Radiology (all articles)
Retrospective Study: AI Tool Accurately Excludes Pathology in Up to 52.7% of Unremarkable Chest Radiographs with Low Critical Misses – Radiology
24 Aug, 2024 | 16:14h | UTCStudy Design and Population: This retrospective study assessed the effectiveness of a commercial AI tool in correctly identifying unremarkable chest radiographs, thus potentially reducing the workload in radiology departments. The study analyzed 1,961 chest radiographs from adult patients (median age: 72 years) across four Danish hospitals. The radiographs were labeled as remarkable or unremarkable by thoracic radiologists, and the AI tool’s performance was evaluated at varying sensitivity thresholds.
Main Findings: The AI tool demonstrated a specificity of 24.5% to 52.7% at sensitivity thresholds of 99.9% to 98.0%, respectively, effectively excluding pathology in unremarkable chest radiographs. At sensitivities of 95.4% or higher, the AI had equal or lower rates of critical misses compared to radiology reports, with the AI missing only 2.2% of critical findings compared to 1.1% by radiologists at similar sensitivity levels.
Implications for Practice: The results suggest that AI tools could autonomously report up to 52.7% of unremarkable chest radiographs, potentially reducing radiologist workload without compromising patient safety. However, prospective studies are necessary to confirm these findings and optimize AI deployment in clinical practice.
Cohort Study: One-Fourth of MS Relapses Occur Without MRI Activity, Highlighting ACES Phenomenon – JAMA Neurol
18 Aug, 2024 | 19:16h | UTCStudy Design and Population: This multicenter observational cohort study examined 637 clinical relapse events in 608 patients with relapsing-remitting multiple sclerosis (RRMS) from the French MS registry, spanning January 2015 to June 2023. The study included relapses with brain and spinal cord MRI performed within 12-24 months before and 50 days after the event.
Main Findings: Approximately 26% of relapses were classified as acute clinical events with stable MRI (ACES), showing no new T2 or gadolinium-enhanced T1 lesions. ACES were more likely in patients on highly effective disease-modifying therapies (DMTs), with longer disease duration, or with fatigue. ACES were associated with increased rates of relapse, confirmed disability accrual, and progression to secondary progressive MS, though their MRI stability was unaffected by DMTs.
Implications for Practice: The study suggests that MRI alone may not fully capture disease activity in RRMS, highlighting the need for comprehensive clinical assessment in therapeutic decision-making and clinical trial designs.
Retrospective Cohort Study: Rheumatoid Arthritis Linked to Over 50% Increased Lung Cancer Risk, with a Three-Fold Risk in RA-Associated Interstitial Lung Disease – Arthritis Rheumatol
18 Aug, 2024 | 18:58h | UTCStudy Design and Population: This retrospective matched cohort study examined the risk of lung cancer in 72,795 patients with rheumatoid arthritis (RA) and 757 patients with RA-associated interstitial lung disease (RA-ILD) from the Veterans Health Administration database, compared with 633,937 non-RA controls. The study spanned from 2000 to 2019, with patients matched on age, gender, and enrollment year.
Main Findings: The study found that RA was associated with a 58% increase in lung cancer risk (adjusted hazard ratio [aHR] 1.58). The risk was significantly higher in RA-ILD patients, with a more than three-fold increase (aHR 3.25) compared to non-RA controls. Even among never smokers, RA patients showed a 65% increased lung cancer risk, indicating that factors beyond smoking contribute to the elevated risk.
Implications for Practice: The study underscores the significant increase in lung cancer risk among patients with RA, particularly those with RA-ILD. While this elevated risk is notable, further research is necessary to determine the most effective strategies for monitoring and managing this risk. Clinicians should be aware of these findings and consider them when evaluating the overall health and risk factors of patients with RA, especially those with additional pulmonary complications like ILD. Enhanced awareness and individualized risk assessments may help in early detection and management of lung cancer in this high-risk population.
Study Shows High Prevalence of Solid Lung Nodules in Nonsmoking Adults – Radiology
14 Aug, 2024 | 13:14h | UTCStudy Design and Population: This cohort study examined the prevalence and size distribution of solid lung nodules in a nonsmoking population from the Northern Netherlands. A total of 10,431 participants aged 45 years and older, predominantly nonsmokers, were included in the Imaging in Lifelines (ImaLife) study. The study utilized low-dose chest CT scans to detect and measure lung nodules.
