Title | ||
---|---|---|
Multi-dimensional proprio-proximus machine learning for assessment of myocardial infarction. |
Abstract | ||
---|---|---|
•In this work, we use a plurality of sifted clinical indices/features for comprehensive analysis of cardiac segments in the left ventricle (LV). The performance of the analysis is improved by incorporating information from neighbouring segments, thus taking into account the effect of regional influence.•Validation of our proposed approach was performed in a clinical study involving 30 patients with a first-time myocardium infarction (“heart attack”) and 9 age- and sex-matched volunteers. By comparing classification results to identify Infarcted from Non-infarcted cardiac segments, we observed that using multiple sifted clinical features can better differentiate these two groups. Moreover, by incorporating neighbouring information, we significantly improve the classification performance.•Based on this study, a set of basis clinical features were identified for building a viable classification model. The machine learning approach presented in our work proves to be promising and can potentially assist clinicians to perform fast and quantitative diagnosis of Infarcted regions in the LV. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.compmedimag.2018.09.007 | Computerized Medical Imaging and Graphics |
Keywords | Field | DocType |
Feature selection,Pattern classification,Cardiac diagnosis,Myocardial infarction,Left ventricle | Myocardial infarction,Computer vision,Multi dimensional,Feature selection,Infarction,Artificial intelligence,Cardiac magnetic resonance imaging,Medicine,Machine learning | Journal |
Volume | ISSN | Citations |
70 | 0895-6111 | 1 |
PageRank | References | Authors |
0.35 | 11 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Feng Yang | 1 | 26 | 15.37 |
Xulei Yang | 2 | 130 | 17.07 |
Soo Kng Teo | 3 | 14 | 6.97 |
Gary Lee | 4 | 1 | 0.35 |
Liang Zhong | 5 | 4 | 4.21 |
Ru-San Tan | 6 | 239 | 22.37 |
Y. Su | 7 | 20 | 10.55 |