Abstract #2191

A Combination of Radiomic Features from MRI and Ultrasound Appears to better predict presence of prostate cancer: Validation against whole mount pathology

Mahdi Orooji¹, Mehdi Alilou², Rachel Sparks³, Mirabela Rusu⁴, Nicolas Bloch⁵, Ernest Feleppa⁶, Dean Barratt⁷, Lee Ponsky⁸, and Anant Madabhushi²

¹Biomedical Engineering, CenteCase Western Reserve University, Cleveland, OH, United States, ²Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States, ³Centre for Medical Image Computing, University College of London, London, United Kingdom, ⁴Albany, NY, United States, ⁵Boston Medical Center, Boston, MA, United States, ⁶Lizzi Center for Biomedical Engineering, Riverside Research, New York, NY, United States, ⁷University College London, London, United Kingdom, ⁸University Hospital Case Medical Center, Cleveland, OH, United States

To evaluate whether the combination of computer extracted or radiomic image parameters from two complementary modalities, MRI-TRUS can enable better prediction of presence of prostate cancer compared to either modality individually. We considered 12 slides who underwent MRI, TRUS prior to radical prostatectomy. Deformable co-registration methods were used for spatially aligning the pre-operative in vivo MRI and ultrasound with the ex vivo whole mount radical prostatectomy specimens to establish the ground truth for cancer extent on the imaging. It yielded the best separability between cancer and non-cancer regions with an Area under the operating characteristic curve of 0.88.

This abstract and the presentation materials are available to members only; a login is required.

Join Here