Robust Automatic Pectoral Muscle Segmentation from Mammograms Using Texture Gradient and Euclidean Distance Regression
Autor: | Ashwin Kothari, Avinash G. Keskar, Vibha Bafna Bora |
---|---|
Rok vydání: | 2015 |
Předmět: |
Polynomial
Databases Factual 020205 medical informatics Computer science Breast Neoplasms CAD 02 engineering and technology Article Pattern Recognition Automated Pectoralis Muscles 030218 nuclear medicine & medical imaging Hough transform law.invention 03 medical and health sciences 0302 clinical medicine law 0202 electrical engineering electronic engineering information engineering Humans Radiology Nuclear Medicine and imaging Computer vision Segmentation Computed radiography Radiological and Ultrasound Technology business.industry Reproducibility of Results Computer Science Applications Euclidean distance Computer-aided diagnosis Line (geometry) Radiographic Image Interpretation Computer-Assisted Female Artificial intelligence business Algorithms Mammography |
Zdroj: | Journal of Digital Imaging. 29:115-125 |
ISSN: | 1618-727X 0897-1889 |
Popis: | In computer-aided diagnosis (CAD) of mediolateral oblique (MLO) view of mammogram, the accuracy of tissue segmentation highly depends on the exclusion of pectoral muscle. Robust methods for such exclusions are essential as the normal presence of pectoral muscle can bias the decision of CAD. In this paper, a novel texture gradient-based approach for automatic segmentation of pectoral muscle is proposed. The pectoral edge is initially approximated to a straight line by applying Hough transform on Probable Texture Gradient (PTG) map of the mammogram followed by block averaging with the aid of approximated line. Furthermore, a smooth pectoral muscle curve is achieved with proposed Euclidean Distance Regression (EDR) technique and polynomial modeling. The algorithm is robust to texture and overlapping fibro glandular tissues. The method is validated with 340 MLO views from three databases-including 200 randomly selected scanned film images from miniMIAS, 100 computed radiography images and 40 full-field digital mammogram images. Qualitatively, 96.75 % of the pectoral muscles are segmented with an acceptable pectoral score index. The proposed method not only outperforms state-of-the-art approaches but also accurately quantifies the pectoral edge. Thus, its high accuracy and relatively quick processing time clearly justify its suitability for CAD. |
Databáze: | OpenAIRE |
Externí odkaz: |