AIM: development of medical decision support systems for MRI diagnostics of rectal cancer: localization and segmentation of the primary tumor.

PATIENTS AND METHODS: the research included 450 MRI studies of patients with rectal cancer and 450 MRI studies of patients without a tumor lesion of the rectum. All patients with tumors of rectum had histological verification of the malignant process. Data were collected in T2Wcoronal and axial projections (MRI Philips Achieva 1.5 T). Object marking was carried out only for T2W projections, where the area of interest was segmented - rectum, sigmoid colon and tumor. The ITK-Snap program was used to label MRI images. The validated studies and labeling were used to create a machine learning model that demonstrates the capability of the dataset to build medical decision support systems. SegResNet, TransUnet, 3D Unet neural networks were used to create a basic artificial intelligence model. The data set of patients and the direct marking of MRI studies were carried out by doctors of Ryzhikh National Medical Research Center of Coloproctology. The development of the artificial intelligence model, markup validation was carried out by employees of JSC "National Center of Service Integration" and LLC "Medical Screening Systems".

RESULTS: dice similarity coefficient (DSC) of various neural networks were: TransUnet - 0.33, SegResNet - 0.50, 3D Unet - 0.42. The diagnostic efficiency of the SegResNet neural network in detecting rectal tumors with the addition of negative examples and post-processing was: accuracy 77.0%; sensitivity 98.1%; specificity 45.1%; positive predictive value 72.9%; negative predictive value of 94.1%. At this stage, AI has a fairly high sensitivity and accuracy, which indicates a high diagnostic efficiency in terms of visualizing the primary tumor and determining localization in the rectum. However, the specificity of the method is still at an unsatisfactory level (45.1%), which indicates a high percentage of false positive results in healthy patients and does not allow the model to be used as a screening method at this stage of development.

CONCLUSION: the collected dataset of MRI studies and their markup made it possible to obtain an AI model that allows solving the problem of segmenting a rectal tumor and determining its localization. The next stage in the development of AI is to improve its specificity, expand the analyzed parameters, such as the depth of tumor invasion, visualization of metastatic lymph nodes and the status of the resection margin. To further develop the model metric and improve its diagnostic capabilities, we should experiment with training parameters and increase the dataset.

The problem of inflammatory bowel disease (IBD) — ulcerative colitis (UC) and Crohn's disease (CD) has not lost its urgency for several decades. Patients with IBD require long-term, continuous, often lifelong therapy and follow-up. This paper presents the data of patients’ register, worked outin Mechnikov North-Western State Medical University, in the Centre of IBD treatment.
As per the Register, an average time of diagnosis was 2.6 years (30.7 months) — for CD and 1.1 year (12.7 months) — for UC. At the same time, only 36.9% of CD patients versus 72% of UC patients were diagnosed within the first year, with the peak incidence at the age between 18 and 30 years.
Extra-intestinal manifestations are marked in 43.5% of CD patients and in 23.2% of UC patients. Besides, a quarter of them have more than one extra-intestinal symptoms, with bone and joint involvement domination (in 29.2% of CD patients and 18.4% of UC patients).
Epidemiological registers, including IBD registers, form an important database on the incidence, characteristics, regional distribution, and nature of the disease development, which helps to navigate the profile of patients, investigate possible causes and determine risk factors affecting its course.
However, the unified Federal Register will allow us to get a complete picture of patients with IBD in the country.
In addition, maintaining a national register and pharmaco-economical evaluation of various treatment methods will, in our opinion, optimize treatment costs; ensure rational planning and use of budgetary funds.

AIM: to evaluate the clinical efficiency of autologous platelet-rich plasma (PRP) therapy in outpatient treatment of chronic anal fissure combined with anal sphincter spasm.
PATIENTS AND METHODS: a comparative study included 480 patients with chronic anal fissure combined with anal sphincter spasm. Before excision of the anal fissure with a radiosurgical scalpel at the first stage of treatment, standard conservative treatment was performed in 220 patients (group I) and PRP therapy was used in 260 patients (group II) by injecting autologous platelet-rich plasma under the scar tissue of the fissure and into the anal sphincter. The tone of the anal sphincter was evaluated by sphincterometry.
RESULTS: after surgery, the pain was less intensive in group II than in group I patients, increased tone of anal sphincter was eliminated, quality of life and working capacity were restored, and the period of epithelization of the anal canal wound reduced (29.4 ±2.8 days versus 40.6 ±4.5 days). The recurrence rate decreased from 17.7% to 7.3%.
CONCLUSION: the use of PRP therapy in combination with excision of the anal fissure gives good results in 90.4% of patients.

