Thorax computed tomography (CTX) guided ground truth annotation of CHEST radiographs (CXR) for improved classification and detection of COVID-19.

Several data sets have been collected and various artificial intelligence models have been developed for COVID-19 classification and detection from both chest radiography (CXR) and thorax computed tomography (CTX) images. However, the pitfalls and shortcomings of these systems significantly limit their clinical use. In this respect, improving the weaknesses of advanced models can be very effective besides developing new ones. The inability to diagnose ground-glass opacities by conventional CXR has limited the use of this modality in the diagnostic work-up of COVID-19. In our study, we investigated whether we could increase the diagnostic efficiency by collecting a novel CXR data set, which contains pneumonic regions that are not visible to the experts and can only be annotated under CTX guidance. We develop an ensemble methodology of well-established deep CXR models for this new data set and develop a machine learning-based non-maximum suppression strategy to boost the performance for challenging CXR images. CTX and CXR images of 379 patients who applied to our hospital with suspected COVID-19 were evaluated with consensus by seven radiologists. Among these, CXR images of 161 patients who also have had a CTX examination on the same day or until the day before or after and whose CTX findings are compatible with COVID-19 pneumonia, are selected for annotating. CTX images are arranged in the main section passing through the anterior, middle, and posterior according to the sagittal plane with the reformed maximum intensity projection (MIP) method in the coronal plane. Based on the analysis of coronal MIP reconstructed CTX images, the regions corresponding to the pneumonia foci are annotated manually in CXR images. Radiologically classified posterior to anterior (PA) CXR of 218 patients with negative thorax CTX imaging were classified as COVID-19 pneumonia negative group. Accordingly, we have collected a new data set using anonymized CXR (JPEG) and CT (DICOM) images, where the PA CXRs contain pneumonic regions that are hidden or not easily recognized and annotated under CTX guidance. The reference finding was the presence of pneumonic infiltration consistent with COVID-19 on chest CTX examination. COVID-Net, a specially designed convolutional neural network, was used to detect cases of COVID-19 among CXRs. Diagnostic performances were evaluated by ROC analysis by applying six COVID-Net variants (COVIDNet-CXR3-A, -B, -C/COVIDNet-CXR4-A, -B, -C) to the defined data set and combining these models in various ways via ensemble strategies. Finally, a convex optimization strategy is carried out to find the outperforming weighted ensemble of individual models. The mean age of 161 patients with pneumonia was 49.31 ± 15.12, and the median age was 48 years. The mean age of 218 patients without signs of pneumonia in thorax CTX examination was 40.04 ± 14.46, and the median was 38. When working with different combinations of COVID-Net's six variants, the area under the curve (AUC) using the ensemble COVID-Net CXR 4A-4B-3C was .78, sensitivity 67%, specificity 95%; COVID-Net CXR 4a-3b-3c was .79, sensitivity 69% and specificity 94%. When diverse and complementary COVID-Net models are used together through an ensemble, it has been determined that the AUC values are close to other studies, and the specificity is significantly higher than other studies in the literature.

The Evaluation of Adropin and Autotaxin as Potential Markers of Endothelial Dysfunction in Preeclampsia.

Endothelial dysfunction (ED) plays a prominent role in the pathogenesis of preeclampsia (PE). There is a need for non-invasive methods to assess endothelial function in preeclamptic patients. In the present study, adropin, autotaxin (ATX), and lysophosphatidic acid (LPA) were evaluated as indicators of ED. Patients diagnosed with PE and healthy pregnant women (n = 42 for each group) were compared. After measuring flow-mediated dilation (FMD), the participants were stratified as ED (+) or ED (-) based on a cut-off value of 6.5%. The PE patients were divided as early/late onset PE and severe/mild PE. Adropin, ATX, and LPA levels were measured, and their relevance to ED was evaluated. Student t, Mann-Whitney U, or ANOVA tests were used for statistics, as appropriate. Adropin levels were diminished in the ED (+) group, whereas ATX and LPA levels were increased. The decrease in adropin levels was more pronounced in severe PE, showing a positive correlation with the FMD. In the logistic regression model, adropin was the only parameter that was an independent variable for the FMD test (P < .001). Adropin measurements in serum may be of value for disease follow-up in patients with PE.

Quantitative evaluation of hepatic steatosis using attenuation imaging in a pediatric population: a prospective study.

BACKGROUND: Obesity and fatty-liver disease are increasingly common in children. Hepatic steatosis is becoming the most common cause of chronic liver disease during childhood. There is a need for noninvasive imaging methods that are easily accessible, safe and do not require sedation in the diagnosis and follow-up of the disease. OBJECTIVE: In this study, the diagnostic role of ultrasound attenuation imaging (ATI) in the detection and staging of fatty liver in the pediatric age group was investigated using the magnetic resonance imaging (MRI)-proton density fat fraction as the reference. MATERIALS AND METHODS: A total of 140 children with both ATI and MRI constituted the study group. Fatty liver was classified as mild (S1, defined as ≥ 5% steatosis), moderate (S2, defined as ≥ 10% steatosis), or severe (S3, defined as ≥ 20% steatosis) according to MRI-proton density fat fraction values. MRI studies were performed on the same 1.5-tesla (T) MR device without sedation and contrast agent. Ultrasound examinations were performed independently by two radiology residents blinded to the MRI data. RESULTS: While no steatosis was detected in half of the cases, S1 steatosis was found in 31 patients (22.1%), S2 in 29 patients (20.7%) and S3 in 10 patients (7.1%). A strong correlation was found between attenuation coefficient and MRI-proton density fat fraction values (r = 0.88, 95% CI 0.84-0.92; P < 0.001). The area under the receiver operating characteristic curve values of ATI were calculated as 0.944 for S > 0, 0.976 for S > 1 and 0.970 for S > 2, based on 0.65, 0.74 and 0.91 dB/cm/MHz cut-off values, respectively. The intraclass correlation coefficient values for the inter-observer agreement and test-retest reproducibility were calculated as 0.90 and 0.91, respectively. CONCLUSION: Ultrasound attenuation imaging is a promising noninvasive method for the quantitative evaluation of fatty liver disease.