Automatic detection of tuberculosis related abnormalities in Chest X-ray images using hierarchical feature extraction scheme
作者：
Highlights：
• Developed a hierarchical method to mimic radiologist’s interpretation procedure.
• Proposed seventeen geometrical shape features to encode thoracic abnormalities.
• Combined shape features with texture features for improved abnormality detection.
• Disease detection performance improved significantly using combined feature set.
• The statistical evaluation proved the significance of the obtained results.
摘要
•Developed a hierarchical method to mimic radiologist’s interpretation procedure.•Proposed seventeen geometrical shape features to encode thoracic abnormalities.•Combined shape features with texture features for improved abnormality detection.•Disease detection performance improved significantly using combined feature set.•The statistical evaluation proved the significance of the obtained results.
论文关键词：Tuberculosis,Pneumonia,X-ray images,Lung segmentation,Respiratory illness,Hierarchical classification
论文评审过程：Received 27 December 2019, Revised 2 May 2020, Accepted 2 May 2020, Available online 11 May 2020, Version of Record 21 May 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113514
