CMB-net: a deep convolutional neural network for diagnosis of cerebral microbleeds

Zhihai Lu, Yan Yan, Shui Hua Wang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Cerebral microbleed (CMB) is related to cerebral vascular diseases. In this paper, we propose the use of deep convolutional neural network to implement CMB automatic diagnosis based on brain susceptibility-weighted images (SWIs). First of all, a sliding neighborhood method was employed to get 13,031 samples for training and testing. Then, an 18-layer CMB-Net was designed to classify the samples as CMB or non-CMB. The CMB-Net was trained by RMSprop based on the five-fold cross- validation. The total running time of the five-fold cross-validation was merely 184.79 s, and the average testing accuracy reached 98.39%, which was better than several recently published methods. The results suggested that our CMB-Net was accurate in detecting CMB.

Original languageEnglish
Pages (from-to)19195-19214
Number of pages20
JournalMultimedia Tools and Applications
Volume81
Issue number14
DOIs
Publication statusPublished - Jun 2022
Externally publishedYes

Keywords

  • Cerebral microbleed
  • Computer aided diagnosis
  • Convolutional neural network
  • Susceptibility-weighted image

Fingerprint

Dive into the research topics of 'CMB-net: a deep convolutional neural network for diagnosis of cerebral microbleeds'. Together they form a unique fingerprint.

Cite this