Using deep learning to assess liver diseases with ultrasound data
Acquisition and Frequency Spectroscopic Evaluation of Broadband Clinical Ultrasound Raw Data for Liver Cirrhosis and Focal Pathologies Using Neural Networks for Tissue and Pathology Differentiation
This study is testing if a new deep learning method using ultrasound data can better identify liver diseases in patients compared to traditional methods.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 200 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Technische Universität Dresden Academic / other |
| Locations | 4 sites (Dresden and 3 other locations) |
| Trial ID | NCT06317181 on ClinicalTrials.gov |
What this trial studies
This clinical trial aims to evaluate the effectiveness of neural networks trained on raw ultrasound radiofrequency data for assessing liver diseases in patients undergoing ultrasound examinations. The study will compare the performance of these neural networks against traditional elastography methods and other neural networks trained on standard b-mode images. Participants will undergo clinical elastography and additional ultrasound assessments to establish a reliable ground truth for the evaluation. The goal is to determine if the deep learning approach can accurately identify diffuse liver diseases and distinguish focal liver pathologies from healthy tissue.
Who should consider this trial
Good fit: Ideal candidates are patients scheduled for an ultrasound investigation due to suspected liver disease.
Not a fit: Patients who have undergone recent liver interventions or contrast-enhanced ultrasounds may not benefit from this study.
Why it matters
Potential benefit: If successful, this approach could lead to more accurate and efficient assessments of liver diseases, improving patient outcomes.
How similar studies have performed: While the use of deep learning in medical imaging is gaining traction, this specific application of neural networks on ultrasound radiofrequency data is relatively novel and has not been extensively tested in prior studies.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * scheduled for an ultrasound investigation by an independent physician * signed declaration of consent Exclusion Criteria: * smaller interventions in the same liver during the last 2 Week (for example liver biopsy) * contrast enhanced ultrasound less than a day ago * major intervention at the liver (for example partial resection)
Where this trial is running
Dresden and 3 other locations
- University Hospital — Dresden, Germany (Recruiting)
- Diakonissen Hospital Dresden — Dresden, Germany (Recruiting)
- University Hospital Halle (Saale) — Halle, Germany (Recruiting)
- University Hospital Leipzig — Leipzig, Germany (Recruiting)
Study contacts
- Principal investigator: Moritz Herzog, MD — University Hospital Dresden
- Study coordinator: Moritz Herzog, MD
- Email: moritz.herzog@ukdd.de
- Phone: 0049 351 458 11501
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.