Medical computer-aided detection method based on deep learning.
10.7507/1001-5515.201611064
- Author:
Pan TAO
1
;
Zhongliang FU
2
;
Kai ZHU
3
;
Lili WANG
3
Author Information
1. Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610041, P.R.China;University of Chinese Academy of Sciences, Beijing 100049, P.R.China.284792640@qq.com.
2. Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610041, P.R.China.
3. Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610041, P.R.China;University of Chinese Academy of Sciences, Beijing 100049, P.R.China.
- Publication Type:Journal Article
- Keywords:
computer-aided detection;
echocardiogram;
magnetic resonance image;
object detection;
region convolutional neural network
- From:
Journal of Biomedical Engineering
2018;35(3):368-375
- CountryChina
- Language:Chinese
-
Abstract:
This paper performs a comprehensive study on the computer-aided detection for the medical diagnosis with deep learning. Based on the region convolution neural network and the prior knowledge of target, this algorithm uses the region proposal network, the region of interest pooling strategy, introduces the multi-task loss function: classification loss, bounding box localization loss and object rotation loss, and optimizes it by end-to-end. For medical image it locates the target automatically, and provides the localization result for the next stage task of segmentation. For the detection of left ventricular in echocardiography, proposed additional landmarks such as mitral annulus, endocardial pad and apical position, were used to estimate the left ventricular posture effectively. In order to verify the robustness and effectiveness of the algorithm, the experimental data of ultrasonic and nuclear magnetic resonance images are selected. Experimental results show that the algorithm is fast, accurate and effective.
