Imaging Research Physical science
Imaging Research Physical science
Gangeh M.J.,University of Toronto |
Gangeh M.J.,Imaging Research Physical science |
Tizhoosh H.R.,University of Waterloo |
Wu K.,University of Waterloo |
And 5 more authors.
2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017 | Year: 2017
Recent advances in using quantitative ultrasound (QUS) methods have provided a promising framework to non-invasively and inexpensively monitor or predict the effectiveness of therapeutic cancer responses. One of the earliest steps in using QUS methods is contouring a region of interest (ROI) inside the tumour in ultrasound B-mode images. While manual segmentation is a very time-consuming and tedious task for human experts, auto-contouring is also an extremely difficult task for computers due to the poor quality of ultrasound B-mode images. However, for the purpose of cancer response prediction, a rough boundary of the tumour as an ROI is only needed. In this research, a semi-automated tumour localization approach is proposed for ROI estimation in ultrasound B-mode images acquired from patients with locally advanced breast cancer (LABC). The proposed approach comprised several modules, including 1) feature extraction using keypoint descriptors, 2) augmenting the feature descriptors with the distance of the keypoints to the user-input pixel as the centre of the tumour, 3) supervised learning using a support vector machine (SVM) to classify keypoints as 'tumour' or 'non-tumour', and 4) computation of an ellipse as an outline of the ROI representing the tumour. Experiments with 33 B-mode images from 10 LABC patients yielded promising results with an accuracy of 76.7% based on the Dice coefficient performance measure. The results demonstrated that the proposed method can potentially be used as the first stage in a computerassisted cancer response prediction system for semi-automated contouring of breast tumours. © 2017 IEEE.
Falou O.,Sunnybrook Health science Center |
Falou O.,Imaging Research Physical science |
Falou O.,University of Toronto |
Sadeghi-Naini A.,Sunnybrook Health science Center |
And 30 more authors.
Translational Oncology | Year: 2013
Purpose: Ultrasound elastography is a new imaging technique that can be used to assess tissue stiffness. The aim of this study was to investigate the potential of ultrasound elastography for monitoring treatment response of locally advanced breast cancer patients undergoing neoadjuvant therapy. Methods: Fifteen women receiving neoadjuvant chemotherapy had the affected breast scanned before, 1, 4, and 8 weeks following therapy initiation, and then before surgery. Changes in elastographic parameters related to tissue biomechanical properties were then determined and compared to clinical and pathologic tumor response after mastectomy. Results: Patients who responded to therapy demonstrated a significant decrease (P <.05) in strain ratios and strain differences 4 weeks after treatment initiation compared to non-responding patients. Mean strain ratio and mean strain difference for responders was 81 ± 3% and 1 ± 17% for static regions of interest (ROIs) and 81 ± 3% and 6 ± 18% for dynamic ROIs, respectively. In contrast, these parameters were 102±2%, 110±17%, 101±4%, and 109±30% for non-responding patients, respectively. Strain ratio using static ROIs was found to be the best predictor of treatment response, with 100% sensitivity and 100% specificity obtained 4 weeks after starting treatment. Conclusions: These results suggest that ultrasound elastography can be potentially used as an early predictor of tumor therapy response in breast cancer patients. Copyright © 2013 Neoplasia Press, Inc. All rights reserved.