Main Findings: Lung nodules were present in 42% of participants, with a higher prevalence in males (47.5%) than females (37.7%). The prevalence of clinically relevant nodules (≥100 mm³) was 11.1%, and actionable nodules (≥300 mm³) were found in 2.3% of individuals. Both prevalence and nodule size increased with age, and male participants consistently showed a higher prevalence and larger nodule sizes compared to females.
Implications for Practice: While 42% of nonsmoking adults in this Northern European cohort were found to have solid lung nodules, the incidence of lung cancer within this population is notably low. This suggests that many of the clinically relevant and even actionable nodules identified in nonsmokers are likely benign. These findings highlight the need to refine nodule management strategies for individuals at low risk of lung cancer, potentially reducing unnecessary follow-up and interventions in nonsmoking populations. Future research on lung cancer outcomes in this cohort could further inform and optimize guidelines for nodule management in low-risk groups.
RCT: Eliminating Fasting Before Contrast-Enhanced CT in Outpatients Reduces Nausea and Vomiting Without Increasing Acute Adverse Reactions – Insights Imaging
11 Aug, 2024 | 13:41h | UTCStudy Design and Population: This single-center, randomized clinical trial was conducted in Spain with 1,103 adult outpatients undergoing non-emergency contrast-enhanced CT scans. Patients were randomized into two groups: one group fasted for at least 6 hours (control), while the other group had no food restrictions (intervention). The primary aim was to assess whether eliminating fasting affects the incidence of acute adverse reactions (AARs), such as nausea and vomiting.
Main Findings: The study found no significant difference in the overall incidence of acute adverse reactions between the fasting and non-fasting groups (3.21% vs. 2.30%; p = 0.36). However, the non-fasting group had a significantly lower incidence of nausea and vomiting (0.92% vs. 2.86%; p = 0.02). Multivariate logistic regression identified fasting, age, allergies, neurological diseases, and contrast media concentration as independent risk factors for nausea and vomiting.
Implications for Practice: The findings suggest that the traditional practice of fasting before contrast-enhanced CT scans is unnecessary and may increase the risk of nausea and vomiting. Therefore, unrestricted food intake should be allowed for most contrast-enhanced CT exams, reserving fasting only for specific imaging procedures.
IDSA 2024 Guidelines for Managing Complicated Intra-abdominal Infections – Clin Infect Dis
10 Aug, 2024 | 22:10h | UTCIntroduction: The Infectious Diseases Society of America (IDSA) has updated its clinical practice guidelines for managing complicated intra-abdominal infections in adults, children, and pregnant individuals. The update focuses on risk assessment, diagnostic imaging, and microbiological evaluation, with recommendations grounded in systematic literature reviews and the GRADE approach for rating evidence.
Key Points:
1 – Risk Stratification:
– For adults with complicated intra-abdominal infections, the APACHE II score is recommended for risk stratification within 24 hours of hospital or ICU admission. The WSES Sepsis Severity Score is an acceptable alternative.
– No specific severity scoring system is recommended for pediatric patients.
2 – Diagnostic Imaging for Appendicitis:
– In non-pregnant adults, CT is suggested as the initial imaging modality for suspected acute appendicitis.
– For children, an abdominal ultrasound (US) is preferred initially, with MRI or CT recommended if the US is inconclusive.
– In pregnant individuals, US or MRI can be considered, with MRI suggested if initial US results are inconclusive.
3 – Imaging for Acute Cholecystitis and Cholangitis:
– For non-pregnant adults, US is recommended initially. If inconclusive, a CT scan is suggested.
– For pregnant individuals, US or MRI can be used, but the guidelines do not specify a preferred modality due to a knowledge gap.
4 – Blood Cultures:
– Blood cultures are recommended in adults and children with suspected intra-abdominal infections presenting with severe symptoms such as hypotension or tachypnea, especially when antibiotic-resistant organisms are a concern.
– Routine blood cultures are not recommended for patients without these risk factors.
5 – Intra-abdominal Fluid Cultures:
– In complicated intra-abdominal infections requiring source control procedures, obtaining intra-abdominal cultures is advised to guide antimicrobial therapy.
– In uncomplicated appendicitis cases, routine cultures are not recommended unless the patient is immunocompromised or complicated disease is suspected during surgery.
Conclusion: These guidelines provide evidence-based recommendations to improve the management of complicated intra-abdominal infections, emphasizing appropriate risk stratification, targeted diagnostic imaging, and the selective use of cultures to guide therapy.
