Automatic Mass Detection in Ultrasound Breast ImagesUsing Computer Assisted Detection
Farzan Khatib · Medical Informatics · 2012
This work is concentrated on extraction of mass in Ultrasound breast images in to help doctors interpreting such images efficiently using Computer-Aided Detection. A set of six popular ultrasound machines were selected and images were acquired sweeping: modes of operation, transducer, frequency and contrast. To make a complete set of ultrasound images in B-Mode a multi purpose multi tissue Ultrasound Phantom was used. Gamma corrections, contrast stretching and filtering accompanied by morphological Image Processing were among the steps that were applied to find the final image. Two experienced radiologists were marked output. Statistical analysis showed a sensitivity of 100% and accuracy of 99% for solid mass and 99% and 98% for cystic mass respectively. It also showed that the same procedure can be use for cystic and solid breast masses with small change.