The quality of magnetic resonance images may influence the diagnosis and subsequent treatment. Therefore, in this paper, a novel no-reference (NR) magnetic resonance image quality assessment (MRIQA) method is proposed. In the approach, deep convolutional neural network architectures are fused and jointly trained to better capture the characteristics of MR images. Then, to improve the quality prediction performance, the support vector machine regression (SVR) technique is employed on the features generated by fused networks. In the paper, several promising network architectures are introduced, investigated, and experimentally compared with state-of-the-art NR-IQA methods on two representative MRIQA benchmark datasets. One of the datasets is introduced in this work. As the experimental validation reveals, the proposed fusion of networks outperforms related approaches in terms of correlation with subjective opinions of a large number of experienced radiologists.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7913522 | PMC |
| http://dx.doi.org/10.3390/s21041043 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Conventional MRI-Based Structural Disconnection and Morphometric Similarity Networks and Their Clinical Correlates in Multiple Sclerosis.
Neurology
February 2025
Department of Advanced Biomedical Sciences, University "Federico II," Naples, Italy.
Background And Objectives: Although multiple sclerosis (MS) can be conceptualized as a network disorder, brain network analyses typically require advanced MRI sequences not commonly acquired in clinical practice. Using conventional MRI, we assessed cross-sectional and longitudinal structural disconnection and morphometric similarity networks in people with MS (pwMS), along with their relationship with clinical disability.
Methods: In this longitudinal monocentric study, 3T structural MRI of pwMS and healthy controls (HC) was retrospectively analyzed.
Gadopiclenol Enables Reduced Gadolinium Dose While Maintaining Quality of Pulmonary Arterial Enhancement for Pulmonary MRA: An Opportunity for Improved Safety and Sustainability.
Invest Radiol
January 2025
From the Departments of Radiology (J.F.H., S.Y.C., J.-P.G., J.S., P.N., S.B.R., T.M.G.), Biomedical Engineering (S.B.R., T.M.G.), Medical Physics (S.Y.C., S.B.R., T.M.G.), Medicine (S.B.R.), and Emergency Medicine (S.B.R.), University of Wisconsin-Madison, WI; and Department of Diagnostic and Interventional Radiology (J.F.H., J.-P.G.), University Hospital Würzburg, Würzburg, Germany.
Rationale And Objectives: Pulmonary magnetic resonance angiography (MRA) is an imaging method with proven utility for the exclusion of pulmonary embolism and avoids the need for ionizing radiation and iodinated contrast agents. High-relaxivity gadolinium-based contrast agents (GBCAs), such as gadopiclenol, can be used to reduce the required gadolinium dose for pulmonary MRA. The aim of this study was to compare the contrast enhancement performance of gadopiclenol with an established gadobenate dimeglumine-enhanced pulmonary MRA protocol.
View Article and Find Full Text PDFAtomic locations and adsorbate interactions of Al single and pair sites in H-ZSM-5 zeolite.
Science
January 2025
Wolfson Catalysis Centre, Department of Chemistry, University of Oxford, Oxford, UK.
The distribution of substitutional aluminum (Al) atoms in zeolites affects molecular adsorbate geometry, catalytic activity, and shape and size selectivity. Accurately determining Al positions has been challenging. We used synchrotron resonant soft x-ray diffraction (RSXRD) at multiple energies near the Al K-edge combined with molecular adsorption techniques to precisely locate "single Al" and "Al pairs" in a commercial H-ZSM-5 zeolite.
View Article and Find Full Text PDF18F-DCFPyL PET/MRI Radiomics for Intraprostatic Prostate Cancer Detection and Metastases Prediction Using Whole-Gland Segmentation.
Br J Radiol
January 2025
Joint Department of Medical Imaging, University Medical Imaging Toronto (UMIT), University Health Network, Mount Sinai Hospital & Women's College Hospital; University of Toronto, Toronto, ON, Canada.
Objectives: To evaluate 18F-DCFPyL-PET/MRI whole-gland-derived radiomics for detecting clinically significant (cs) prostate cancer (PCa) and predicting metastasis.
Methods: Therapy-naïve PCa patients who underwent 18F-DCFPyL PET/MRI were included. Whole-prostate-segmentation was performed.
Imaging Findings, Complications, and Mimics after Common and Advanced Dental Procedures.
Radiographics
February 2025
From the Department of Radiology, Nihon University School of Dentistry at Matsudo, 2-870-1 Sakaecho-Nishi, Matsudo, Chiba 271-8587, Japan (K.I., K.O., T.K.); Department of Diagnostic Radiology, National Cancer Center Hospital East, Chiba, Japan (H.K.); Department of Radiology, VA Boston Health Care System, Boston, Mass (V.C.A.A.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (O.S.).
Various new dental treatment methods have been introduced in dental clinics, and many new materials have been used in recent years for dental treatments. Dentistry is divided into several specialties, each offering unique treatments, such as endodontics, implantology, oral surgery, and orthodontics. CT and MR images after dental treatment reveal a variety of hard- and soft-tissue changes and dental materials, which often cause image artifacts.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!