Retrospective Study: Automated Multiorgan CT Markers Predict Diabetes and Cardiometabolic Comorbidities – Radiology
10 Aug, 2024 | 21:36h | UTCStudy Design and Population: This retrospective study analyzed data from 32,166 Korean adults (mean age, 45 years) who underwent health screenings, including fluorodeoxyglucose PET/CT scans, between 2012 and 2015. The study aimed to evaluate the predictive ability of automated CT-derived markers, such as visceral and subcutaneous fat, muscle area, bone density, liver fat, and aortic calcification, for diabetes and associated cardiometabolic conditions.
Main Findings: Visceral fat index showed the highest predictive performance for both prevalent and incident diabetes, with an AUC of 0.70 for men and 0.82 for women in cross-sectional analyses. Combining visceral fat, muscle area, liver fat, and aortic calcification improved prediction, yielding a C-index of 0.69 for men and 0.83 for women. Additionally, the study found that these CT markers were effective in identifying metabolic syndrome, fatty liver, coronary artery calcium scores >100, sarcopenia, and osteoporosis, with AUCs ranging from 0.80 to 0.95.
Implications for Practice: Automated CT-derived markers can effectively predict diabetes and multiple cardiometabolic comorbidities, surpassing traditional anthropometric measures. These findings suggest that integrating such automated assessments into routine clinical practice could enhance risk stratification and preventive care, particularly through opportunistic screening during routine CT scans.
Deep Learning Model Noninferior to Radiologists in Detecting Clinically Significant Prostate Cancer at MRI – Radiology
10 Aug, 2024 | 21:31h | UTCStudy Design and Population: This retrospective study evaluated the performance of a deep learning (DL) model for detecting clinically significant prostate cancer (csPCa) using multiparametric MRI (mpMRI) images from 5215 patients (5735 examinations) with a mean age of 66 years. The study included patients who underwent prostate MRI between January 2017 and December 2019 at a single academic institution. The DL model was trained on T2-weighted, diffusion-weighted, and contrast-enhanced MRI sequences, with pathologic diagnosis as the reference standard.
Main Findings: The DL model achieved an area under the receiver operating characteristic curve (AUC) of 0.89 on the internal test set and 0.86 on an external test set, demonstrating noninferiority to radiologists, who had AUCs of 0.89 and 0.84, respectively. Additionally, the combination of the DL model and radiologists improved diagnostic performance (AUC of 0.89). Gradient-weighted class activation maps (Grad-CAMs) effectively localized csPCa lesions, overlapping with true-positive cases in 92% of internal test set and 97% of external test set cases.
Implications for Practice: The DL model showed comparable performance to experienced radiologists in detecting csPCa at MRI, suggesting its potential to assist radiologists in improving diagnostic accuracy and reducing interobserver variability. Future research should focus on integrating the model into clinical workflows and assessing its impact on biopsy targeting.
Cohort Study: Efficacy of first-line color doppler ultrasound in diagnosing giant cell arteritis – Ann Intern Med
25 May, 2024 | 19:39h | UTCThis prospective multicenter study aimed to evaluate the efficacy of using color Doppler ultrasound of the temporal arteries as the first-line diagnostic tool for Giant Cell Arteritis (GCA) in 165 elderly patients with high clinical suspicion of the disease. The study followed participants over two years, comparing ultrasound results with temporal artery biopsy (TAB) and physician-based clinical diagnosis including other imaging tests. Key findings indicate that ultrasound confirmed GCA in 44% of cases, which was higher compared to TAB (17%) and clinical expertise (21%). The study showed that using ultrasound first can avoid the need for further invasive tests like TAB in patients with positive ultrasound results. The limitations of the study include its small sample size, unblinded test results, and the absence of a universally accepted objective diagnostic standard. However, it highlights the potential of ultrasound in the early and non-invasive diagnosis of GCA, potentially reducing the risk of severe complications by expediting treatment initiation.
