Background: Despite the dramatic increase in the use of medical imaging in various therapeutic fields of clinical trials, the first step of image quality check (image QC), which aims to check whether images are uploaded appropriately according to the predefined rules, is still performed manually by image analysts, which requires a lot of manpower and time.
Methods: In this retrospective study, 1669 computed tomography (CT) images with five specific anatomical locations were collected from Asan Medical Center and Kangdong Sacred Heart Hospital. To generate the ground truth, two radiologists reviewed the anatomical locations and presence of contrast enhancement using the collected data. The individual deep learning model is developed through InceptionResNetv2 and transfer learning, and we propose Image Quality Check-Net (Image QC-Net), an ensemble AI model that utilizes it. To evaluate their clinical effectiveness, the overall accuracy and time spent on image quality check of a conventional model and ImageQC-net were compared.
Results: ImageQC-net body part classification showed excellent performance in both internal (precision, 100%; recall, 100% accuracy, 100%) and external verification sets (precision, 99.8%; recovery rate, 99.8%, accuracy, 99.8%). In addition, contrast enhancement classification performance achieved 100% precision, recall, and accuracy in the internal verification set and achieved (precision, 100%; recall, 100%; accuracy 100%) in the external dataset. In the case of clinical effects, the reduction of time by checking the quality of artificial intelligence (AI) support by analysts 1 and 2 (49.7% and 48.3%, respectively) was statistically significant (p < 0.001).
Conclusions: Comprehensive AI techniques to identify body parts and contrast enhancement on CT images are highly accurate and can significantly reduce the time spent on image quality checks.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9107169 | PMC |
| http://dx.doi.org/10.1186/s12880-022-00815-4 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A review of Kilovoltage (kV) Radiotherapy Treatment in the UK: Quality Control, Radiation Dosimetry, Treatment Equipment and Workload.
Br J Radiol
January 2025
Radiotherapy Physics Dept, Ipswich Hospital, Ipswich, Suffolk, IP45PD, UK.
Objectives: To survey kilovoltage (kV) radiotherapy in the UK, updating a 2016 study, focussing on radiotherapy physics, including equipment quality control (QC) and radiation dosimetry, with information on installed equipment and clinical activity.
Methods: All UK radiotherapy physics departments (n = 68) were invited to complete a comprehensive survey. An analysis of the installed equipment base, patient numbers, clinical activity, QC testing and radiation dosimetry processes were undertaken.
Time-efficient HPLC Validation Methodology for the Qualitative Analysis of 68Ga PSMA-11 in Routine Clinical Usage under Isocratic Method.
Indian J Nucl Med
November 2024
Department of Nuclear Medicine and Molecular Imaging, Homi Bhabha Cancer Hospital and Mahamana Pandit Madan Mohan Malaviya Cancer Centre, Tata Memorial Centre, Homi Bhabha National Institute, Varanasi, Uttar Pradesh, India.
Background: Prostate-specific membrane antigen (PSMA) has shown to be a promising agent for prostate cancer imaging under PET-CT. With the automation in radiolabeling with 68Ga, using iTG 68Ge/68Ga generator, it has helped introduce various new diagnostic agents and achieve good manufacturing practices (GMP) simultaneously. However, before any radiopharmaceutical is put into clinical usage, it should always be checked for its radiochemical purity and other quality parameters before injecting in the patient.
View Article and Find Full Text PDFHealth impacts of a remotely delivered prolonged nightly fasting intervention in stressed adults with memory decline and obesity: A nationwide randomized controlled pilot trial.
J Clin Transl Sci
November 2024
College of Health Solutions, Arizona State University, Phoenix, AZ, USA.
Objective/goals: Cognitive decline is intricately linked to various factors such as obesity, stress, poor sleep, and circadian rhythm misalignment, which are interrelated in their impact on cognitive health. Irregular food-intake timing further compounds these issues. The practice of prolonged nightly fasting (PNF) may help synchronize food intake with circadian rhythms, potentially mitigating adverse effects of cognitive decline and associated factors.
View Article and Find Full Text PDFReturn to Work, Sport, and Sport- Related Activity After Distal Triceps Tendon Repair: A Systematic Review.
Am J Sports Med
January 2025
Rothman Orthopaedic Institute, Thomas Jefferson University Hospital, Philadelphia, Pennsylvania, USA.
Background: Distal triceps tendon injuries are relatively rare injuries, often occurring in highly active patients with physically demanding jobs or lifestyles. Information on return to work, sport, and activity is essential for patient education and counseling after a distal triceps tendon rupture.
Purpose: To determine the rates of return to work, sport, and sport-related activity after distal triceps tendon repair.
Understanding the Medical Education Experiences of Low-Income Students Through a Maslow's Hierarchy of Needs Lens: An Exploratory Qualitative Study.
J Gen Intern Med
January 2025
MD/PhD Program, Yale School of Medicine, New Haven, CT, USA.
Background: Diversity in the physician workforce is critical for quality patient care. Students from low-income backgrounds represent an increasing proportion of medical school matriculants, yet little research has addressed their medical school experiences.
Objective: To explore the medical school experiences of students from low-income backgrounds using a modified version of Maslow's Hierarchy of Needs (physiologic, safety, love/belonging, esteem, and self-actualization) as a theoretical framework.
Want 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!