-
World Journal of Emergency Surgery :... Nov 2023An updated overview of ultrasound (US) for diagnosis of acute cholecystitis (AC) remains lacking. This systematic review was conducted to evaluate the diagnostic... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
An updated overview of ultrasound (US) for diagnosis of acute cholecystitis (AC) remains lacking. This systematic review was conducted to evaluate the diagnostic performance of US for AC.
METHODS
A systematic review was conducted following PRISMA guidelines. We meticulously screened articles from MEDLINE, Embase, and the Cochrane Library, spanning from inception to August 2023. We employed the search strategy combining the keywords "bedside US", "emergency US" or "point-of-care US" with "AC". Two reviewers independently screened the titles and abstracts of the retrieved articles to identify suitable studies. The inclusion criteria encompassed articles investigating the diagnostic performance of US for AC. Data regarding diagnostic performance, sonographers, and sonographic findings including the presence of gallstone, gallbladder (GB) wall thickness, peri-GB fluid, or sonographic Murphy sign were extracted, and a meta-analysis was executed. Case reports, editorials, and review articles were excluded, as well as studies focused on acalculous cholecystitis. The study quality was assessed with the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.
RESULTS
Forty studies with 8,652 patients were included. The majority of studies had a low risk of bias and applicability concerns. US had a pooled sensitivity of 71% (95% CI, 69-72%), a specificity of 85% (95% CI, 84-86%), and an accuracy of 0.83 (95% CI, 0.82-0.83) for the diagnosis of AC. The pooled sensitivity and specificity were 71% (95% CI, 67-74%) and 92% (95% CI, 90-93%) performed by emergency physicians (EPs), 79% (95% CI, 71-85%) and 76% (95% CI, 69-81%) performed by surgeons, and 68% (95% CI 66-71%) and 87% (95% CI, 86-88%) performed by radiologists, respectively. There were no statistically significant differences among the three groups.
CONCLUSION
US is a good imaging modality for the diagnosis of AC. EP-performed US has a similar diagnostic performance to radiologist-performed US. Further investigations would be needed to investigate the impact of US on expediting the management process and improving patient-centered outcomes.
Topics: Humans; Cholecystitis, Acute; Ultrasonography; Sensitivity and Specificity
PubMed: 38037062
DOI: 10.1186/s13017-023-00524-5 -
Biomedical Engineering Online Dec 2023This systematic review and meta-analysis were conducted to objectively evaluate the evidence of machine learning (ML) in the patient diagnosis of Intracranial Hemorrhage... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
This systematic review and meta-analysis were conducted to objectively evaluate the evidence of machine learning (ML) in the patient diagnosis of Intracranial Hemorrhage (ICH) on computed tomography (CT) scans.
METHODS
Until May 2023, systematic searches were conducted in ISI Web of Science, PubMed, Scopus, Cochrane Library, IEEE Xplore Digital Library, CINAHL, Science Direct, PROSPERO, and EMBASE for studies that evaluated the diagnostic precision of ML model-assisted ICH detection. Patients with and without ICH as the target condition who were receiving CT-Scan were eligible for the research, which used ML algorithms based on radiologists' reports as the gold reference standard. For meta-analysis, pooled sensitivities, specificities, and a summary receiver operating characteristics curve (SROC) were used.
RESULTS
At last, after screening the title, abstract, and full paper, twenty-six retrospective and three prospective, and two retrospective/prospective studies were included. The overall (Diagnostic Test Accuracy) DTA of retrospective studies with a pooled sensitivity was 0.917 (95% CI 0.88-0.943, I = 99%). The pooled specificity was 0.945 (95% CI 0.918-0.964, I = 100%). The pooled diagnostic odds ratio (DOR) was 219.47 (95% CI 104.78-459.66, I = 100%). These results were significant for the specificity of the different network architecture models (p-value = 0.0289). However, the results for sensitivity (p-value = 0.6417) and DOR (p-value = 0.2187) were not significant. The ResNet algorithm has higher pooled specificity than other algorithms with 0.935 (95% CI 0.854-0.973, I = 93%).
CONCLUSION
This meta-analysis on DTA of ML algorithms for detecting ICH by assessing non-contrast CT-Scans shows the ML has an acceptable performance in diagnosing ICH. Using ResNet in ICH detection remains promising prediction was improved via training in an Architecture Learning Network (ALN).
