[Texture analysis of 3D models for the prediction of the grade of clear cell renal cell carcinoma of the kidney (pilot study)].

AIM: To evaluate the possibilities of textural analysis of 3D models in differentiating the degree of nuclear dysplasia of the clear cell renal cell carcinoma (ccRCC). MATERIALS AND METHODS: The specimens after surgical treatment of 190 patients with ccRCC were analyzed. In all cases, nephron-sparing surgery (NSS) was performed through laparoscopic access. The clinical characteristics were evaluated, including age, gender, tumor localization (side, surface and segments), absolute tumor volume, Charlson comorbidity index, body mass index, nephrometry scores (RENAL, PADOVA, C-index). Patients were divided into 2 groups. In group 1, there were 119 patients with the ccRCC of Grade 1 or 2, while group 2 consisted of 71 patients with ccRCC of Grade 3 and 4. All patients underwent 3D virtual planning of procedure using the 3D modeling program "Amira". At the first stage, two experienced radiologists performed manual segmentation of 3D models of kidney parenchyma tumors. At the second stage, the tumor shape was analyzed with a mathematical calculation of three indicators and more than 300 textural features of statistics of types 1-2 were extracted. Further, an intellectual analysis was carried out. For the evaluation of tumor grade according to Furman system, the classification problem was solved using the machine learning algorithm Stochastic Gradient Descent and cross-validation k=5. RESULTS: The accuracy of classification for the two groups of Grade 1 or 2 and Grade 3 or 4 on the F1 metric was 72.2. To build the model, the following parameters were selected: the absolute tumor volume, the Charlson comorbidity index, "Energy", the first quartile and the second decile of the pixel intensity distribution. CONCLUSION: The texture analysis of 3D models for the prediction of Fuhrman grade in ccRCC demonstrated satisfactory quality for two groups of Grade 1 or 2 and Grade 3 or 4 nuclear dysplasia.

[Prospects for early detection of keratoconus based on systems built for computer-assisted diagnostics of structural changes in the cornea]. / Perspektivy rannego vyyavleniya keratokonusa na osnove postroeniya sistem mashinnoi diagnostiki strukturnykh izmenenii rogovitsy.

The article is devoted to the problem of diagnosing subclinical keratoconus (KK). The need to identify early signs of KK is primarily associated with the potential for the development of iatrogenic keratoectasia in cases of underdiagnosis of the disease when determining the conditions for laser keratorefractive surgery involving a decrease in the thickness of the cornea. Today generally accepted algorithms for early computer-assisted diagnosis of KK are mainly based on the analysis of various morphometric parameters of the cornea, reflecting changes in its shape and thickness induced by structural abnormalities. Direct detection of structural changes in the cornea characteristic of early KK requires the use of high-tech imaging methods that are not always applicable in everyday clinical practice. The promising approach proposed in this study is based on the fact that a digital image of a corneal «slice¼ obtained using serial analyzers such as the Scheimpflug camera widely used in clinical practice provides indirect information about the structure of the epithelial layer, the local thickening of which takes place in the initial stages KK. It is this criterion that underlies the proposed system of computer-assisted diagnosis of KK. The carried out studies have shown the high sensitivity of this algorithm, and its specificity can be increased by involving the known diagnostic indicators of KK.

[Use of intelligent analysis in urology].

The main methods of intellectual analysis (IA) used in modern medicine are described in the review. The main areas for IA application in the healthcare are diagnostics, treatment, prognosis of the course and efficiency of treatment in various diseases. The IA is based on mathematical methods and algorithms. The basic concepts of IA along with examples of its use in urological practice are presented in the review.

[Analysis of the learning curve in laparoscopic partial nephrectomy in patients with localized renal parenchymal lesions depending on the nephrometric score].

AIM: to analyze the learning curve of surgeons while performing laparoscopic partial nephrectomy in patients with localized renal parenchymal lesions by calculating the MIC (negative surgical margin, ischemia, and complications) index depending on tumor complexity according to the R.E.N.A.L. and PADUA nephrometric scores. MATERIALS AND METHODS: the retrospective study included the results of laparoscopic partial nephrectomies in 320 patients with localized renal parenchymal lesions. The procedures were carried out by four surgeons from the Institute of Urology and Human Reproductive Health of FGAOU VO I.M. Sechenov First Moscow State Medical University, Moscow, Russia (EC-1; ESH-4; EB-7; ME-13) from January 2014 to June 2019. At baseline, all operators had experience of performing at least 30 laparoscopic interventions. In addition to the standard preoperative examination, a 3D virtual planning was carried out using the Amira 3D modeling program. In all cases, the nephrometric assessment of complexity was performed according to the R.E.N.A.L. and PADUA scores. The learning curve was assessed based on the results of operations based on the MIC index. All surgical interventions were divided into eras. In the era, 40 consecutive procedures for each operator were evaluated. Acquired skills were assessed over two eras. RESULTS: The average age of patients, of which 191 (59.7%) were men, was 54.4+/-11.37 years. The average body mass index was 28.55+/-3.85 kg/m2, the absolute volume of kidney lesions was 26.72+/-43.72 cm3, the average Charlson comorbidity index was 1.46+/-1.29, the average R.E.N.A.L. and PADUA scores were 6.38+/-1.75 and 7.92+/-1.51, respectively, the average duration of procedure was 150.36+/-50.18 min, the average blood loss was 227.94+/-280.22 ml, the average time thermal ischemia was 13.28+/-7.82 min. Postoperative complications were seen in 36 (11.2%) cases, of which grade III and more according to Clavien-Dindo developed in 8 patients (2.5%). A positive surgical margin was found in 4 (1.2%) patients. The overall MIC index was achieved in 243 (75.9%) cases; in era 1 it was seen in 71.9% cases in comparison with 80% in era 2. With the 1st degree of complexity (152 (47.5%) patients), MIC was achieved in 80.9% of cases, compared to 76.6% and 56.8% in patients with 2nd degree of complexity (n=124, 38.8%) and 3rd degree of complexity (n=44, 13.8%), respectively. Rate of MIC achievement in eras 1 and 2 for different surgeons were as following: 65% and 72.5%, 75 and 80%, 87.5 and 85% and 60 and 82.5%, for operator 1, 4, 7 and 13, respectively. Age, tumor complexity, R.E.N.A.L. score and PADUA score were the most significant parameters for determining MIC, identified on the basis of the criterion of equality of group means of discrete analysis. CONCLUSION: In all surgeons, the MIC index increased with the accumulation of experience in performing laparoscopic partial nephrectomy, but was lower with an increased degree of complexity of procedures. The minimum number of laparoscopic partial nephrectomies required to achieve an MIC more or equal 70% should be at least 40.

[The construction of the three-dimensional model of the damaged bone tissue based on its roentgenogram]. / Postroenie trekhmernoi modeli povrezhdeniia kostnoi tkani po rentgenogramme.

The objective of the present work was to develop the method for the visualization of the shape of the bone surface in the region of its traumatic damage based on the results of the analysis of a single X-ray image for the solution of the problems facing forensic medical expertise and traumatology. The three-dimensional models of the fractures of the long tubular bones constructed with the use of the visualization technique were shown to adequately reproduce the morphological picture of the injury. It allowed to enhance the potential of the forensic medical analysis and the accuracy of the diagnostic methods employed for the purposes of forensic medical expertise.