Search

Background Inflammatory bowel disease (IBD) is verified on the basis of complex assessment of clinical, laboratory, endoscopic and morphological data. However, due to the lack of a ‘golden’ standard and similarity of the clinical picture, it usually takes more than 1 year to diagnose ulcerative colitis (UC) and more than 2 years for Crohn`s disease (CD). The aim of the study is to optimize the existing methods in diagnosis of IBD with an application of an artificial neural network (ANN). Methods 216 patients with verified IBD (163 – UC, 53 – CD of large bowel) and 34 patients without endoscopic findings underwent colonoscopy in the Peter the Great Clinic of Mechnikov North-Western State Medical University (Saint-Petersburg, Russia). During the endoscopic examination 856 images were obtained: 268 images of “normal mucosa”, 194 ones of CD of large bowel and 394 ones of UC. The study included images of mild, moderate and severe activity of IBD. Mayo endoscopic score was used to assess endoscopic activity of UC. For CD the scoring scales were not provided, the activity of the disease was based on the length of the affected segment, presence of erosions, ulcers and complications such as strictures, fistulae and stenosis. All images were captured in high-resolution with the same endoscope (Olympus) and stored in a jpeg format. Poor-quality images resulting from blurs, defocus and poor air insufflation were excluded. We also created the ANN using the Neural Network Toolbox application from the MATLAB application package. The ANN consisted of 2 models: the first one was multilayer perceptron which determined a presence of pathology, the second was convolutional neural network which differentiated the types of IBD (UC or CD). Results All the endoscopic images were downloaded to the created ANN. It was trained 3 times due to the decrease of its accuracy. The average accuracy of the developed model in differentiation of pathology was 77%. This result could be associated with an insufficient number of CD images or ANN training on continuous data set of images with UC and CD features without clustering them to particular patient. Conclusion We conclude that the developed ANN shows moderate accuracy in recognition of different forms of IBD. This study has a limitation as the images were taken only with endoscope Olympus. Enlarged sample size and inclusion of morphologic images are needed in order to improve the accuracy of ANN.

Background IBD are immunomediated diseases that usually manifest at an early age, require lifelong pathogenetic therapy and significantly reduce the quality of life of a patient. Methods Since February 2017, the ‘North-West register of IBD patients’ has installed data of 1130 patients with an introduced diagnosis of UC or CD: 41.3% of them are patients with a diagnosis of CD and 58.7%—with a diagnosis of UC. Results Among patients with IBD the majority had mild (33.4%) and moderate activity (34%), a quarter was in remission and 7.65%—expressed activity. A population researches study using the University of Manitoba’s IBD epidemiology database (UMIBDED) reported that 6.2% of IBD patients had at least one extraintestinal manifestation, and 0.3% had several. The extraintestinal manifestations were observed in 43.4% of patients; meanwhile, 25% of them revealed mostly than one extraintestinal manifestation. System manifestations were more often registered in CD than in UC. The most frequent extraintestinal manifestations were signs of involvement of skeletal and muscular system. On the first place, it is peripheral arthropathy (73.6%), sacroiliitis (8.8%), ankylosing spondyloarthritis (8.8%), entezitis (10.3%) rheumatoid arthritis (1.5%), dactylitis (1.5%) were less frequent. Generally, articulate manifestations were noted by 17.5% of all included patients. In CD and UC, extra-intestinal manifestations were more often common in patients with a moderate attack (in 75.6 % and 51.6% of cases). In CD, extra-intestinal manifestations were more often frequent in patients with moderate attack −50.8%, in patients in remission there numbered to 32.8%, in severe attack-14.8%, in mild-1.6%. In UC, extra-intestinal manifestations were observed in severe attack in 2.6%, in moderate attack 35.9%, in mild attack 41%, in patients in remission 20.5%. Conclusion Among patients with IBD, extraintestinal manifestations, among which joint lesions prevail, are detected in 43.4% of the examined persons. The trend is noted to reduce the number of patients with severe attacks of the disease and extraintestinal manifestations, that can be related with improving the quality of diagnosis, reduction of terms of diagnosing and developing new methods of treatment for IBD. Peripheral arthropathy predominate among the extra-intestinal manifestations. We found no correlation between the severity of IBD and the presence of extra-intestinal manifestations. The spectrum of extra-intestinal manifestations includes more than 20 manifestations (diseases), which requires skills and experience in their diagnosis, as well as joint management of such patients by specialists of various profiles.

