[Epicardial fat Tissue Volumetry: Comparison of Semi-Automatic Measurement and the Machine Learning Algorithm].

Aim        To compare assessments of epicardial adipose tissue (EAT) volumes obtained with a semi-automatic, physician-performed analysis and an automatic analysis using a machine-learning algorithm by data of low-dose (LDCT) and standard computed tomography (CT) of chest organs.Material and methods        This analytical, retrospective, transversal study randomly included 100 patients from a database of a united radiological informational service (URIS). The patients underwent LDCT as a part of the project "Low-dose chest computed tomography as a screening method for detection of lung cancer and other diseases of chest organs" (n=50) and chest CT according to a standard protocol (n=50) in outpatient clinics of Moscow. Each image was read by two radiologists on a Syngo. via VB20 workstation. In addition, each image was evaluated with a developed machine-learning algorithm, which provides a completely automatic measurement of EAT.Results   Comparison of EAT volumes obtained with chest LDCT and CT showed highly consistent results both for the expert-performed semi-automatic analyses (correlation coefficient >98 %) and between the expert layout and the machine-learning algorithm (correlation coefficient >95 %). Time of performing segmentation and volumetry on one image with the machine-learning algorithm was not longer than 40 sec, which was 30 times faster than the quantitative analysis performed by an expert and potentially facilitated quantification of the EAT volume in the clinical conditions.Conclusion            The proposed method of automatic volumetry will expedite the analysis of EAT for predicting the risk of ischemic heart disease.

Reproducibility of CT texture features of pancreatic neuroendocrine neoplasms.

PURPOSE: To evaluate the reproducibility of textural features of pancreatic neuroendocrine neoplasms (PNENs), obtained under various CT-scanning conditions. METHODS AND MATERIALS: We included 12 patients with PNENs and 2 contrast enhanced CT (CECT): 1) from our center according to standard CT-protocol; 2) from another institution. Two radiologists independently segmented the entire neoplasm volume using a 3D region of interest by LIFEx application on the arterial phase and then copied it to the other phases. 52 texture features were calculated for each phase. As a criterion for the segmentation consistency, a value of neoplasm volume was compared using the Bland-Altman method. The Kendall concordance coefficient was calculated to assess the texture features reproducibility in three scenarios: 1) different radiologists, same CECT; 2) same radiologist, different CECT; 3) different radiologists, different CECT. RESULTS: For the scenario 1 the neoplasm volumes (except one large PNEN) were found within two standard deviations; this indicates high consistency of the segmentation. For the first scenario, Kendall's coefficient exceeded a threshold of 0.7 for all 52 features for all CT phases. For the second and third scenario, the concordance coefficient exceeded a threshold of 0.7 in 38, 28, 42, 45 and in 36, 25, 36, 44 features for the native, arterial, venous and delayed phases, respectively. CONCLUSION: The highest reproducibility was found in the first scenario compared to the second and third: 100 % vs. 74 % and 67 %. Reproducible texture features can be reliably used to assess the PNENs structure.