PROJECT TITLE :

Tumour ROI estimation in ultrasound images via radon barcodes - 2016

ABSTRACT:

Quantitative ultrasound (QUS) methods give a promising framework which will non-invasively and inexpensively be used to predict or assess the tumour response to cancer treatment. The first step in using the QUS methods is to select a locality of interest (ROI) within the tumour in ultrasound pictures. Manual segmentation, but, is very time consuming and tedious. During this paper, a semi-automated approach can be proposed to roughly localize an ROI for a tumour in ultrasound pictures of patients with regionally advanced breast cancer (LABC). Content-based mostly barcodes, a recently introduced binary descriptor based on Radon remodel, were utilized in order to find similar cases and estimate a bounding box surrounding the tumour. Experiments with 33 B-scan pictures resulted in promising results with an accuracy of 81percent.