RESUMEN
OBJECTIVES: The brain and spinal cord, constituting the central nervous system (CNS), could be impacted by an inflammatory disease known as multiple sclerosis (MS). The convolutional neural networks (CNN), a machine learning method, can detect lesions early by learning patterns on brain magnetic resonance image (MRI). We performed this study to investigate the diagnostic performance of CNN based MRI in the identification, classification, and segmentation of MS lesions. METHODS: PubMed, Web of Science, Embase, the Cochrane Library, CINAHL, and Google Scholar were used to retrieve papers reporting the use of CNN based MRI in MS diagnosis. The accuracy, the specificity, the sensitivity, and the Dice Similarity Coefficient (DSC) were evaluated in this study. RESULTS: In total, 2174 studies were identified and only 15 articles met the inclusion criteria. The 2D-3D CNN presented a high accuracy (98.81, 95% CI: 98.50-99.13), sensitivity (98.76, 95% CI: 98.42-99.10), and specificity (98.67, 95% CI: 98.22-99.12) in the identification of MS lesions. Regarding classification, the overall accuracy rate was significantly high (91.38, 95% CI: 83.23-99.54). A DSC rate of 63.78 (95% CI: 58.29-69.27) showed that 2D-3D CNN-based MRI performed highly in the segmentation of MS lesions. Sensitivity analysis showed that the results are consistent, indicating that this study is robust. CONCLUSION: This metanalysis revealed that 2D-3D CNN based MRI is an automated system that has high diagnostic performance and can promptly and effectively predict the disease.
Asunto(s)
Aprendizaje Profundo , Imagen por Resonancia Magnética , Esclerosis Múltiple , Esclerosis Múltiple/diagnóstico por imagen , Humanos , Imagen por Resonancia Magnética/métodos , Encéfalo/diagnóstico por imagen , Encéfalo/patología , Sensibilidad y EspecificidadRESUMEN
RATIONALE AND OBJECTIVES: The rate of complications and risk of local recurrence following percutaneous radiofrequency ablation (RFA) and microwave ablation (MWA) for liver tumors varies significantly between investigations. This meta-analysis aimed to assess complication rates and risk of local recurrence after percutaneous RFA and MWA. MATERIALS AND METHODS: PubMed, Medline, Web of Science, the Cochrane Library, Embase, Google Scholar, and CINAHL were systematically searched from database inception until August 2022 to retrieve articles reporting the complication rates and risk of recurrence after percutaneous RFA and MWA for the treatment of liver tumors. Pooled odds ratios (OR) with 95% confidence intervals (CI) were calculated and displayed by forest plots. To measure heterogeneity, Cochran Q and I2 statistics were also applied. Egger's test and funnel plots were also performed to assess any potential publication bias. Additionally, subgroup analysis was done to investigate the source of heterogeneity. RESULTS: 26 studies including 2026 and 1974 patients for RFA and MWA, respectively, were included. The rate of minor complications was significantly higher after MWA compared to RFA, yielding an overall OR of 0.688 (95% CI: 0.549-0.862, P = 0.001). Similarly, the rate of major complications was significantly higher after MWA than RFA (P = 0.012), yielding an overall OR of 0.639 (95% CI: 0.450-0.907). No significant difference was found between RFA and MWA in terms of local recurrence after ablation (P > 0.05). In addition, there was no statistical evidence of publication bias. CONCLUSION: When most factors are considered equally, percutaneous RFA and MWA can be considered safe modalities for the treatment of liver tumors, with RFA superior in terms of the incidence of minor and major complications.
