Image metrics based on Human Visual System (HVS) play a remarkable role in the evaluation of complex image processing algorithms. However, mimicking the HVS is known to be complex and computationally expensive (both in terms of time and memory), and its usage is thus limited to a few applications and to small input data. All of this makes such metrics not fully attractive in real-world scenarios. To address these issues, we propose Deep Image Quality Metric (DIQM), a deep-learning approach to learn the global image quality feature (mean-opinion-score). DIQM can emulate existing visual metrics efficiently, reducing the computational costs by more than an order of magnitude with respect to existing implementations.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TIP.2019.2944079 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Application value of split-bolus contrast injection combined with dual-energy CT scanning technology in pediatric CTU imaging.
Eur J Radiol
January 2025
Department of Radiology Children's Hospital of Chongqing Medical University, National Clinical Research Center for Child Health and Disorders, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing Key Laboratory of Child Neurodevelopment and Cognitive Disorders, China. Electronic address:
Objective: To explore the clinical value of combining split-bolus contrast injection with dual-energy CT(DECT) scanning technology in pediatric computed tomography urography (CTU) imaging.
Methods: A total of 128 children aged 0-17 years were prospectively selected and randomly assigned to three groups: A, B, and C. For Group A, a high-pitch flash mode was employed, where a single bolus of contrast agent was followed by four-phase scanning (noncontrast, cortex, medulla, and excretory phases).
Deep learning aided determination of the optimal number of detectors for photoacoustic tomography.
Biomed Phys Eng Express
January 2025
Applied Sciences, Indian Institute of Information Technology Allahabad, Deoghat, Jhalwa, Allahabad, 211012, INDIA.
Photoacoustic tomography (PAT) is a non-destructive, non-ionizing, and rapidly expanding hybrid biomedical imaging technique, yet it faces challenges in obtaining clear images due to limited data from detectors or angles. As a result, the methodology suffers from significant streak artifacts and low-quality images. The integration of deep learning (DL), specifically convolutional neural networks (CNNs), has recently demonstrated powerful performance in various fields of PAT.
View Article and Find Full Text PDFIntraindividual Comparison of Image Quality Between Low-Dose and Ultra-Low-Dose Abdominal CT With Deep Learning Reconstruction and Standard-Dose Abdominal CT Using Dual-Split Scan.
Invest Radiol
January 2025
From the Department of Radiology, Ulsan University Hospital, Ulsan, Republic of Korea (T.Y.L.); Department of Radiology, University of Ulsan College of Medicine, Seoul, Republic of Korea (T.Y.L.); Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea (J.H.Y., H.K., J.M.L.); Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea (J.H.Y., S.H.P., J.M.L.); Department of Radiology, Inje University Busan Paik Hospital, Busan, Republic of Korea (J.Y.P.); Department of Radiology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea (S.H.P.); Department of Radiology, Hanyang University College of Medicine, Seoul, Republic of Korea (C.L.); Division of Biostatistics, Medical Research Collaborating Center, Seoul National University Hospital, Seoul, Republic of Korea (Y.C.); and Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea (J.M.L.).
Objective: The aim of this study was to intraindividually compare the conspicuity of focal liver lesions (FLLs) between low- and ultra-low-dose computed tomography (CT) with deep learning reconstruction (DLR) and standard-dose CT with model-based iterative reconstruction (MBIR) from a single CT using dual-split scan in patients with suspected liver metastasis via a noninferiority design.
Materials And Methods: This prospective study enrolled participants who met the eligibility criteria at 2 tertiary hospitals in South Korea from June 2022 to January 2023. The criteria included (a) being aged between 20 and 85 years and (b) having suspected or known liver metastases.
Even though Leydig cell tumor (LCT) represents the most common neoplasia among testicular sex cord-stromal tumors (SCSTs), it is a rare condition, comprising 1-2% of all testicular tumors, with a 10% risk of malignancy most commonly located in retroperitoneal lymph nodes. LCTs may demonstrate various clinical manifestations - from asymptomatic intratesticular swelling through nonspecific symptoms such as loss of libido, impotence or infertility, up to feminizing or virilizing syndromes due to hormonal activity of the tumor. This article presents a case of Leydig cell tumor that was associated with azoospermia what have rarely been reported worldwide.
View Article and Find Full Text PDFAbnormal network homogeneity in patients with bipolar disorder in attention network.
Brain Imaging Behav
January 2025
Key Laboratory of Adolescent Cyberpsychology and Behavior (Ministry of Education), Wuhan, China.
Bipolar disorder (BD) is a complex psychiatric condition marked by significant mood fluctuations that deeply affect quality of life. Understanding the neural mechanisms underlying BD is critical for improving diagnostic accuracy and developing more effective treatments. This study utilized resting-state functional magnetic resonance imaging (rs-fMRI) to investigate functional connectivity within the ventral and dorsal attention networks in 52 patients with BD and 51 healthy controls.
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!