Topics: Humans; Prospective Studies; Sensitivity and Specificity; Retrospective Studies; Algorithms; Machine Learning; Diagnostic Tests, Routine
PubMed: 38049809
DOI: 10.1186/s12938-023-01172-1 -
Zeitschrift Fur Rheumatologie Mar 2024Rheumatoid arthritis-associated interstitial lung disease (RA-ILD) is a major driver of premature mortality in patients with rheumatoid arthritis (RA). Detection of... (Review)
Review
OBJECTIVE
Rheumatoid arthritis-associated interstitial lung disease (RA-ILD) is a major driver of premature mortality in patients with rheumatoid arthritis (RA). Detection of RA-ILD is crucial but requires awareness among the treating physicians. To date, however, there is no international recommendation concerning screening for ILD in RA patients.
METHODS
After a systematic literature review, the modified Delphi technique in combination with the nominal group technique was used to provide a Delphi consensus statement elaborated by an expert panel of pneumonologists, rheumatologists, and a radiologist. Based on the available evidence, several clusters of questions were defined and discussed until consent was reached.
RESULTS
A screening algorithm for ILD in patients with RA based on clinical signs, respiratory symptoms, and risk factors has been developed. Further, the recommendations address diagnostic tools for RA-ILD and the follow-up of RA patients qualifying for ILD screening.
Topics: Humans; Arthritis, Rheumatoid; Lung Diseases, Interstitial; Risk Factors
PubMed: 38240817
DOI: 10.1007/s00393-023-01464-w -
European Journal of Radiology Open Dec 2023Burnout among physicians has a prevalence rate exceeding 50%. The radiology department is not immune to the burnout epidemic. Understanding and addressing burnout among... (Review)
Review
RATIONALE AND OBJECTIVES
Burnout among physicians has a prevalence rate exceeding 50%. The radiology department is not immune to the burnout epidemic. Understanding and addressing burnout among radiologists has been a subject of recent interest. Thus, our study aims to systematically review studies reporting the prevalence of burnout in physicians in the radiology department while providing an overview of the factors associated with burnout among radiologists.
MATERIALS AND METHODS
The search was conducted from inception until November 13th, 2022, in PubMed, Embase, Education Resources Information Center, PsycINFO, and psycArticles. Studies reporting the prevalence of burnout or any subdimensions among radiology physicians, including residents, fellows, consultants, and attendings, were included. Data on study characteristics and estimates of burnout syndrome or any of its subdimensions were collected and summarized.
RESULTS
After screening 6379 studies, 23 studies from seven countries were eligible. The number of participants ranged from 26 to 460 (median, 162; interquartile range, 91-264). In all, 18 studies (78.3%) employed a form of the Maslach Burnout Inventory. In comparison, four studies (17.4%) used the Stanford Professional Fulfillment Index, and one study (4.3%) used a single-item measure derived from the Zero Burnout Program survey. Overall burnout prevalence estimates were reported by 14 studies (60.9%) and varied from 33% to 88%. High burnout prevalence estimates were reported by only five studies (21.7%) and ranged from 5% to 62%. Emotional exhaustion and depersonalization prevalence estimates were reported by 16 studies (69.6%) and ranged from 11%-100% and 4%-97%, respectively. Furthermore, 15 studies (65.2%) reported low personal accomplishment prevalence, ranging from 14.7% to 84%. There were at least seven definitions for overall burnout and high burnout among the included studies, and there was high heterogeneity among the cutoff scores used for the burnout subdimensions.
CONCLUSION
Burnout in radiology is increasing globally, with prevalence estimates reaching 88% and 62% for overall and high burnout, respectively. A myriad of factors has been identified as contributing to the increased prevalence. Our data demonstrated significant variability in burnout prevalence estimates among radiologists and major disparities in burnout criteria, instrument tools, and study quality.
PubMed: 37920681
DOI: 10.1016/j.ejro.2023.100530 -
BMC Medical Informatics and Decision... Jul 2023Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are...
INTRODUCTION
Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are critical for improving patients' outcomes, as over 40% of patients with EC are diagnosed after metastasis. Recent advances in machine learning (ML) techniques, particularly in computer vision, have demonstrated promising applications in medical image processing, assisting clinicians in making more accurate and faster diagnostic decisions. Given the significance of early detection of EC, this systematic review aims to summarize and discuss the current state of research on ML-based methods for the early detection of EC.
