Related Experiment Video
Updated: Jan 7, 2026
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
23.0K
Artificial Intelligence-Accelerated vs. Conventional Diffusion-Weighted Imaging for Prostate MRI: Comparing Quality
Vlad Sacalean1, Oliver Gebler1, Wei Liu2
1Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, University of Freiburg, Hugstetterstr. 55, 79106 Freiburg, Germany (V.S., O.G., F.B., J.W., M.F.R., H.E.).
Academic Radiology
|January 1, 2026
Summary
Artificial intelligence-accelerated diffusion-weighted imaging (AI-DWI) significantly reduces prostate MRI scan time. This AI-DWI sequence maintains diagnostic image quality while altering quantitative diffusion metrics.
Area of Science:
- Radiology and Medical Imaging
- Artificial Intelligence in Healthcare
- Prostate Cancer Diagnostics
Background:
- Diffusion-weighted imaging (DWI) is crucial for prostate MRI but increases scan duration.
- Developing faster DWI techniques is essential for improving patient experience and workflow efficiency.
Purpose of the Study:
- To evaluate an artificial intelligence (AI)-accelerated, reduced-field-of-view diffusion sequence (AI-DWI) for prostate MRI.
- To determine if AI-DWI can shorten scan time without compromising perceived image quality.
- To assess the impact of AI-DWI on quantitative diffusion metrics.
Main Methods:
- Prospective diagnostic accuracy study comparing AI-DWI with conventional DWI (c-DWI) in men with elevated PSA.
- Subjective image quality assessed by three radiologists.
- Quantitative analysis included mean apparent diffusion coefficient (ADC) and texture features.
- Statistical analysis using Wilcoxon signed-rank and paired t-tests.
Main Results:
- AI-DWI acquisition time was significantly shorter than c-DWI (3 min 59 s vs. 4 min 21 s).
- No significant differences in subjective image quality (overall quality, lesion conspicuity, artifacts, anatomic differentiability).
- AI-DWI showed significantly lower mean and maximum ADC values compared to c-DWI; other quantitative metrics showed no significant differences.
Conclusions:
- AI-DWI enables reduced acquisition time in prostate MRI while preserving subjective image quality.
- Quantitative analysis reveals lower mean and maximum ADC values with AI-DWI, with no significant changes in other metrics.
- AI-DWI represents a promising advancement for efficient and effective prostate MRI.
