Automatic Pediatric Liver Stiffness Prediction using Deep Learning on Ultrasound Images

Abstract:

Liver stiffness, a biomarker for chronic hepatic disorders, is measured using a popular non-invasive ultrasound (US) shear-wave elastography (SWE) technique, for the pediatric population. Every elastography bears additional financial and resource burden on the patient and the healthcare system. In this work, we benchmark and test different deep learning (DL) models for liver stiffness prediction from grayscale ultrasound images.

Example US Images + DL Models Predictions

TBA

References:

S. Deoghare et al., Automatic pediatric liver stiffness prediction using deep learning on ultrasound images. In preparation, 2024.

S. Deoghare, P. N. T. Nguyen, A. T. Trout, J. R. Dillman, V. B. S. Prasath. Fake it till you make it: Generative AI models for creating realistic artificial pediatric liver ultrasound images. Ultracon, Orlando, FL, USA, March 2023.

S. Deoghare, R. Yadav, L. A. Gillligan, V. B. S. Prasath, A. Trout, J. Dillman. Deep learning predicts ultrasound SWE liver stiffness in children. 106th RSNA Annual Meeting, 29 November - 5 December 2020.

Posters:

P. N. T. Ngyuen, S. Deoghare, A. T. Trout, J. R. Dillman, V. Acharya, V. B. S. Prasath. Fake it till you make it: Synthetic generation of pediatric liver ultrasound images using generative AI models. Undergraduate Research Showcase, University of Cincinnati, April 2022. Poster presentation. Vol. 4 No. 1 (2022): 2022: Undergraduate Scholarly Showcase Proceedings.

Back to Ultrasound Projects Main Page. Back to Research Page.