Random forest learning of ultrasonic statistical physics and object spaces for lesion detection in 2D sonomammography
Sheet D, Karamalis A, Kraft S, Noel PB, Vag T, Sadhu A, Katouzian A, Navab N, Chatterjee J, Ray AK (2013)
Publication Type: Conference contribution
Publication year: 2013
Journal
Book Volume: 8675
Conference Proceedings Title: Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Event location: USA
ISBN: 9780819494498
DOI: 10.1117/12.2006370
Abstract
Breast cancer is the most common form of cancer in women. Early diagnosis can significantly improve life-expectancy and allow different treatment options. Clinicians favor 2D ultrasonography for breast tissue abnormality screening due to high sensitivity and specificity compared to competing technologies. However, inter- and intra-observer variability in visual assessment and reporting of lesions often handicaps its performance. Existing Computer Assisted Diagnosis (CAD) systems though being able to detect solid lesions are often restricted in performance. These restrictions are inability to (1) detect lesion of multiple sizes and shapes, and (2) differentiate between hypo-echoic lesions from their posterior acoustic shadowing. In this work we present a completely automatic system for detection and segmentation of breast lesions in 2D ultrasound images. We employ random forests for learning of tissue specific primal to discriminate breast lesions from surrounding normal tissues. This enables it to detect lesions of multiple shapes and sizes, as well as discriminate between hypo-echoic lesion from associated posterior acoustic shadowing. The primal comprises of (i) multiscale estimated ultrasonic statistical physics and (ii) scale-space characteristics. The random forest learns lesion vs. background primal from a database of 2D ultrasound images with labeled lesions. For segmentation, the posterior probabilities of lesion pixels estimated by the learnt random forest are hard thresholded to provide a random walks segmentation stage with starting seeds. Our method achieves detection with 99.19% accuracy and segmentation with mean contour-to-contour error > 3 pixels on a set of 40 images with 49 lesions. © 2013 SPIE.
Involved external institutions
Germany (DE)How to cite
APA:
Sheet, D., Karamalis, A., Kraft, S., Noel, P.B., Vag, T., Sadhu, A.,... Ray, A.K. (2013). Random forest learning of ultrasonic statistical physics and object spaces for lesion detection in 2D sonomammography. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. USA.
MLA:
Sheet, Debdoot, et al. "Random forest learning of ultrasonic statistical physics and object spaces for lesion detection in 2D sonomammography." Proceedings of the Medical Imaging 2013: Ultrasonic Imaging, Tomography, and Therapy, USA 2013.
BibTeX: Download