基于多示例学习的颈椎健康评分方法

Translated title of the contribution: Cervical Vertebrae Health Score Method Based on Multiple Instance Learning

Jiachen Li, Songhua Xu, Xueying Qin

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

This paper introduces an online scoring method for cervical vertebrae health based on multiple instance learning (MIL) of multiple-valued input, in order to assess cervical vertebrae health score and solve the data labeling difficulty. It is only necessary to simply label the long-term sequence of cervical vertebrae motion data during the training phase to estimate the health score of the cervical short-term state. Firstly, the multiple-valued input is divided into sub-classifiers of multiple binary inputs and trained separately. Then use the Gaussian model to fuse the instance scores trained by each sub-classifier. Finally, the bag score is calculated with a new scoring mechanism and the cervical vertebrae health can be assessed in real-time. Qualitative and quantitative experiments include the bag score prediction accuracy, instance visualization analysis, bag score curve analysis and real-time scoring analysis, which illustrate the effectiveness of the algorithm in assessing the health of the cervical vertebrae.

Translated title of the contributionCervical Vertebrae Health Score Method Based on Multiple Instance Learning
Original languageChinese (Traditional)
Pages (from-to)94-103
Number of pages10
JournalJisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics
Volume31
Issue number1
DOIs
StatePublished - Jan 1 2019

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Keywords

  • Bag scoring mechanism
  • Cervical vertebrae health impact score assessment
  • Multiple instance learning
  • Multiple-valued input labels

Fingerprint

Dive into the research topics of 'Cervical Vertebrae Health Score Method Based on Multiple Instance Learning'. Together they form a unique fingerprint.

Cite this