No abstract

Objective: to develop a diagnostic model that includes CT and radiomic features for the differential diagnosis of pancreatic neuroendocrine tumors (PNETs) G1 and G2 and pancreatic renal cell carcinoma (RCC) metastases.Material and Methods. 78 patients with 79 hypervascular PNETs and 17 patients with 24 pancreatic RCC metastases who underwent pancreatic resection and histological verification were selected in the study. All the patients underwent preoperative contrast enhanced CT (CECT). We assessed tumor attenuation, composition (cystic/solid), homogeneity (homogeneous/heterogeneous), calcification and presence of the main pancreatic duct (MPD) dilation. We calculated lesion-to-parenchyma contrast (LPC), relative tumor enhancement ratio (RTE) and extracted 52 texture features for arterial phase of CECT. Qualitative and texture features were compared between PNETs and pancreatic RCC metastasis. The selection of predictors for the logistic model was carried out in 2 successive stages: 1) selection of predictors based on one-factor logistic models, the selection criterion was p < 0.2; 2) selection of predictors using L2 regularization (LASSO regression after standardization of independent variables). The selected predictors were included in a logistic regression model without interactions, the coefficients of which were estimated using the maximum likelihood method with a penalty of 0.8.Results. There was no difference in composition, homogeneity (homogeneous/heterogeneous) and presence of the MPD dilation between groups. We did not find calcification in pancreatic RCC metastasis, in contrast to the PNETs (9% contained calcifications). After selection, the LCR, CONVENTIONAL_HUmin, GLCM_Correlation, NGLDM_Coarseness were included in the final diagnostic model, which showed a sensitivity and specificity of 95.8%; 62% in the prediction of pancreatic RCC metastases.Conclusion. The diagnostic model developed on the basis of texture and CT-features has high sensitivity (95.8%) with moderate specificity (62%), which allows it to be used in complex diagnostic cases to determine the patient's treatment tactics.

Timely instrumental diagnosis of diseases of the hepatopancreatoduodenal region, especially of an oncological nature, is the key to successful treatment, improving prognosis and improving the quality of life of patients. At the moment, the possibilities of radiation diagnostics make it possible to identify and evaluate the nature of the blood supply to the neoplasm, its prevalence, cellularity, and in the case of MRI studies with hepatospecific contrast agents, also evaluate the functional activity of liver cells. Nevertheless, the steady development of methods for treating cancer patients, in particular, chemotherapy, and a personalized approach to the choice of patient management tactics require a detailed assessment of the morphological types of certain neoplasms. The need for dynamic monitoring of the results of treatment, monitoring of accidentally detected, potentially malignant neoplasms, and the development of screening programs determine the steady increase in the number of CT and MR examinations performed annually in the world and in our country. These factors have led to the application of texture analysis or radiomics and machine learning algorithms. At the same time, such techniques as radiography, ultrasound, CT and MRI with extracellular and tissue-specific contrast enhancement, and MRI-DWI do not lose their significance. The ongoing research allows the Federal State Budgetary Institution National Medical Research Center of Surgery named after A.V. Vishnevsky of the Ministry of Health of Russia to implement the concept of preoperative non-invasive diagnosis and differential diagnosis of surgical and oncological diseases of the hepatopancreatoduodenal region and apply the knowledge gained in planning surgical treatment. Implementation of the problem of post-processor data processing of radiation diagnostics of surgical and oncological diseases of the hepatopancreatoduodenal region using radiomics and AI technologies is important and extremely relevant for modern medicine.

A study of the international literature on texture analysis was performed, and the reported data was compared to the findings of radiomics studies performed by the specialists of our institute. The relevant papers were searched using a combination of the following search terms: “radiomics”, “radiology”, “texture analysis”, “perspectives”, and “clinical implementation”. The search was limited to papers published in English within the last 5 years, which essentially focused on liver and pancreas disorders. Due to the publication of new data on a fairly daily basis, the topic has not lost its relevance. The vast majority of authors confirm that radiomics can be efficiently used during diagnosis, treatment planning, and patient monitoring. However, consensus on the implementation of radiomics has not been reached yet, thereby delaying its introduction into clinical practice. The data collected in our institution reports that the clinical application of texture analysis methods may be very promising.

