An Improved Neural Network Method for Forearm Bone Imaging Segmentation  

作　　者：Songzheng Huang Jianfeng Chen Songzheng Huang;Jianfeng Chen(Zhejiang Kangyuan Medical Devices Incorporation, Hangzhou, China;Department of Radiology and Medical Imaging, Stritch School of Medicine, Loyola University Medical Center, Chicago, USA)

机构地区：[1]Zhejiang Kangyuan Medical Devices Incorporation, Hangzhou, China [2]Department of Radiology and Medical Imaging, Stritch School of Medicine, Loyola University Medical Center, Chicago, USA

出　　处：《Open Journal of Radiology》2022年第4期176-188,共13页放射学期刊（英文）

摘　　要：In this paper, we propose several improved neural networks and training strategy using data augmentation to segment human radius accurately and efficiently. This method can provide pixel-level segmentation accuracy through the low-level features of the neural network, and automatically distinguish the classification of radius. The versatility and applicability can be effectively improved by learning and training digital X-ray images obtained from digital X-ray imaging systems of different manufacturers.In this paper, we propose several improved neural networks and training strategy using data augmentation to segment human radius accurately and efficiently. This method can provide pixel-level segmentation accuracy through the low-level features of the neural network, and automatically distinguish the classification of radius. The versatility and applicability can be effectively improved by learning and training digital X-ray images obtained from digital X-ray imaging systems of different manufacturers.

关 键 词：Human Radius Digital X-Ray Image U-shaped Unet Neural Network SEGMENTATION 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]