Reference (link to abstract – $ for full-text):
Meta-Analysis: Efficacy of MRI in prostate cancer screening for reducing unnecessary biopsies
28 Apr, 2024 | 20:13h | UTCThis meta-analysis evaluated the effectiveness of incorporating magnetic resonance imaging (MRI) into prostate cancer screening pathways, compared to prostate-specific antigen (PSA)–only screening strategies. Analyzing data from 80,114 men across 12 studies, the findings demonstrate that MRI-based screening, particularly when using a sequential approach and a PI-RADS score ≥3 cutoff for biopsy, significantly increases the odds of detecting clinically significant prostate cancers (OR, 4.15) while reducing unnecessary biopsies (OR, 0.28) and detection of clinically insignificant cancers (OR, 0.34). Implementing a higher PI-RADS score of ≥4 further decreased the detection of insignificant cancers and biopsies performed, without impacting the detection rate of significant cancers. These results support the integration of MRI into screening programs to enhance diagnostic precision and reduce patient harm.
Reference (link to abstract – $ for full-text):
Pictorial Review | Watch out for the early killers: imaging diagnosis of thoracic trauma
9 Aug, 2023 | 15:02h | UTCWatch Out for the Early Killers: Imaging Diagnosis of Thoracic Trauma – Korean Journal of Radiology
Pictorial Review | Occupational lung diseases: spectrum of common imaging manifestations
9 Aug, 2023 | 14:51h | UTCOccupational Lung Diseases: Spectrum of Common Imaging Manifestations – Korean Journal of Radiology
Determination of “borderline resectable” pancreatic cancer – A global assessment of 30 shades of grey
8 Aug, 2023 | 13:22h | UTC
Commentary on Twitter
What is BORDERLINE respectable?! ?
A global assessment of 30 shades of grey ???
? Interobserver variability among radiologists and surgeons globally is high
?⚖️ Central review of images required for quality control initiativeshttps://t.co/Z2G1cInZ5f pic.twitter.com/mlucwMT5f9
— Giovanni Marchegiani (@Gio_Marchegiani) July 30, 2023
RCT | Mammography screening with AI reduces workload by 44.3% without loss in detection efficacy
4 Aug, 2023 | 12:13h | UTCArtificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (MASAI): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study – The Lancet Oncology (link to abstract – $ for full-text)
News Release: First randomized trial finds AI-supported mammography screening is safe and almost halves radiologist workload – Lancet
Commentaries:
Large Mammography Study Shows Significant Benefits with AI-Aided Screening – Diagnostic Imaging
Study | AI use in lung cancer screening enhances prediction of lung cancer death, CVD death, and all-cause death
1 Aug, 2023 | 14:31h | UTCAI Body Composition in Lung Cancer Screening: Added Value Beyond Lung Cancer Detection – Radiology (free for a limited period)
Commentary: Study: AI Assessment of Chest CT May Predict Multiple Mortality Risks – Diagnostic Imaging
Study | New deep learning model effectively detects type 2 diabetes from chest X-rays
28 Jul, 2023 | 14:15h | UTC
Commentary on Twitter
"Your Chest-ray indicates you may have diabetes"https://t.co/1TEHWvG33D
The latest unexpected outgrowth of deep learning #AI @NatureComms @AyisPyrros and colleagues pic.twitter.com/wZcTT2GCy2— Eric Topol (@EricTopol) July 11, 2023
New Cochrane handbook for systematic reviews of diagnostic test accuracy
25 Jul, 2023 | 14:02h | UTCCochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy – Cochrane Library
News Release: Introducing the new Cochrane Handbook for Diagnostic Test Accuracy – Cochrane Library
Consensus Paper | Lung ultrasound in acute and chronic heart failure
24 Jul, 2023 | 13:06h | UTC
Review | Radiomics-based fertility-sparing treatment in endometrial carcinoma
24 Jul, 2023 | 13:00h | UTC
Review | Infection prevention and control in the medical imaging environment
18 Jul, 2023 | 13:31h | UTC
Review | CT and chest radiography in evaluation of mechanical circulatory support devices for acute heart failure
18 Jul, 2023 | 13:28h | UTC
Guidelines and recommendations for performance of the fetal echocardiogram
17 Jul, 2023 | 13:45h | UTC
Clinical insights into small cell lung cancer: tumor heterogeneity, diagnosis, therapy, and future directions
26 Jun, 2023 | 00:31h | UTC
Scientific Advisory | Expedited CT scanning with iodinated contrast when necessary favored over renal concerns in emergencies
22 Jun, 2023 | 15:19h | UTCRelated:
Radiographic Contrast Media and the Kidney – Clinical Journal of the American Society of Nephrology
Contrast-Associated Acute Kidney Injury – Journal of Clinical Medicine
Imaging features of the postoperative spine: a guide to basic understanding of spine surgical procedures
15 Jun, 2023 | 14:43h | UTC