Objectives: To compare the diagnostic performance of a newly developed artificial intelligence (AI) algorithm derived from the fusion of convolution neural networks (CNN) versus human observers in the estimation of malignancy risk in pulmonary nodules. Methods: The study population consists of 158 nodules from 158 patients. All nodules (81 benign and 77 malignant) were determined to be malignant or benign by a radiologist based on pathologic assessment and/or follow-up imaging. Two radiologists and an AI platform analyzed the nodules based on the Lung-RADS classification. The two observers also noted the size, location, and morphologic features of the nodules. An intraclass correlation coefficient was calculated for both observers and the AI; ROC curve analysis was performed to determine diagnostic performances. Results: Nodule size, presence of spiculation, and presence of fat were significantly different between the malignant and benign nodules (p < 0.001, for all three). Eighteen (11.3%) nodules were not detected and analyzed by the AI. Observer 1, observer 2, and the AI had an AUC of 0.917 ± 0.023, 0.870 ± 0.033, and 0.790 ± 0.037 in the ROC analysis of malignity probability, respectively. The observers were in almost perfect agreement for localization, nodule size, and lung-RADS classification [κ (95% CI)=0.984 (0.961–1.000), 0.978 (0.970–0.984), and 0.924 (0.878–0.970), respectively]. Conclusion: The performance of the fusion AI algorithm in estimating the risk of malignancy was slightly lower than the performance of the observers. Fusion AI algorithms might be applied in an assisting role, especially for inexperienced radiologists. Advances in knowledge: In this study, we proposed a fusion model using four state-of-art object detectors for lung nodule detection and discrimination. The use of fusion of deep learning neural networks might be used in a supportive role for radiologists when interpreting lung nodule discrimination.

The purpose of this study was to investigate the relation between pancreatic steatosis and visceral adiposity. Furthermore, the study sought to explore the association between pancreatic steatosis, pancreas volume, hepatic steatosis, age, and sex in adults without prior history of pancreatic disease. The research also served to define a cut-off value of visceral fat tissue area (VFA) predicting fatty pancreas. CT scans of 98 living-liver donor transplant patients without prior history of pancreatic disease were evaluated for the presence of fatty pancreas. Pancreas volume, VFA, subcutaneous-total FA, VFA/TFA ratios of the patients with and without fatty pancreas were quantified with a semi-automated model on CT. Coexistence of hepatic steatosis was also recorded. VFA, TFA and VFA/TFA were significantly greater in the fatty group (p<0.001, p<0.001, p<0.001; respectively), and pancreatic steatosis was moderately correlated with VFA, VFA/TFA and TFA with the highest correlation coefficient with VFA (r=-0.715, r=-0.605, r=-0.573, respectively; p<0.001 for all). A cut-off value of VFA ≥ 107.2 cm2 estimates pancreatic steatosis with a sensitivity and specificity of 90% (95% CI=77-96%) and 87.9% (95% CI=77%-94%), respectively. Pancreas volume was higher in the fatty-group with a mean value of 86.5±17.3 mL (range; 58-119.2 mL, p=0.097). In multiple logistic regression analyses, pancreatic steatosis was significantly associated with VFA and the male sex (OR=58.2, 95% CI=12.2-277.1, p<0.001; OR=11.4, 95% CI=2.1-63.4, p<0.001; respectively). 77.5% of the fatty pancreas subjects had co-existing hepatic steatosis. Pancreatic steatosis is related to higher VFA, VFA/TFA and hepatic steatosis. A cut-off value of VFA ≥ 107.2 cm2 may predict pancreatic steatosis.