AIM: to improve the results of chronic anal fissure treatment.
PATIENTS AND METHODS: the prospective randomized study included 176 patients divided in two groups. Eighty-eight patients underwent fissure excision in combination with injection of botulinum toxin type A (incobotulinum toxin) into the internal anal sphincter (main group, BTA), and 88 patients underwent anal fissure excision in combination with lateral subcutaneous sphincterotomy (control group, LIS).
RESULTS: on the 30th day after surgery, spasm of internal anal sphincter, according to profilometry, persisted in 14.8% of patients of the main group (BTA) and 22.7% of patients in the control group (LSS) (p = 0.18), and on the 60th day in 20.4% and 14.8% of patients, respectively (p = 0.32). On the 60th day after surgery, the postoperative wound did not epithelialize in 14% of patients in the BTA group and 1% of the LSS group (p = 0.0006). On the 30th day after surgery, complaints of incontinence were noted by 32% of patients in the BTA group and 31% in the LSS group (p = 0.87), on the 60th day — 7% and 11% of patients, respectively (p = 0.29). The intensity of pain after surgery in the compared groups did not differ both after defecation and during the day (p > 0.05). Expansion of the surgery volume increases the chance of developing temporary anal sphincter incontinence (ASI) by 2.44 times on the 30th day of observation (p = 0.01) and by 3 times — on day 60 (p = 0.04). The use of BTA as a method of internal anal sphincter relaxation increases the chance of slowing down the epithelization of the postoperative wound by 13.7 times [p = 0.01], and the expansion of the surgery volume — by 3.47 times [p = 0.03].
CONCLUSION: the use 40 U of botulinum toxin type A after anal fissure excision is not inferior to lateral subcutaneous sphincterotomy in elimination of spasm internal anal sphincter with a comparable incidence of temporary anal sphincter incontinence within 2 months after surgery. Neurotoxin serves as an alternative to sphincterotomy, however, in some cases, it requires the addition of a agent containing human recombinant epidermal growth factor to the postoperative management of patients.

AIM: to evaluate diagnostic capabilities of computed tomography in identifying the destruction of the diverticulum wall in complicated diverticular disease.
PATIENTS AND METHODS: the prospective cohort study included 70 patients (38 female and 32 male median age - 57 ± 13), which underwent elective surgery for complicated diverticular disease. The following assessment criteria for CT were used: signs of diverticulum destruction, thickness of the bowel wall, length of inflammatory changes of colonic wall, length of pericolonic inflammation. The data of preoperative CT were compared with the morphology of removed bowel specimen.
RESULTS: the sensitivity and specificity of CT were 96.8% and 97.4% in the detection of abscesses, 95% and 100% of colonic fistulas, and 100% and 97% pericolonic inflammation, respectively. Based on results of morphological studies of resected colon segment, two groups of patients were identified: with macroperforation (abscesses and fistulas) and microperforation (pericolic inflammatory mass). According to the ROC-analysis, colon wall thickness ≥ 0.7 cm, length of inflammatory changes of colonic wall ≥ 9.2 cm and the length of pericolonic inflammation ≥ 3.1 cm highly likely show microperforation.
CONCLUSION: CT parameters of thickening of colon wall, length of inflammatory changes of colonic wall and the length of pericolonic inflammation seem to be significant for the possibility of predicting the presence of microperforation. New studies with a larger number of clinical cases are required.

AIM: to assess the early results of hybrid laparoscopic endoscopic procedures for colon tumors.
PATIENTS AND METHODS: a pilot “case-control” study included two groups of patients, who underwent surgery for endoscopic irremovable colon adenomas. Hybrid laparo-endoscopic procedures were done in the main group (n = 31), in the control group — laparoscopic resections of the colon (n = 20).
RESULTS: no significant differences obtained in rate of postoperative complications: 9.7% in the main group vs 20.0% of cases in the control (p = 0.41). The postoperative hospital stay in the main group was significantly less than in control group — 5 versus 7 days (p < 0.0001).
CONCLUSION: the hybrid laparoscopic endoscopic surgery does not associate with the increased risk of postoperative complications. Moreover, this procedure decreases postoperative hospital stay. However, a randomized controlled trial is required.

