Literature DB >> 33831723

Detecting cerebral microbleeds via deep learning with features enhancement by reusing ground truth.

Tianfu Li1, Yan Zou2, Pengfei Bai3, Shixiao Li1, Huawei Wang1, Xingliang Chen1, Zhanao Meng2, Zhuang Kang2, Guofu Zhou4.   

Abstract

BACKGROUND AND OBJECTIVES: Cerebral microbleeds (CMBs) are cerebral small vascular diseases and are often used to diagnose symptoms such as stroke and dementia. Manual detection of cerebral microbleeds is a time-consuming and error-prone task, so the application of microbleed detection algorithms based on deep learning is of great significance. This study presents the feature enhancement technology applying to improve the performances of detecting CMBs. The primary purpose of the feature enhancement is emphasizing the meaningful features, leading deep learning network easier and correctly to optimize.
METHOD: In this study, we applied feature enhancement in detecting CMBs from brain MRI images. Feature enhancement enhanced specific intervals and suppressed the useless intervals of the feature map. This method was applied in SSD-512 and SSD-300 algorithm, using VGG architecture pre-trained in the ImageNet dataset.
RESULTS: The proposed method was applied in SSD-512. Moreover, the model was trained and tested on the sequence of SWAN images of brain MRI images. The results of the experiment demonstrate that our method effectively improves the detection performance of the SSD network in detecting CMBs. We train SSD-512 120000 iterations and test results on the test datasets, by applying the feature enhancement layer, improving the precision with 3.3% and the mAP of 2.3%. In the same way, we trained SSD-300, improving the mAP of 2.0%. 2.8% and 7.4% precision are improved by applying feature enhancement layer In ResNet-34 and MobileNet.
CONCLUSIONS: The proposed method achieved more effective performance, demonstrated that feature enhancement can be a helpful algorithm to enhance the deep learning model.
Copyright © 2021. Published by Elsevier B.V.

Entities:  

Keywords:  Cerebral microbleeds; Convolutional neural network; Deep learning; Feature enhancement; SSD

Year:  2021        PMID: 33831723     DOI: 10.1016/j.cmpb.2021.106051

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  1 in total

1.  Construction of a Medical Micro-Object Cascade Network for Automated Segmentation of Cerebral Microbleeds in Susceptibility Weighted Imaging.

Authors:  Zeliang Wei; Xicheng Chen; Jialu Huang; Zhenyan Wang; Tianhua Yao; Chengcheng Gao; Haojia Wang; Pengpeng Li; Wei Ye; Yang Li; Ning Yao; Rui Zhang; Ning Tang; Fei Wang; Jun Hu; Dong Yi; Yazhou Wu
Journal:  Front Bioeng Biotechnol       Date:  2022-07-20
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.