Purpose: The aim of this study is to evaluate the diagnostic contribution of diffusion-weighted magnetic resonance imaging (MRI) and computed tomography (CT) to distinguish extramural venous invasion (EMVI) in rectal adenocarcinoma. Materials and Methods: Fifty-eight patients who had been diagnosed with rectal adenocarcinoma (30 patients with EMVI and 28 patients without EMVI) were enrolled in the study. Apparent diffusion coefficient (ADC) values of the tumour and the EMVI (+) vein, the lengths of the tumours were measured on MRI. The diameters of the superior rectal vein (SRV)-inferior mesenteric vein (IMV) and distant metastatic spread were evaluated on CT. The ability of these findings to detect EMVI was assessed using receiver operating characteristic (ROC) analysis. Pathology was accepted as the reference test for EMVI. Results: Mean diameters of the SRV (4.9 ± 0.9 mm vs 3.7 ± 0.8 mm) and IMV (6.9 ± 0.8 mm vs 5.4 ± 0.9 mm) were significantly larger ( P < .001) and tumour ADC values were significantly lower (0.926 ± 0.281 × 10⁻³ mm²/s vs 1.026 ± 0.246 × 10⁻³ mm²/s; P = .032) in EMVI (+) patients. Diameters of 3.95 mm for the SRV (area under the curve [AUC] ± standard error [SE]: 0.851 ± 0.051, P < .001, sensitivity: 93.3%, specificity: 67.9%) and 5.95 mm for the IMV (AUC ± SE: 0.893 ± 0.040, P < .001, sensitivity: 93.3%, specificity: 71.4%) and an ADC value of 0.929 × 10⁻³ mm²/s (AUC ± SE: 0.664 ± 0.072, P = .032 sensitivity: 76.7%, specificity: 57.1%) were found to be cutoff values, determined by ROC analysis, for detection of EMVI. Distant metastases were significantly more prevalent in EMVI (+) patients ( P < .001). Conclusion: The measurement of ADC values and SRV-IMV diameters seems to have contribution for diagnosis of EMVI in rectal adenocarcinoma. EMVI (+) patients appear to have higher risks of distant metastases at diagnosis.

Objective: The purpose of this study was to assess the diagnostic performance of multiphasic computed tomography (CT) in the discrimination of metastatic lymph nodes (LNs) of papillary thyroid cancer by using quantitative parameters. Methods: This study enrolled 272 pathologically proven metastatic and benign LNs. Multiphasic CT was utilized by using nonenhanced, arterial (25-second delay), and venous (80-second delay) phases. Mean tissue attenuation values (MAVs) of metastatic and benign LNs were measured, and normalized MAV (common carotid artery and paraspinal muscle) and wash-in and wash-out percentages were also calculated. Results: The arterial phase showed the highest diagnostic performance in differentiation (area under the curve ± standard error, 0.97 ± 0.02; 95% confidence interval, 0.94–1.0; P < 0.001). Cutoff values for MAVs, normalized MAVs, and wash-in and wash-out percentages to predict metastatic LNs were calculated as 109 HU, 0.33, 1.93, 122.5, and −5.6 (sensitivity: 93.4%, 93.3%, 90.4%, 94.1%, and 97.8%, and specificity: 99.3%, 90.4%, 98.5%, 92.6%, and 99.3%, respectively). Conclusions: Early-phase enhanced CT and the use of quantitative parameters derived from multiphasic CT improve the detection of cervical lymph node metastasis from papillary thyroid cancer.

Acute pulmonary thromboembolism (PTE) is a common cause of cardiovascular mortality. Right ventricular (RV) dysfunction is the most important cause of mortality. Computed Tomography Pulmonary Angiography (CTPA) can detect right ventricular enlargement which is an indicator of RV dysfunction at the time of diagnosis. This study aimed to determine the parameters indicating RV dysfunction in CTPA and correlation of early mortality findings. In this retrospective study, electronic files of patients diagnosed PTE with CTPA between January 2012 and December 2017 were evaluated. Measurements of heart chambers, IVC reflux, and IVS morphology were calculated. In-hospital mortality of the patients after acute PTE diagnosis was evaluated. There were 206 eligible patients. Among the evaluated radiological parameters, right atrium (RA) size (p= 0.002), PA size (p= 0.003), Ao size (p= 0.006), and the presence of IVC reflux (p= 0.001) were associated with mortality. No significant relationship was found between RV/LV ≥1 and mortality (p= 0.908). All patients with PTE-related mortality had RV/LV ratio ≥1 in CTPA and had IVC reflux. Patients with an RV/LV ratio of ≥1 had statistically significantly higher troponin levels (p= 0.004) and IVC reflux (p= 0.025) compared to patients with an RV/LV ratio of <1. In conclusion, RV/LV ratio should be evaluated together with cardiac biomarkers to define mortality risk.