AIM: to work out the algorithm for diagnosis and treatment of non-healing postoperative wounds of the perineum and anal canal.
PATIENTS AND METHODS: the prospective cohort study included 119 people which underwent surgery for chronic anal fissure, hemorrhoids and anal fistula. The main group included 63 patients with long-term non-healing chronic wounds (46-159 days after surgery, mean 106.0 ± 44.8 days). The control group included 56 patients, whose postoperative period was uneventful and whose wounds healed on the 38.0 ± 10.4 days (p = 0.001).The wound healing and possible deviations in its course were assessed in all the patients using clinical, microbiological, cytological, pathomorphological pathophysiological tests, as well as molecular diagnostics (PCR). The main and control groups of the patients were homogenous in the main parameters (age, sex, the nature of surgical treatment), with the exception of the history of the disease. In the patients with a history of non-healing postoperative wounds, the incidence of sexually transmitted infections (STI) and inflammatory diseases of the pelvic organs, possibly caused by STI, was 44.4%, and in the patients of the control group — 10.7%, (p = 0.002).
RESULTS: in all patients of the main group at the time of admission and in 85.7% of the control group on the 30th day after the surgery, the wounds were contaminated with various microorganisms during bacteriological examination. Clinically significant microorganisms were found in 71.4% of the patients in the main group and in 12.5% of the control group (p = 0.0001). Associations of microorganisms were found in 73.0% in the main group and only in 33.9% in the controls (p = 0.01). During PCR in wounds of the perineum and anal canal STI were found in 34.9% in the main group, while in the control — 7.1% (p = 0.003). Histological examination of tissues taken from the area of non-healing wounds revealed papillomavirus infection (koilocytosis) in 11 (17.5%) patients. The patients with non-healing wounds were treated depending on the isolated pathogen and sensitivity to antibiotics, as well as appropriate treatment if an STI was detected. In 6.3% in the main group, the wounds did not heal and a spasm of the internal sphincter was detected. These patients got injection of botulinum toxin type A (BTA) into the internal sphincter (40 U). After 9.4 days after the BTA complete wound healing was noted. A control test (profilometry) on the 7th day after the BTA showed no spasm of the internal sphincter in all cases.
CONCLUSION: healing processes in patients after anal surgery may slow down due to the presence of infectious agents, opportunistic pathogens and STI, which support the inflammatory wound reaction in the postoperative period, as well as due to spasm of the anal sphincter. It is necessary to carry out targeted diagnostics, to prescribe appropriate treatment, and in the presence of anal sphincter spasm, to eliminate it.

The most effective method of pilonidal sinus treatment is surgery, which usually leads to the prolonged healing wounds in the sacrococcygeal area.According to the scientific sources, the use of vacuum-assisted wound therapy positively affects wound healing rate and decreases the postoperative morbidity rate. However, the lack of adequately powered and well-conducted RCTs, which could clearly define the treatment approach and indications, drives the necessity for further studies.

Subepithelial rectal tumors are a group of histologically heterogeneous neoplasms located under the epithelium of the mucosa and have no specific clinical manifestations. Differential diagnosis of these tumors is an urgent problem, since the prognosis and treatment choice depend on the specific type of tumor. The aim of the work was to study the possibilities of the ultrasound method in the diagnosis of subepithelial rectal tumors and to identify signs for each type of tumor. An analysis of the literature data showed that ultrasound as an integral part of complex diagnostics using medical imaging methods (ultrasound, CT, MRI) makes it possible to identify and characterize these tumors, providing valuable information for the treatment.

Impaired motility of the gastrointestinal tract after surgery for colorectal cancer is a serious problem in the early postoperative period for both the patient and the medical staff. The literature review is devoted to the problem of postoperative ileus with an emphasis on the theory of its etiology and pathogenesis. Understanding the mechanism of this pathological condition will make it possible to find ways to prevent it.