Asunto(s)
Carcinoma Hepatocelular , Ablación por Catéter , Neoplasias Hepáticas , Ablación por Radiofrecuencia , Humanos , Carcinoma Hepatocelular/terapia , Microondas/uso terapéutico , Resultado del Tratamiento , Neoplasias Hepáticas/terapia , Ablación por Radiofrecuencia/efectos adversos , Ablación por Catéter/efectos adversos , Estudios RetrospectivosRESUMEN
Background A simplification of the Liver Imaging Reporting and Data System (LI-RADS) version 2018 (v2018), revised LI-RADS (rLI-RADS), has been proposed for imaging-based diagnosis of hepatocellular carcinoma (HCC). Single-site data suggest that rLI-RADS category 5 (rLR-5) improves sensitivity while maintaining positive predictive value (PPV) of the LI-RADS v2018 category 5 (LR-5), which indicates definite HCC. Purpose To compare the diagnostic performance of LI-RADS v2018 and rLI-RADS in a multicenter data set of patients at risk for HCC by performing an individual patient data meta-analysis. Materials and Methods Multiple databases were searched for studies published from January 2014 to January 2022 that evaluated the diagnostic performance of any version of LI-RADS at CT or MRI for diagnosing HCC. An individual patient data meta-analysis method was applied to observations from the identified studies. Quality Assessment of Diagnostic Accuracy Studies version 2 was applied to determine study risk of bias. Observations were categorized according to major features and either LI-RADS v2018 or rLI-RADS assignments. Diagnostic accuracies of category 5 for each system were calculated using generalized linear mixed models and compared using the likelihood ratio test for sensitivity and the Wald test for PPV. Results Twenty-four studies, including 3840 patients and 4727 observations, were analyzed. The median observation size was 19 mm (IQR, 11-30 mm). rLR-5 showed higher sensitivity compared with LR-5 (70.6% [95% CI: 60.7, 78.9] vs 61.3% [95% CI: 45.9, 74.7]; P < .001), with similar PPV (90.7% vs 92.3%; P = .55). In studies with low risk of bias (n = 4; 1031 observations), rLR-5 also achieved a higher sensitivity than LR-5 (72.3% [95% CI: 63.9, 80.1] vs 66.9% [95% CI: 58.2, 74.5]; P = .02), with similar PPV (83.1% vs 88.7%; P = .47). Conclusion rLR-5 achieved a higher sensitivity for identifying HCC than LR-5 while maintaining a comparable PPV at 90% or more, matching the results presented in the original rLI-RADS study. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Sirlin and Chernyak in this issue.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/patología , Neoplasias Hepáticas/patología , Estudios Retrospectivos , Imagen por Resonancia Magnética/métodos , Medios de Contraste , Sensibilidad y Especificidad , Estudios Multicéntricos como AsuntoRESUMEN
BACKGROUND: Liver abscesses differ in their aetiology, location, and number. Image-guided percutaneous drainage techniques are the currently used management for liver abscesses. We conducted our study to compare the clinical safety and efficacy of percutaneous needle aspiration (PNA) to percutaneous catheter drainage (PCD). METHODS: A systematic review of major reference databases was undertaken in February 2022 for randomized controlled trials (RCTs) that compare PNA to PCD in treating liver abscess patients. The quality of the included trials was assessed using the Cochrane tool. Statistical meta-analysis was conducted using RevMan and open meta-analyst software. RESULTS: Fifteen RCTs were included in this review, with 1676 patients enrolled. The overall quality of the included trials was moderate, with most domains of unclear risk. PCD was superior to PNA in the success rate (RR = 1.23; 95% CI [1.12, 1.36], P < 0.00001), time for achieving 50% reduction of cavity size (MD = -2.32; 95% CI [-3.07, -1.57], P < 0.00001), and time for clinical improvement (MD = -1.92; 95% CI [-2.55, -1.28], P < 0.00001). The two modalities did not differ in the days of hospital stay, duration of IV antibiotics, and time needed for total or subtotal reduction of cavity size (P = 0.36, P = 0.06 and P = 0.40, respectively). High heterogeneity levels were detected. Regarding major complications, the two modalities were equally safe (P = 0.39). CONCLUSION: PCD has a higher success rate and results in a faster 50% reduction in the abscess cavity size and clinical improvement. The two modalities are equally safe.
