Related Experiment Video
Updated: Jul 6, 2026
04:25
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
2.1K
Evaluation of high-resolution pituitary dynamic contrast-enhanced MRI using deep learning-based compressed sensing
Meng Zhang1,2, Chunchao Xia1, Jing Tang1
1Department of Radiology, West China Hospital, Sichuan University, Chengdu, China.
European Radiology
|April 13, 2025
Summary
High-resolution dynamic contrast-enhanced MRI using deep learning reconstruction significantly improves microadenoma detection. This advanced technique enhances diagnostic accuracy for pituitary abnormalities, aiding timely patient management.
Area of Science:
- Radiology and Medical Imaging
- Artificial Intelligence in Medicine
- Endocrinology
Background:
- Pituitary microadenomas are challenging to diagnose due to limitations in conventional MRI resolution.
- Dynamic Contrast-Enhanced (DCE) MRI is crucial for pituitary lesion characterization.
- High false-negative rates in diagnosing microadenomas necessitate improved imaging strategies.
Purpose of the Study:
- To evaluate the diagnostic performance of high-resolution DCE MRI with deep learning-based compressed sensing and super-resolution (DLCS-SR) reconstruction.
- To compare the efficacy of DLCS-SR reconstructed images against conventional DCE MRI sequences for microadenoma identification.
- To assess the potential of DLCS-SR in overcoming resolution limitations of standard DCE MRI.
Main Methods:
- A prospective study involving 126 participants with suspected pituitary microadenomas.
- Acquisition of single-scan DCE MRI data, reconstructed into four image groups: 1.5-mm DLCS-SR, 1.5-mm DLCS, 1.5-mm routine, and 3-mm DLCS-SR.
- Diagnostic criteria established using comprehensive clinical and laboratory data; two readers assessed diagnostic performance using κ statistics, DeLong, and McNemar tests.
Main Results:
- 1.5-mm DLCS-SR images demonstrated superior diagnostic agreement (κ = 0.746-0.848) compared to 1.5-mm DLCS (κ = 0.585-0.687), 1.5-mm routine (κ = 0.449-0.487), and 3-mm DLCS-SR (κ = 0.347-0.369) (p < 0.001).
- The area under the ROC curve for 1.5-mm DLCS-SR images (0.89-0.94) was significantly higher than for 1.5-mm DLCS (0.83-0.87), 1.5-mm routine (0.76-0.78), and 3-mm DLCS-SR (0.72-0.74) images (p < 0.001).
- DLCS-SR reconstruction significantly improved image quality and diagnostic efficacy for microadenoma detection.
Conclusions:
- High-resolution DCE MRI with DLCS-SR reconstruction offers superior diagnostic performance for identifying pituitary abnormalities and microadenomas.
- This advanced reconstruction technique shows significant clinical potential for improving the accuracy of DCE MRI in diagnosing pituitary microadenomas.
- DLCS-SR effectively overcomes resolution limitations, reducing false-negative rates and enhancing patient management.
Related Concept Videos
01:24Magnetic Resonance Imaging
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
01:27Imaging Studies III: Computed Tomography
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...