Deep learning approach to femoral AVN detection in digital radiography: differentiating patients and pre-collapse stages.

OBJECTIVE: This study aimed to evaluate a new deep-learning model for diagnosing avascular necrosis of the femoral head (AVNFH) by analyzing pelvic anteroposterior digital radiography. METHODS: The study sample included 1167 hips. The radiographs were independently classified into 6 stages by a radiologist using their simultaneous MRIs. After that, the radiographs were given to train and test the deep learning models of the project including SVM and ANFIS layer using the Python programming language and TensorFlow library. In the last step, the test set of hip radiographs was provided to two independent radiologists with different work experiences to compare their diagnosis performance to the deep learning models' performance using the F1 score and Mcnemar test analysis. RESULTS: The performance of SVM for AVNFH detection (AUC = 82.88%) was slightly higher than less experienced radiologists (79.68%) and slightly lower than experienced radiologists (88.4%) without reaching significance (p-value > 0.05). Evaluation of the performance of SVM for pre-collapse AVNFH detection with an AUC of 73.58% showed significantly higher performance than less experienced radiologists (AUC = 60.70%, p-value < 0.001). On the other hand, no significant difference is noted between experienced radiologists and SVM for pre-collapse detection. ANFIS algorithm for AVNFH detection with an AUC of 86.60% showed significantly higher performance than less experienced radiologists (AUC = 79.68%, p-value = 0.04). Although reaching less performance compared to experienced radiologists statistically not significant (AUC = 88.40%, p-value = 0.20). CONCLUSIONS: Our study has shed light on the remarkable capabilities of SVM and ANFIS as diagnostic tools for AVNFH detection in radiography. Their ability to achieve high accuracy with remarkable efficiency makes them promising candidates for early detection and intervention, ultimately contributing to improved patient outcomes.

Predicting the COVID-19 Patients Status Using Chest CT Scan Findings: A Risk Assessment Model Based on Decision Tree Analysis.

BACKGROUND: The role of chest computed tomography (CT) to diagnose coronavirus disease 2019 (COVID-19) is still an open field to be explored. The aim of this study was to apply the decision tree (DT) model to predict critical or non-critical status of patients infected with COVID-19 based on available information on non-contrast CT scans. METHODS: This retrospective study was performed on patients with COVID-19 who underwent chest CT scans. Medical records of 1078 patients with COVID-19 were evaluated. The classification and regression tree (CART) of decision tree model and k-fold cross-validation were used to predict the status of patients using sensitivity, specificity, and area under the curve (AUC) assessments. RESULTS: The subjects comprised of 169 critical cases and 909 non-critical cases. The bilateral distribution and multifocal lung involvement were 165 (97.6%) and 766 (84.3%) in critical patients, respectively. According to the DT model, total opacity score, age, lesion types, and gender were statistically significant predictors for critical outcomes. Moreover, the results showed that the accuracy, sensitivity and specificity of the DT model were 93.3%, 72.8%, and 97.1%, respectively. CONCLUSIONS: The presented algorithm demonstrates the factors affecting health conditions in COVID-19 disease patients. This model has the potential characteristics for clinical applications and can identify high-risk subpopulations that need specific prevention. Further developments including integration of blood biomarkers are underway to increase the performance of the model.

Contrast-enhanced weighted-T1 and FLAIR sequences in MRI of meningeal lesions.

Magnetic resonance imaging (MRI) is widely used in meningeal lesions due to rapid and accurate diagnosis and prevention of serious complications. The aim of the present study was to compare these two sequences after injection of a contrast agent into meningeal lesions. This is a descriptive-analytical study that was performed in 2018-2020 on patients referred to the radiology ward with detection of any meningeal involvements in the MRI images. In addition to T1-W, FLAIR sequence imaging was also performed. Images were initially evaluated by two expert radiologists and a neurologist. The diagnostic values of the sequences were compared. Overall, a total number of 147 patients with meningeal lesions in their brain MRI entered the study. 57.1% of cases (84 patients) had an infectious etiology and 42.9% (63 patients) had a tumoral etiology. T1-W images without contrast were able to diagnose 78 cases of meningitis (92.8% of them), and FLAIR sequences could diagnose 82 patients (97.6% of them). Without contrast injection on MRI, the diagnostic value of T1-W sequence was higher than FLAIR sequence for tumoral lesions (P < 0.01). The enhancement degree of T1-W was higher for tumoral findings (P < 0.01). In contrast, the enhancement degree of the FLAIR sequence was higher for infectious findings, which was also statistically significant (P = 0.015). FLAIR sequences had 92% sensitivity and 85% specificity for diagnosis of brain inflammatory diseases. Similar analysis showed that T1 sequence had 82% sensitivity and 73% specificity for diagnosis of brain inflammatory diseases.