Paper 13412-54
Paper 13412-54
Combining ultrasound radiofrequency data with radiomics for prostate stromal nodule detection
19 February 2025 • 5:30 PM - 7:00 PM PST | Golden State Ballroom
Abstract
This study integrates radiomics with ultrasound (US) radiofrequency (RF) data to enhance stromal nodule detection in ex-vivo prostate specimens with benign prostatic hyperplasia (BPH). By combining RF data and B-mode images, the regions of interest in the prostate were analyzed. Annotated RGB images identified stromal and non-stromal regions, which were correlated with US data. Radiomic features, including first-order energy and GLCM-based metrics, were extracted using PyRadiomics. Machine learning models showed that RF-derived radiomic features significantly improve stromal nodule detection, offering a non-invasive, precise diagnostic approach.The integration of radiomics with RF data offers a non-invasive, precise method for distinguishing between stromal and non-stromal regions of prostate, promising improved patient outcomes and personalized treatment plans.
Presenter
The Univ. of Texas at Dallas (United States), The Univ. of Texas Southwestern Medical Ctr. at Dallas (United States)
Teja Pathour has recently completed his PhD from Bioengineering department at University of Texas at Dallas. His research mainly focuses on applying machine learning techniques for ultrasound imaging. He works with characterizing acoustic responses from novel contrast agents and their behavior under ultrasound using machine learning models. He also works with ex-vivo prostate tissues for segmentation and characterization of different zones and region of interest.