基于HA-UNet++的甲状腺结节超声图像分割方法  

Ultrasonic Image Segmentation of Thyroid Nodules Based on HA-UNet++

作　　者：朱永田 田飞[1] 董宝良[1] ZHU Yongtian;TIAN Fei;DONG Baoliang(Department 4 of System,North China Institute of Computing Technology,Beijing 100083,China)

机构地区：[1]华北计算技术研究所系统四部,北京100083

出　　处：《计算机与现代化》2025年第3期93-98,105,共7页Computer and Modernization

摘　　要：甲状腺疾病是成年人群中最常诊断出的结节性病变之一,发病率呈现逐年升高的趋势。随着人工智能技术的发展,使用计算机视觉技术对甲状腺超声图像进行自动化的诊断,可以显著提高诊断的准确性和效率。但是大多数基于深度学习的图像分割方法,受限于感受野的大小,对于图像的重要特征不能及时地进行关注及有效提取,导致分割的准确性不高。为了解决以上问题,本文采用一种新的深度学习网络模型HA-UNet++,对甲状腺结节超声图像进行分割。HA-UNet++在编码路径每个阶段中,会改良backbone网络结构,同时在网络中具有3层卷积的卷积块中加入混合膨胀卷积,并在每个卷积块后加入注意力机制,使其能够迅速地预测增强后的甲状腺结节数据集,并在此基础上对甲状腺结节进行标记分割。Thyroid disease is one of the most frequently diagnosed nodular lesions in adult population,and it’s incidence is in⁃creasing year by year.With the development of artificial intelligence technology,the automatic diagnosis of thyroid ultrasound im⁃ages using computer vision technology can significantly improve the accuracy and efficiency of diagnosis.However,most image segmentation methods based on deep learning,limited by the size of receptive field,cannot focus on the important features of the image in time and extract them effectively,resulting in low segmentation accuracy.In order to solve the above problems,a new deep learning network model HA-UNet++(Hybrid Dilated Convolution-Attention-UNet++)is adopted in this paper to segment ultrasonic images of thyroid nodules.HA-UNet++improves backbone network structure at each stage of encoding path.At the same time,hybrid dilated convolution is added to the convolution blocks with three layers of convolution in the network,and at⁃tention mechanism is added to each convolution block,so that it can quickly predict the enhanced thyroid nodule data set.On this basis,thyroid nodules are labeled and segmented.

关 键 词：图像分割 甲状腺结节 混合膨胀卷积 注意力机制 U-Net++ 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]