Research goal. Comparative characteristics of the dynamics of CT semiotics and biochemical parameters of two groups of patients: with positive RT-PCR and with triple negative RT-PCR. Reflection of the results by comparing them with the data already available in the literature.The aim of the study is to compare the dynamics of CT semiotics and biochemical parameters of blood tests in two groups of patients: with positive RT-PCR and with triple negative RT-PCR. We also reflect the results by comparing them with the data already available in the literature.Materials and methods. We have performed a retrospective analysis of CT images of 66 patients: group I (n1 = 33) consists of patients who had three- time negative RT-PCR (nasopharyngeal swab for SARS-CoV-2 RNA) during hospitalization, and group II (n2 = 33) includes patients with triple positive RT-PCR. An important selection criterion is the presence of three CT examinations (primary, 1st CT and two dynamic examinations – 2nd CT and 3rd CT) and at least two results of biochemistry (C-reactive protein (CRP), fibrinogen, prothrombin time, procalcitonin) performed in a single time interval of ± 5 days from 1st CT, upon admission, and ± 5 days from 3st CT. A total of 198 CT examinations of the lungs were analyzed (3 examinations per patient).Results. The average age of patients in the first group was 58 ± 14.4 years, in the second – 64.9 ± 15.7 years. The number of days from the moment of illness to the primary CT scan 6.21 ± 3.74 in group I, 7.0 (5.0–8.0) in group II, until the 2nd CT scan – 12.5 ± 4, 87 and 12.0 (10.0–15.0), before the 3rd CT scan – 22.0 (19.0–26.0) and 22.0 (16.0–26.0), respectively.In both groups, all 66 patients (100%), the primary study identified the double-sided ground-glass opacity symptom and 36 of 66 (55%) patients showed consolidation of the lung tissue. Later on, a first follow-up CT defined GGO not in all the cases: it was presented in 22 of 33 (67%) patients with negative RT-PCR (group I) and in 28 of 33 (85%) patients with the positive one (group II). The percentage of studies showing consolidation increased significantly: up to 30 of 33 (91%) patients in group I, and up to 32 of 33 (97%) patients in group II. For the first time, radiological symptoms of “involutional changes” appeared: in 17 (52%) patients of the first group and in 5 (15%) patients of the second one. On second follow-up CT, GGO and consolidations were detected less often than on previous CT: in 1 and 27 patients of group I (3% and 82%, respectively) and in 6 and 30 patients of group II (18% and 91%, respectively), although the consolidation symptom still prevailed significantly . The peak of “involutional changes” occurred on last CT: 31 (94%) and 25 (76%) patients of groups I and II, respectively.So, in the groups studied, the dynamics of changes in lung CT were almost equal.After analyzing the biochemistry parameters, we found out that CRP significantly decreased in 93% of patients (p < 0.001) in group I; in group II, there was a statistically significant decrease in the values of C-reactive protein in 81% of patients (p = 0.005). With an increase in CT severity of coronavirus infection by one degree, an increase in CRP by 41.8 mg/ml should be expected. In group I, a statistically significant (p = 0.001) decrease in fibrinogen was recorded in 77% of patients; and a similar dynamic of this indicator was observed in group II: fibrinogen values decreased in 66% of patients (p = 0.002).Such parameters as procalcitonin and prothrombin time did not significantly change during inpatient treatment of the patients of the studied groups (p = 0.879 and p = 0.135), which may indicate that it is inappropriate to use these parameters in assessing dynamics of patients with a similar course of the disease. When comparing the outcomes of the studied groups, there was a statistically significant higher mortality in group II – 30.3%, in group I – 21.2% (p = 0.043).Conclusion. According to our data, a course of the disease does not significantly differ in the groups of patients with positive RT-PCR and three-time negative RT-PCR. A negative RT-PCR analysis may be associated with an individual peculiarity of a patient such as a low viral load of SARS-CoV-2 in the upper respiratory tract. Therefore, with repeated negative results on the RNA of the virus in the oro- and nasopharynx, one should take into account the clinic, the X-ray picture and biochemical indicators in dynamics and not be afraid to make a diagnosis of COVID-19.