摘要
目的乳腺癌是常见的高发病率肿瘤疾病,早期确诊是预防乳腺癌的关键。为获得肿瘤准确的边缘和形状信息,提高乳腺肿瘤诊断的准确性,本文提出了一种结合残差路径及密集连接的乳腺超声肿瘤分割方法。方法基于经典的深度学习分割模型U-Net,添加残差路径,减少编码器和解码器特征映射之间的差异。在此基础上,在特征输入层到解码器最后一步之间引入密集块,通过密集块组成从输入特征映射到解码最后一层的新连接,减少输入特征图与解码特征图之间的差距,减少特征损失并保存更有效信息。结果将本文模型与经典的U-Net模型、引入残差路径的U-Net(U-Net with Res paths)模型在上海新华医院崇明分院乳腺肿瘤超声数据集上进行10-fold交叉验证实验。本文模型的真阳率(true positive,TP)、杰卡德相似系数(Jaccard similarity,JS)和骰子系数(Dice coefficients,DC)分别为0.8707、0.8037和0.8824,相比U-Net模型分别提高了1.08%、2.14%和2.01%;假阳率(false positive,FP)和豪斯多夫距离(Hausdorff distance,HD)分别为0.1040和22.3114,相比U-Net模型分别下降了1.68%和1.4102。在54幅图像的测试集中,评价指标JS>0.75的肿瘤图像数量的总平均数为42.1,最大值为46。对比实验结果表明,提出的算法有效改善了分割结果,提高了分割的准确性。结论本文提出的基于U-Net结构并结合残差路径与新的连接的分割模型,改善了乳腺超声肿瘤图像分割的精确度。
Objective Precise segmentation of breast cancer tumors is of great concern.For women,breast cancer is a common tumor disease with a high incidence,and obtaining accurate diagnosis in the early stage of breast cancer has always been the key to preventing breast cancer.Doctors can improve the accuracy of the diagnosis of breast tumors by obtaining accurate information on the edge and shape of the tumor.Common breast imaging techniques include ultrasound imaging,magnetic resonance imaging(MRI),and X-ray imaging.However,X-ray imaging often causes radiation damage to breast tissue in women,whereas MRI imaging is not only expensive but also needs a longer scanning time.Compared with the two methods above,the ultrasound imaging detection method has the advantages of no radiation damage to tissue,ease of use,imaging the front of any breast,fast imaging speed,and cheap price.However,ultrasound images rely more on professional ultrasound doctors because of problems such as speckle noise and low resolution than other commonly used techniques.Thus,experienced,well-trained doctors are needed in the diagnostic process.In recent years,improving the accuracy of diagnosis by combining medical imaging technology with computer science and technology to segment tumors accurately and help related medical personnel in diagnosis and identification has become a trend.In the past 10 years,various methods,such as thresholding method,clustering-based algorithm,graph-based algorithm,and active contour algorithm,have been used to segment breast tumors on ultrasound images.However,these methods have limited ability to represent features.In the past few years,deep convolutional neural networks have become more widely used in visual recognition tasks.They can automatically find suitable features for target data and tasks.The convolutional network has existed for a long time.However,the hardware environment at that time limited its development because the size of the training set and the size of the network structure parameters require a large a
作者
陈杨怀
陈胜
姚莉萍
Chen Yanghuai;Chen Sheng;Yao Liping(School of Optical Electrial and Computer Engineeing University of Shanghai for Science and Technology,Shanghai 200930,China;Chongming Branch,Xinhua Hospital,School of Medicine,Shanghai Jiao Tong University,Shanghai 202150,China)
出处
《中国图象图形学报》
CSCD
北大核心
2021年第3期633-643,共11页
Journal of Image and Graphics
基金
国家自然科学基金项目(81101116)。
关键词
肿瘤分割
乳腺超声
卷积网络
残差路径
密集块
tumor segmentation
breast ultrasound
convolutional network
residual paths(Res paths)
dense block