Asunto(s)
Drenaje , Absceso Hepático , Humanos , Drenaje/métodos , Succión , Absceso Hepático/cirugía , Biopsia con Aguja , CatéteresRESUMEN
OBJECTIVES: To evaluate the risk of developing eye lens opacities and cataracts among physicians and healthcare workers occupationally exposed to radiation. METHODS: Our literature search captured articles published in Embase, Web of Science, PubMed, Cochrane Library, Cumulative Index to Nursing and Allied Health Literature, and Google Scholar databases until September 2021. Then, we retrieved articles reporting cataracts and eye lens opacities induced by radiation exposure among healthcare professionals. The outcomes of interest were cataracts, nuclear opacity, cortical opacity, posterior subcapsular opacity, and any lens opacity. RESULTS: Of the 4123 articles identified, 15 studies met the inclusion criteria. Healthcare workers exposed to radiation had a significantly greater risk of posterior subcapsular cataracts (PSCs), cataracts, and any lens opacities than those of the non-exposed participants (p<0.05). The cortical opacity was not significantly different between the exposed and non-exposed participants (p>0.05). Radiation was not determined to be a risk factor for nuclear opacity as it was significantly greater in the control group than the exposed participants. Subgroup analysis revealed that nurses had the highest risk for PSCs (risk ratio = 4.00), followed by interventional cardiologists (risk ratio = 3.85). CONCLUSION: The risk of posterior subcapsular opacities and cataracts is significantly higher in healthcare workers with occupational radiation exposure than in non-exposed workers, highlighting the necessity to enhance and promote the wearing of protective measures with high safety levels.
Asunto(s)
Catarata , Cristalino , Médicos , Traumatismos por Radiación , Catarata/epidemiología , Catarata/etiología , Personal de Salud , Humanos , Traumatismos por Radiación/epidemiología , Traumatismos por Radiación/etiologíaRESUMEN
Objectives: The primary purpose of this study was to assess and report the perceived negative impact of long duty hours on education and personal well-being among medical trainees in the diagnostic radiology residency training program in Saudi Arabia. Methods: This cross-sectional study used a questionnaire (sent by email) with eight indicators related to the education and well-being of radiology residents in Saudi Arabia during the academic year 2019-2020. Participants were given a five-point Likert response format for each indicator. The relative importance index (RII) was calculated to rank the different indicators. Results: Our of 337 residents, 116 diagnostic radiology trainees completed the survey, with a response rate of 34.4%. A total of 102 (87.9%) indicated their preference for 16-hour shifts instead of the currently implemented 24-hour duty system. Using the RII, three items related to the post-duty day ranked at the top of the list. The negative impact on sleep rhythm during the post-call day ranked first (mean 4.23 ± 1.02, RII 0.84), followed by the impact on social life, family activities, and exercise during the post-call day (mean 4.09 ± 1.06, RII 0.81). The third highest ranking factor was missing academic activities on the post-call day (mean 3.91 ± 1.15, RII 0.78). There was no relationship between negative perception and gender (P > 0.05). Conclusion: The 24-hour duty system had a negative impact on radiology residents' education and personal well-being, especially for items related to the post-call day. Reforming duty hours should be considered to promote residents' well-being.
RESUMEN
RATIONALE AND OBJECTIVES: To assess the magnitude and determinants of computer vision syndrome (CVS) among radiologists in Saudi Arabia using a reliable and validated survey instrument. MATERIALS AND METHODS: This nationwide cross-sectional web-based survey took place in April 2021 and included all radiologists and radiology residents residing practicing in Saudi Arabia. We used the reliable and validated CVS questionnaire. Univariate and multivariate analyses were carried out using nonparametric methods. The CVS score was correlated with different demographic- and health-related variables. The Mann-Whitney U test and Kruskal-Wallis test were used to determine if there was a statistically significant difference between subgroups. RESULTS: The survey was completed by 416 participants. The prevalence of CVS was 65.4% (95% CI: 60.8-70.0). The median CVS score was 7.5 (interquartile range: 4.0; 12.0). Mild CVS was observed in 188 participants (69.1%), moderate CVS was observed in 69 (25.4%), and severe CVS was observed in 15 (5.5%). The most common symptoms perceived by participants were headache (72.1%), dryness (70.7%), burning (63.7%), blurred vision (56.3%), and increased sensitivity to light (55.5%). Multinomial regression analysis suggested that female sex (p < 0.001), work as a general radiologist (p = 0.05), and the use of eyeglasses (p = 0.001) were significant predictors of CVS. CONCLUSION: The prevalence of CVS among radiologists in our study was high. Local and international societies need to establish and implement legislative and preventive measures to ensure the safety and ocular and visual health of radiologists.