METHODS
We conducted a comprehensive systematic search of five databases (PubMed, Scopus, Web of Science, Wiley, and IEEE) using search terms such as "ML", "Deep Learning (DL (", "Neural Networks (NN)", "Esophagus", "EC" and "Early Detection". After applying inclusion and exclusion criteria, 31 articles were retained for full review.
RESULTS
The results of this review highlight the potential of ML-based methods in the early detection of EC. The average accuracy of the reviewed methods in the analysis of endoscopic and computed tomography (CT (images of the esophagus was over 89%, indicating a high impact on early detection of EC. Additionally, the highest percentage of clinical images used in the early detection of EC with the use of ML was related to white light imaging (WLI) images. Among all ML techniques, methods based on convolutional neural networks (CNN) achieved higher accuracy and sensitivity in the early detection of EC compared to other methods.
CONCLUSION
Our findings suggest that ML methods may improve accuracy in the early detection of EC, potentially supporting radiologists, endoscopists, and pathologists in diagnosis and treatment planning. However, the current literature is limited, and more studies are needed to investigate the clinical applications of these methods in early detection of EC. Furthermore, many studies suffer from class imbalance and biases, highlighting the need for validation of detection algorithms across organizations in longitudinal studies.
Topics: Humans; Deep Learning; Early Detection of Cancer; Machine Learning; Neural Networks, Computer; Esophageal Neoplasms
PubMed: 37460991
DOI: 10.1186/s12911-023-02235-y -
Diagnostics (Basel, Switzerland) Oct 2023: Carpal tunnel syndrome (CTS) is the most common entrapment neuropathy for which ultrasound imaging has recently emerged as a valuable diagnostic tool. This... (Review)
Review
: Carpal tunnel syndrome (CTS) is the most common entrapment neuropathy for which ultrasound imaging has recently emerged as a valuable diagnostic tool. This meta-analysis aims to investigate the role of ultrasound radiomics in the diagnosis of CTS and compare it with other diagnostic approaches. : We conducted a comprehensive search of electronic databases from inception to September 2023. The included studies were assessed for quality using the Quality Assessment Tool for Diagnostic Accuracy Studies. The primary outcome was the diagnostic performance of ultrasound radiomics compared to radiologist evaluation for diagnosing CTS. : Our meta-analysis included five observational studies comprising 840 participants. In the context of radiologist evaluation, the combined statistics for sensitivity, specificity, and diagnostic odds ratio were 0.78 (95% confidence interval (CI), 0.71 to 0.83), 0.72 (95% CI, 0.59 to 0.81), and 9 (95% CI, 5 to 15), respectively. In contrast, the ultrasound radiomics training mode yielded a combined sensitivity of 0.88 (95% CI, 0.85 to 0.91), a specificity of 0.88 (95% CI, 0.84 to 0.92), and a diagnostic odds ratio of 58 (95% CI, 38 to 87). Similarly, the ultrasound radiomics testing mode demonstrated an aggregated sensitivity of 0.85 (95% CI, 0.78 to 0.89), a specificity of 0.80 (95% CI, 0.73 to 0.85), and a diagnostic odds ratio of 22 (95% CI, 12 to 41). : In contrast to assessments by radiologists, ultrasound radiomics exhibited superior diagnostic performance in detecting CTS. Furthermore, there was minimal variability in the diagnostic accuracy between the training and testing sets of ultrasound radiomics, highlighting its potential as a robust diagnostic tool in CTS.
PubMed: 37892101
DOI: 10.3390/diagnostics13203280 -
Insights Into Imaging Oct 2023The study aim was to conduct a systematic review of the literature reporting the application of radiomics to imaging techniques in patients with ovarian lesions.
OBJECTIVES
The study aim was to conduct a systematic review of the literature reporting the application of radiomics to imaging techniques in patients with ovarian lesions.
METHODS
MEDLINE/PubMed, Web of Science, Scopus, EMBASE, Ovid and ClinicalTrials.gov were searched for relevant articles. Using PRISMA criteria, data were extracted from short-listed studies. Validity and bias were assessed independently by 2 researchers in consensus using the Quality in Prognosis Studies (QUIPS) tool. Radiomic Quality Score (RQS) was utilised to assess radiomic methodology.