Background Due to the lack of a ‘gold standard’ in the diagnosis of IBD the differential diagnosis between ulcerative colitis and Crohn′s disease can be very difficult. Verification of diagnosis of IBD takes a long time in majority of cases. Methods We have created an artificial neural network (ANN) of the multilayer perceptron type using the Neural Network Toolbox application from the MATLAB application package. Three types of images were used to train the ANN: the norm of the endoscopic picture of the colon, the endoscopic pictures of UC and CD. The first stage is the training of an artificial neural network to distinguish the presence or absence of pathology (29 images of the ‘normal colon’, 14 images of the CD, and 15 - UC). The second stage was to train the ANN to recognise the various forms of IBD. The network was trained on an array of 124 images (62 images of each class of pathologies). Each image was previously converted to the grayscale mode and then into a matrix of pixels. A vector with the number of elements equal to the size of the image was fed to the input of the perceptron. Results To solve the task of identifying the pathology a perceptron was built with 32,2784 input neurons, 10 hidden neurons and 2 output neurons which represent the conclusion that the image belongs to one of the two classes: norm or pathology. To solve the problem of differentiating CD and UC a perceptron was created with 364500 input neurons (this value was determined by the image resolution) and 2 output neurons representing the conclusion that the image belongs to one of the two classes: UC or CD. The best result in differentiation of pathology was shown by the ANN of MP 364500 type: 364500-20-2: 2, which total accuracy of recognition was 96,8%. The average accuracy of the developed model was 92.6%. However, in the control sample, the accuracy was 84.2%. This fact indicates that the model should be taught on more images. In addition to the ‘accuracy’ criterion, the ‘completeness’ parameter was used to evaluate the system. ‘Completeness’ for recognition of the image of the norm was the highest and equal to 1, for UC the criterion of ‘completeness’ was 0.89. The lowest ‘completeness’ was obtained when recognising the image of the CD (0.67). Conclusion ANN type MP 364500: 364500-20-2: 2 has shown the best results in the set targets. Efficiency in pathology recognition was 96.8%. The efficiency of the created ANN in solving the problem of recognition of different forms of IBD (UC/CD) can be described by the following parameters: specificity (Sp) −78.2%, sensitivity (Se) - 93.1%, accuracy (Ac) - 85,7%. The obtained ANN can be used to solve the problems of classification of endoscopic images of the intestine for the presence of IBD and for differential diagnosis.

Background Untimely diagnosis increases the number of severe forms of IBD, which enlarges the possibility of life-threatening complications, extraintestinal presentations, and the patient’s need for surgical treatment. Methods We analysed the data of 1130 patients with an established diagnosis of UC or CD. The dynamics of the timing of diagnosis of IBD, the nature of the disease, the frequency of occurrence of intestinal complications, extraintestinal presentations were evaluated. Results The maximum frequency of start of both UC and CD falls on the young age of patients - from 19 to 38 years. The duration of symptoms before diagnosis is established is 2.3 years (27.4 months) for CD, 1.1 years (12.1 months) for UC. 81.8% of patients with UC are diagnosed no more than 4 years, but in 10.9% of patients this interval was 4–9 years; in 3.6%, 9–13 years; in 1.9%, 13–18 years, and in another 1.8%, more than 20 years. In CD 59.5% of patients fall into the diagnosis interval up to 4 years, in 27.4% this period takes from 4 to 9 years, in 7%—10–15 years, and in 6% more than 6 years. At the age of 18–25 years severe course of IBD is observed in 12% of patients, at the age of 26–30 years—in 18%, 31–40 years—in 9%. Older people are more likely to experience mild IBD, and the percentage of severe and moderate forms is 4% and 29%, respectively, after 60, and less than 0.5% and 19.5%, respectively, after 70 years. Extraintestinal presentations were observed in 43.4% of patients, with 25% of them having more than one of them. In patients with CD, the development of complications in the first 4 years of the disease was noted in 62%, in UC—in 58.9%. In patients with intestinal complications, the diagnosis period was 2.9 years, without them—2.4 years. However, in patients with a history of surgical treatment of IBD, the diagnosis period was less than 1 year. 69, 3% of revealed patients with a history of needing one or more hospitalisations associated with IBD, and 15.8% underwent surgery for IBD. Conclusion Based on the data obtained, it can be concluded that the main part of complications occurs in the first few years after the onset of the disease. With late diagnosis, the probability of developing not only intestinal complications, but also extra-intestinal presentations significantly increase, which reflects a more severe form of the disease. The shorter time of diagnosis of IBD in patients who need surgical treatment is explained by more pronounced symptoms that require urgent medical care. However, the proportion of IBD with severe and moderate form is greater in young age groups, and as the ‘growing up’ groups - the number of patients with mild IBD begins to prevail.