Purpose: To compare the diagnostic accuracy of convolutional neural networks (CNN) with radiologists as the reference standard in the diagnosis of intracranial hemorrhages (ICH) with non contrast computed tomography of the cerebrum (NCTC).
Methods: PubMed, Embase, Scopus, and Web of Science were searched for the period from 1 January 2012 to 20 July 2020; eligible studies included patients with and without ICH as the target condition undergoing NCTC, studies had deep learning algorithms based on CNNs and radiologists reports as the minimum reference standard. Pooled sensitivities, specificities and a summary receiver operating characteristics curve (SROC) were employed for meta-analysis.
Results: 5,119 records were identified through database searching. Title-screening left 47 studies for full-text assessment and 6 studies for meta-analysis. Comparing the CNN performance to reference standards in the retrospective studies found a pooled sensitivity of 96.00% (95% CI: 93.00% to 97.00%), pooled specificity of 97.00% (95% CI: 90.00% to 99.00%) and SROC of 98.00% (95% CI: 97.00% to 99.00%), and combining retrospective and studies with external datasets found a pooled sensitivity of 95.00% (95% CI: 91.00% to 97.00%), pooled specificity of 96.00% (95% CI: 91.00% to 98.00%) and a pooled SROC of 98.00% (95% CI: 97.00% to 99.00%).
Conclusion: This review found the diagnostic performance of CNNs to be equivalent to that of radiologists for retrospective studies. Out-of-sample external validation studies pooled with retrospective studies found CNN performance to be slightly worse. There is a critical need for studies with a robust reference standard and external data-set validation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ejrad.2021.110073 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Health Care Resource Use and Costs After Hospitalization With Multiple Organ Dysfunction in Children.
JAMA Netw Open
January 2025
Department of Medicine, University of California, San Francisco.
Importance: Multiple organ dysfunction (MOD) is a leading cause of in-hospital child mortality. For survivors, posthospitalization health care resource use and costs are unknown.
Objective: To evaluate longitudinal health care resource use and costs after hospitalization with MOD in infants (aged <1 year) and children (aged 1-18 years).
Diagnostic accuracy of node-RADS for the detection of lymph node invasion: a systematic review and meta-analysis.
Eur Radiol
January 2025
Department of Urological Surgical, JiangNan University Medical Center, Wuxi, China.
Objective: To conduct a meta-analysis assessing the diagnostic performance of the node reporting and data system (Node-RADS) for detecting lymph node (LN) invasion.
Method: We performed a systematic literature search of online scientific publication databases from inception up to July 31, 2024. We used the quality assessment of diagnostic accuracy studies-2 (QUADAS-2) to assess the study quality, and heterogeneity was determined by the Q-test and measured with I statistics.
Reduced SARS-CoV-2 Infection Rates in Lab Workers Conducting Nucleic Acid Testing: Controlling for the Healthy Worker Effect.
J Epidemiol Glob Health
January 2025
Center of Clinical Laboratory, Zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, No.201-209 Hubinnan Road, Xiamen, 361004, China.
Background: During the COVID-19 outbreak in December 2022 in China, some laboratory workers in SARS-CoV-2 nucleic acid testing (NAT) laboratories remained uninfected.
Objectives: To evaluate if the incidence of SARS-CoV-2 infection was reduced in laboratory workers who performed SARS-CoV-2 NAT, and whether this reduction resulted from the healthy worker effect.
Methods: This retrospective cohort study included 423 laboratory workers from 14 SARS-CoV-2 NAT laboratories in Xiamen, China.
Normative measurements of the frontal nerve by magnetic resonance imaging in an Australia cohort.
Surg Radiol Anat
January 2025
Department of Ophthalmology & Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia.
Purpose: To report the normative dimensions of the frontal nerve (FN) on fat-suppressed suppressed gadolinium (fs-gad) enhanced magnetic resonance imaging (MRI).
Method: A retrospective cohort study of patients who underwent coronal fs-gad T1-weighted MRI. Orbits were excluded if there was unilateral or bilateral pathology of the FN or optic nerve sheath (ONS), incomplete MRI sequences, poor image quality or indiscernible FN on radiological assessment.
Automatic multimodal registration of cone-beam computed tomography and intraoral scans: a systematic review and meta-analysis.
Clin Oral Investig
January 2025
Stomatology Hospital, School of Stomatology, Zhejiang University School of Medicine, Clinical Research Center for Oral Diseases of Zhejiang Province, Key Laboratory of Oral Biomedical Research of Zhejiang Province, Cancer Center of Zhejiang University, Hangzhou, 310006, China.
Objectives: To evaluate recent advances in the automatic multimodal registration of cone-beam computed tomography (CBCT) and intraoral scans (IOS) and their clinical significance in dentistry.
Methods: A comprehensive literature search was conducted in October 2024 across the PubMed, Web of Science, and IEEE Xplore databases, including studies that were published in the past decade. The inclusion criteria were as follows: English-language studies, randomized and nonrandomized controlled trials, cohort studies, case-control studies, cross-sectional studies, and retrospective studies.
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!