Objectives: To develop a deep learning algorithm for automated detection and localization of intracranial aneurysms on time-of-flight MR angiography and evaluate its diagnostic performance.
Methods: In a retrospective and multicenter study, MR images with aneurysms based on radiological reports were extracted. The examinations were randomly divided into two data sets: training set of 468 examinations and internal test set of 120 examinations. Additionally, 50 examinations without aneurysms were randomly selected and added to the internal test set. External test data set consisted of 56 examinations with intracranial aneurysms and 50 examinations without aneurysms, which were extracted based on radiological reports from a different institution. After manual ground truth segmentation of aneurysms, a deep learning algorithm based on 3D ResNet architecture was established with the training set. Its sensitivity, positive predictive value, and specificity were evaluated in the internal and external test sets.
Results: MR images included 551 aneurysms (mean diameter, 4.17 ± 2.49 mm) in the training, 147 aneurysms (mean diameter, 3.98 ± 2.11 mm) in the internal test, 63 aneurysms (mean diameter, 3.23 ± 1.69 mm) in the external test sets. The sensitivity, the positive predictive value, and the specificity were 87.1%, 92.8%, and 92.0% for the internal test set and 85.7%, 91.5%, and 98.0% for the external test set, respectively.
Conclusion: A deep learning algorithm detected intracranial aneurysms with a high diagnostic performance which was validated using external data set.
Key Points: • A deep learning-based algorithm for the automated diagnosis of intracranial aneurysms demonstrated a high sensitivity, positive predictive value, and specificity. • The high diagnostic performance of the algorithm was validated using external test data set from a different institution with a different scanner. • The algorithm might be robust and effective for general use in real clinical settings.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00330-020-06966-8 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Assessing the capacity to implement the international health regulations to control COVID-19 at points of entry in Eswatini.
J Infect Dev Ctries
December 2024
Institute of Public Health, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
Introduction: Significant challenges to implementing international health regulations (IHR) at points of entry (PoEs) have been highlighted by the coronavirus disease 2019 (COVID-19) pandemic. Better assessment of the capacities of the PoEs may promote focused interventions. This study aimed to assess the capacities and practices at PoEs.
View Article and Find Full Text PDFBackground: There has been an increase in both primary anatomic (aTSA) and reverse total shoulder arthroplasty (rTSA) over the last decade, with rates peaking for patients aged 75 years and older. Despite aTSA being the mainstay of treatment for patients with glenohumeral arthritis in the absence of rotator cuff insufficiency, there has been an upward trend of rTSA utilization in the elderly due to concerns about rotator cuff integrity, regardless of deformity. The purpose of this study is to evaluate outcomes including pain, function, range of motion, satisfaction, and complications in patients 80 years or older following primary anatomic and reverse total shoulder arthroplasty for osteoarthritis without full thickness rotator cuff tears.
View Article and Find Full Text PDFPivotal trial characteristics and types of endpoints used to support Food and Drug Administration rare disease drug approvals between 2013 and 2022.
Clin Trials
January 2025
Rare Diseases Team, Office of New Drugs, Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, MD, USA.
Background/aims: Rare disease drug development faces unique challenges, such as genotypic and phenotypic heterogeneity within small patient populations and a lack of established outcome measures for conditions without previously successful drug development programs. These challenges complicate the process of selecting the appropriate trial endpoints and conducting clinical trials in rare diseases. In this descriptive study, we examined novel drug approvals for non-oncologic rare diseases by the U.
View Article and Find Full Text PDFComputer-Aided Construction and Evaluation of Poly-L-Lysine/Hyodeoxycholic Acid Nanoparticles for Hemorrhage and Infection Therapy.
Pharmaceutics
December 2024
School of Pharmacy and Bioengineering, Chongqing University of Technology, Chongqing 400054, China.
Traumatic hemorrhage and infection are major causes of mortality in wounds caused by battlefield injuries, hospital procedures, and traffic accidents. Developing a multifunctional nano-drug capable of simultaneously controlling bleeding, preventing infection, and promoting wound healing is critical. This study aimed to design and evaluate a nanoparticle-based solution to address these challenges effectively.
View Article and Find Full Text PDFImpact of Caffeine Intake on Female Basketball Players' Performance.
Nutrients
January 2025
Performance and Sport Rehabilitation Laboratory, University of Castilla La Mancha, 45071 Toledo, Spain.
Background: This study aimed to analyze the effect of caffeine ingestion on basketball performance in semi-professional female players.
Methods: A double-blind, placebo-controlled, randomized experimental design was conducted, in two different periods separated by a week. Twelve female basketball players ingested 3 mg of caffeine/kg of body mass or a placebo.
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!