RESULTS
After duplicate removal, 63 articles were identified, of which 33 were eligible. Fifteen assessed lesion classifications, 10 treatment outcomes, 5 outcome predictions, 2 metastatic disease predictions and 1 classification/outcome prediction. The sample size ranged from 28 to 501 patients. Twelve studies investigated CT, 11 MRI, 4 ultrasound and 1 FDG PET-CT. Twenty-three studies (70%) incorporated 3D segmentation. Various modelling methods were used, most commonly LASSO (least absolute shrinkage and selection operator) (10/33). Five studies (15%) compared radiomic models to radiologist interpretation, all demonstrating superior performance. Only 6 studies (18%) included external validation. Five studies (15%) had a low overall risk of bias, 9 (27%) moderate, and 19 (58%) high risk of bias. The highest RQS achieved was 61.1%, and the lowest was - 16.7%.
CONCLUSION
Radiomics has the potential as a clinical diagnostic tool in patients with ovarian masses and may allow better lesion stratification, guiding more personalised patient care in the future. Standardisation of the feature extraction methodology, larger and more diverse patient cohorts and real-world evaluation is required before clinical translation.
CLINICAL RELEVANCE STATEMENT
Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. Modelling with larger cohorts and real-world evaluation is required before clinical translation.
KEY POINTS
• Radiomics is emerging as a tool for enhancing clinical decisions in patients with ovarian masses. • Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. • Modelling with larger cohorts and real-world evaluation is required before clinical translation.
PubMed: 37782375
DOI: 10.1186/s13244-023-01500-y -
Cancers Jul 2023CDSSs are being continuously developed and integrated into routine clinical practice as they assist clinicians and radiologists in dealing with an enormous amount of... (Review)
Review
CDSSs are being continuously developed and integrated into routine clinical practice as they assist clinicians and radiologists in dealing with an enormous amount of medical data, reduce clinical errors, and improve diagnostic capabilities. They assist detection, classification, and grading of brain tumours as well as alert physicians of treatment change plans. The aim of this systematic review is to identify various CDSSs that are used in brain tumour diagnosis and prognosis and rely on data captured by any imaging modality. Based on the 2020 preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol, the literature search was conducted in PubMed and Engineering Village Compendex databases. Different types of CDSSs identified through this review include Curiam BT, FASMA, MIROR, HealthAgents, and INTERPRET, among others. This review also examines various CDSS tool types, system features, techniques, accuracy, and outcomes, to provide the latest evidence available in the field of neuro-oncology. An overview of such CDSSs used to support clinical decision-making in the management and treatment of brain tumours, along with their benefits, challenges, and future perspectives has been provided. Although a CDSS improves diagnostic capabilities and healthcare delivery, there is lack of specific evidence to support these claims. The absence of empirical data slows down both user acceptance and evaluation of the actual impact of CDSS on brain tumour management. Instead of emphasizing the advantages of implementing CDSS, it is important to address its potential drawbacks and ethical implications. By doing so, it can promote the responsible use of CDSS and facilitate its faster adoption in clinical settings.
PubMed: 37444633
DOI: 10.3390/cancers15133523 -
Frontiers in Radiology 2023Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task is challenging and laborious for radiologists. Deep... (Review)
Review
INTRODUCTION
Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task is challenging and laborious for radiologists. Deep learning has shown promise in automating image segmentation in radiology, including for malignant bone lesions. The purpose of this review is to investigate deep learning-based image segmentation methods for malignant bone lesions on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron-Emission Tomography/CT (PET/CT).
METHOD
The literature search of deep learning-based image segmentation of malignant bony lesions on CT and MRI was conducted in PubMed, Embase, Web of Science, and Scopus electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 41 original articles published between February 2017 and March 2023 were included in the review.
RESULTS
The majority of papers studied MRI, followed by CT, PET/CT, and PET/MRI. There was relatively even distribution of papers studying primary vs. secondary malignancies, as well as utilizing 3-dimensional vs. 2-dimensional data. Many papers utilize custom built models as a modification or variation of U-Net. The most common metric for evaluation was the dice similarity coefficient (DSC). Most models achieved a DSC above 0.6, with medians for all imaging modalities between 0.85-0.9.
DISCUSSION
Deep learning methods show promising ability to segment malignant osseous lesions on CT, MRI, and PET/CT. Some strategies which are commonly applied to help improve performance include data augmentation, utilization of large public datasets, preprocessing including denoising and cropping, and U-Net architecture modification. Future directions include overcoming dataset and annotation homogeneity and generalizing for clinical applicability.
PubMed: 37614529
DOI: 10.3389/fradi.2023.1241651 -
The Indian Journal of Radiology &... Jul 2024Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely... (Review)
Review
Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.
PubMed: 38912238
DOI: 10.1055/s-0043-1775737