Asunto(s)
Computadores , Radiólogos , Estudios Transversales , Femenino , Humanos , Arabia Saudita/epidemiología , SíndromeRESUMEN
In neuro-oncology, magnetic resonance imaging (MRI) is a critically important, non-invasive radiologic assessment technique for brain tumor diagnosis, especially glioma. Deep learning improves MRI image characterization and interpretation through the utilization of raw imaging data and provides unprecedented enhancement of images and representation for detection and classification through deep neural networks. This systematic review and quality appraisal method aim to summarize deep learning approaches used in neuro-oncology imaging to aid healthcare professionals. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, a total of 20 low-risk studies on the established use of deep learning models to identify glioma genetic mutations and grading were selected, based on a Quality Assessment of Diagnostic Accuracy Studies 2 score of ≥9. The included studies provided the deep learning models used alongside their outcome measures, the number of patients, and the molecular markers for brain glioma classification. In 19 studies, the researchers determined that the deep learning model improved the clinical outcome and treatment protocol in patients with a brain tumor. In five studies, the authors determined the sensitivity of the deep learning model used, and in four studies, the authors determined the specificity of the models. Convolutional neural network models were used in 16 studies. In eight studies, the researchers examined glioma grading by using different deep learning models compared with other models. In this review, we found that deep learning models significantly improve the diagnostic and classification accuracy of brain tumors, particularly gliomas without the need for invasive methods. Most studies have presented validated results and can be used in clinical practice to improve patient care and prognosis.
RESUMEN
BACKGROUND: Abdominal lymphangiomatosis is a rare benign condition accounting for less than 1% of all the cases of lymphangiomatosis. Management usually involves radical surgical excision; however, depending upon the extent of involvement, patient condition, and absence of complications, conservative management can be also considered. CASE SUMMARY: We present the case of a 32-year-old male who presented with short onset abdominal pain and melena. Physical examination findings were within normal limits, except for left lower abdominal tenderness. Upper gastrointestinal endoscopy was within normal limits. Abdominal and pelvic ultrasound and computed tomography (CT) scan revealed numerous, variably-sized cystic lesions within the abdominal cavity, exclusively and extensively affecting the small bowel mesentery with sparing of the retroperitoneum. The diagnosis was confirmed by CT and cytological examination. Radical surgical excision was technically impossible in this patient because of the extensive involvement of the mesentery; therefore, the patient was managed conservatively. CONCLUSION: Extensive and exclusive small bowel mesentery involvement in abdominal lymphangiomatosis is rare. Imaging modalities play an important role in establishing the diagnosis and conservative management can be considered when surgery is technically impossible.
RESUMEN
OBJECTIVES: To understand and report the perceived impact of the COVID-19 pandemic on radiology residents in Saudi Arabia with respect to their education, clinical activities, and personal well-being. METHODS: The survey questionnaire was designed by a team of experts based on a review of the literature and was distributed electronically through the Saudi Commission for Health Specialties to residents registered in all radiology residency training programs in Saudi Arabia during the academic year 2019 to 2020. Categorical variables were presented as counts and percentage. Numerical variables were presented as mean and standard deviation if normally distributed. Chi-square testing was used to compare categorical variables with the perceived impact of the COVID-19 pandemic. Spearman correlation was used to correlate numerical variables at the level of significance p-value < 0.05. RESULTS: A total of 109 residents completed the online survey during the study period, with a response rate of 32.2% (109/337). The mean age was 27.3 years (standard deviation, 1.86). The majority of respondents (71.5%, 78/109) reported either a severe or moderate negative impact on educational activities. Also, the majority (73.4%, 80/109) reported either a minimal or moderate negative impact on clinical activities. Residents training in the western province perceived a statistically higher negative impact on educational activities compared to their peers in other regions (pâ¯=â¯0.01). Residents in their second year of residency training perceived a statistically higher negative impact on their participation in clinical activities (pâ¯=â¯0.014). Less than half of the respondents (45.9%, 50/109) reported that they were redeployed to work in another department. The majority (80%, 40/50) reported a negative impact on their well-being. CONCLUSION: The majority of radiology residents in Saudi Arabia reported a negative impact of the COVID-19 pandemic on their education, clinical activities, and personal well-being. Our study also identified and explored some of the innovative solutions and strategies implemented by the training programs and the SCFHS to mitigate the negative effects on trainees.