Salehi Publishes Paper Based on NIH-Funded Research Project in "Journal of Biomedical Optics"
Dr. Hassan S. Salehi, visiting assistant professor of electrical and computer engineering in the College of Engineering, Technology, and Architecture, published an article based on the NIH-funded research in the SPIE Journal of Biomedical Optics, Volume 21, Issue 4, 046006, 2016. The paper, “Coregistered photoacoustic and ultrasound imaging and classification of ovarian cancer: ex vivo and in vivo studies,” was written by lead author Dr. Salehi along with his collaborators at the University of Connecticut, Department of Electrical and Computer Engineering, Department of Biomedical Engineering, and the University of Connecticut Health Center (UConn Health).
The paper reports on a study testing capabilities of a novel co-registered photoacoustic and ultrasound imaging system and classification algorithms using machine learning techniques for ovarian cancer diagnosis. Most ovarian cancers are diagnosed at advanced stages due to the lack of efficacious screening techniques. As a result, there is an urgent need to improve the current clinical practice by advancing the conventional imaging systems and detecting early malignancies in the ovary. Photoacoustic tomography (PAT) is an emerging imaging modality with great potential to assist transvaginal ultrasound for ovarian cancer screening. Therefore, the authors have developed their co-registered photoacoustic tomography (PAT) and ultrasound (US) prototype system for real-time assessment of ovarian masses. Features extracted from PAT and US angular beams, envelopes, and images were input to a logistic classifier and a support vector machine (SVM) classifier to diagnose ovaries as benign or malignant. A total of 25 excised ovaries of 15 patients were studied and the logistic and SVM classifiers achieved sensitivities of 70.4 and 87.7%, and specificities of 95.6 and 97.9%, respectively. Furthermore, the ovaries of two patients were non-invasively imaged using the PAT/US system before surgical excision. By using five significant features and the logistic classifier, 12 out of 14 images (86% sensitivity) from a malignant ovarian mass and all 17 images (100% specificity) from a benign mass were accurately classified; the SVM correctly classified 10 out of 14 malignant images (71% sensitivity) and all 17 benign images (100% specificity). These initial results demonstrate the clinical potential of the PAT/US technique for ovarian cancer diagnosis.
This research was supported by the National Institutes of Health (NIH grant number: R01CA151570).