数: 231 |
| 全文下载次数: 7 |
| 中文摘要: |
| 前列腺核磁共振(magnetic resonance,MR)影像切片后发现有些影像 没有有效的边缘信息,这导致无法明 确定位边缘位置,进而无法分割出前列腺。同时,传统的卷积网络需要参数量庞大占用模型 的存储空间过多。本文提出了一种结合多尺度空洞可分离卷积和通道注意力的U-Net来分 割 前列腺的方法。首先,对50个3维(three-dimensional,3D)前列腺样品进行切片并对切片后图像 进行对比度增强。随 后,将处理后数据输入到残差U-Net中,使用多尺度空洞卷积和通道注意力作为编码-解 码 单元来提取特征信息。最后,使用Dice系数和豪斯多夫距离(Housdorff distance, HD)来评估分割结果。实验 在PROMISE12挑战赛数据集验证,最终Dice系数和HD分别为88.13%、14.17 mm,参数量和 存储空间降低57%。结果表明,本文方法不仅可以分割出没有有效边缘 的前列腺区域提高其分 割精度而且能有效的降低参数量和存储空间,能够应用于模糊边缘的医学图像中。 |
| 英文摘要: |
| After prostate magnetic resonance (MR) image slices,it is found that some images do not have effective edge information,which makes it impossible to clea rly locate the edge position,and thus cannot segment the prostate.At the same time ,the traditional convolutional network requires a large amount of parameters and take s up too much storage space of the model.This paper proposes a method to segment the pro state using U-Net that combines multi-scale dilated separable convolution and channe l attention.First,slice 50three-dimensional (3D) prostate samples and perform contrast enhancement on the sliced images.Subsequently,the processed data is input into the residual U-Ne t,and the multi-scale dilated convolution and channel attention are used as the encoding -decoding unit to extract the feature information.Finally,the Dice coefficient and Hausd orff distance (HD) are used to evaluate the segmentation results.The experiment was verified on the PROMISE12challenge dataset,and the final Dice coefficient and HD were 88.13% and 14.17mm,respectively,and the parameter amount and storage space wer e reduced by 57%.The results show that this method can not only segment the pros tate area without effective edges to improve its segmentation accuracy,but also effe ctively reduce the parameter amount and storage space,and can be applied to medical ima ges with blurred edges. |
| 查看全文 下载PDF阅读器 |
| 关闭 |
|
|
|
|
|