Lumbar Ultrasound Image Feature Extraction and Classification with Support Vector Machine

• Published in: Ultrasound in medicine & biology Vol. 41; no. 10; pp. 2677 - 2689
• Main Authors: Yu, Shuang, Tan, Kok Kiong, Sng, Ban Leong, Li, Shengjin, Sia, Alex Tiong Heng
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01.10.2015
• Subjects: Algorithms; Anesthesia, Epidural - methods; Epidural anesthesia; Feature extraction; Feature selection; Female; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Lumbar Vertebrae - diagnostic imaging; Machine learning; Medical image processing; Pattern Recognition, Automated - methods; Pregnancy; Punctures; Radiology; Reproducibility of Results; Sensitivity and Specificity; Support Vector Machine; Ultrasonography, Interventional - methods; Video processing; Medical image processing; Feature selection; Video processing; Machine learning; Feature extraction; Support vector machine; Epidural anesthesia
• ISSN: 0301-5629; 1879-291X
• DOI: 10.1016/j.ultrasmedbio.2015.05.015

Needle entry site localization remains a challenge for procedures that involve lumbar puncture, for example, epidural anesthesia. To solve the problem, we have developed an image classification algorithm that can automatically identify the bone/interspinous region for ultrasound images obtained from lumbar spine of pregnant patients in the transverse plane. The proposed algorithm consists of feature extraction, feature selection and machine learning procedures. A set of features, including matching values, positions and the appearance of black pixels within pre-defined windows along the midline, were extracted from the ultrasound images using template matching and midline detection methods. A support vector machine was then used to classify the bone images and interspinous images. The support vector machine model was trained with 1,040 images from 26 pregnant subjects and tested on 800 images from a separate set of 20 pregnant patients. A success rate of 95.0% on training set and 93.2% on test set was achieved with the proposed method. The trained support vector machine model was further tested on 46 off-line collected videos, and successfully identified the proper needle insertion site (interspinous region) in 45 of the cases. Therefore, the proposed method is able to process the ultrasound images of lumbar spine in an automatic manner, so as to facilitate the anesthetists' work of identifying the needle entry site.