摘要
超声影像分割既是医学影像图像处理的重要环节,也是临床诊断的常用技术手段。文中提出将SegFormer网络模型用于实现医学超声影像图像的精准分割。一方面,将超声标签图转化为单通道形式,并对其进行二值化处理,以完成对数据集图像的预处理;另一方面,采用迁移学习的方式载入预训练模型,用于微调已经训练好的模型参数,并选用带有动量的随机梯度下降优化器来加速收敛速度及减小震荡。与FCN,UNet和DeepLabV3的对比实验结果表明,该模型在乳腺结节超声影像数据集上的各项评估指标均为最优,mIoU,Acc,DSC和Kappa分别为81.32%,96.22%,88.91%和77.85%。实验结果还表明,该模型在不同超声影像数据集中表现出了良好的鲁棒性。
Ultrasonic image segmentation is not only an important part of medical image processing,but also a common technical means of clinical diagnosis.In this paper,the SegFormer network model is proposed to realize the accurate segmentation of medical ultrasound images.On the one hand,the ultrasonic label image is transformed into a single channel and processed by binarization to complete the preprocessing of the data set image;on the other hand,the pre-training model is loaded into the pre-training model to fine-tune the trained model parameters,and a random gradient descent optimizer with momentum is selected to accelerate the convergence speed and reduce the oscillation.Experimental results show that,compared with FCN,UNet and DeepLabV3,all the evaluation indexes of the proposed model are the best in the breast nodule ultrasound image data set,and the evaluation indexes of mIoU,Acc,DSC and Kappa is 81.32%,96.22%,88.91%and 77.85%respectively.The experimental results also show that the model is robust in different ultrasonic image data sets.
作者
杨靖怡
李芳
康晓东
王笑天
刘汉卿
韩俊玲
YANG Jingyi;LI Fang;KANG Xiaodong;WANG Xiaotian;LIU Hanqing;HAN Junling(School of Medical Image,Tianjin Medical University,Tianjin 300202,China;Beijing Chemical Occupational Disease Control Hospital,Beijing 100093,China)
出处
《计算机科学》
CSCD
北大核心
2023年第S01期404-409,共6页
Computer Science
基金
京津冀协同创新项目(17YEXTZC00020)。
