Random forest learning of ultrasonic statistical physics and object spaces for lesion detection in 2D sonomammography

Debdoot Sheet; Athanasios Karamalis; Silvan Kraft; Peter B. Noël; Tibor Vag; Anup Sadhu; Amin Katouzian; Nassir Navab; Jyotirmoy Chatterjee; Ajoy K. Ray

doi:10.1117/12.2006370

29 March 2013 Random forest learning of ultrasonic statistical physics and object spaces for lesion detection in 2D sonomammography

Debdoot Sheet, Athanasios Karamalis, Silvan Kraft, Peter B. Noël, Tibor Vag, Anup Sadhu, Amin Katouzian, Nassir Navab, Jyotirmoy Chatterjee, Ajoy K. Ray

Author Affiliations +

Proceedings Volume 8675, Medical Imaging 2013: Ultrasonic Imaging, Tomography, and Therapy; 867515 (2013) https://doi.org/10.1117/12.2006370
Event: SPIE Medical Imaging, 2013, Lake Buena Vista (Orlando Area), Florida, United States

Abstract

Breast cancer is the most common form of cancer in women. Early diagnosis can significantly improve lifeexpectancy 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.

Citation Download Citation

Debdoot Sheet, Athanasios Karamalis, Silvan Kraft, Peter B. Noël, Tibor Vag, Anup Sadhu, Amin Katouzian, Nassir Navab, Jyotirmoy Chatterjee, and Ajoy K. Ray "Random forest learning of ultrasonic statistical physics and object spaces for lesion detection in 2D sonomammography", Proc. SPIE 8675, Medical Imaging 2013: Ultrasonic Imaging, Tomography, and Therapy, 867515 (29 March 2013); https://doi.org/10.1117/12.2006370

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available