István Rácz

Background/Aims: We have been developing artificial intelligence based polyp histology prediction (AIPHP) method to classify Narrow Band Imaging (NBI) magnifying colonoscopy images to predict the hyperplastic or neoplastic histology of polyps. Our aim was to analyze the accuracy of AIPHP and narrow-band imaging international colorectal endoscopic (NICE) classification based histology predictions and also to compare the results of the two methods.Methods: We studied 373 colorectal polyp samples taken by polypectomy from 279 patients. The documented NBI still images were analyzed by the AIPHP method and by the NICE classification parallel. The AIPHP software was created by machine learning method. The software measures five geometrical and color features on the endoscopic image.Results: The accuracy of AIPHP was 86.6% (323/373) in total of polyps. We compared the AIPHP accuracy results for diminutive and non-diminutive polyps (82.1% vs. 92.2%; p=0.0032). The accuracy of the hyperplastic histology prediction was significantly better by NICE compared to AIPHP method both in the diminutive polyps (n=207) (95.2% vs. 82.1%) (p<0.001) and also in all evaluated polyps (n=373) (97.1% vs. 86.6%) (p<0.001)Conclusions: Our artificial intelligence based polyp histology prediction software could predict histology with high accuracy only in the large size polyp subgroup.

Background and Aims: Acute non-variceal upper gastrointestinal bleeding (UGIB) is associated with significant morbidity and mortality. Our aim was to evaluate the incidence, management, risk factors and outcomes of acute non-variceal UGIB in a population-based study from Hungary. Methods: The present prospective one–year study involved six major community hospitals in Western Hungary covering a population of 1,263,365 persons between January 1 and December 31, 2016. Data collection included demographics, comorbidities endoscopic management, Glasgow-Blatchford score (GBS), Rockall score (RS) transfusion requirements, length of hospital stay and mortality. Results: 688 cases of acute non-variceal UGIB were included with an incidence rate of 54.4 (95%CI: 50.5-58.6) per 100,000 per year. Endoscopy was performed within 12 hours in 71.8%. 5.3% of the patients required surgical treatment and the overall mortality was 13.5%. Weekend presentation was associated with increased transfusion requirements (p=0.047), surgery (p=0.016) and mortality (p=0.021). Presentation with hemodynamic instability or presence of comorbidities was associated with transfusion (p5points). Conclusions: Incidence rates of acute non-variceal UGIB in Western Hungary are in line with international trends. Longer pre-hospital time, comorbidities, hemodynamic instability, weekend presentation, treatment with anticoagulants or non-steroidal anti-inflammatory drugs was associated with worse outcomes.

Classification of polyps in the human colorectum is a hot topic of gastroenterology. The current advancements in devices of endoscopy made it possible to product high resolution images of polyps with different light filters, e.g. with narrow band imaging (NBI) system. There exists several human classification methods that helps the doctor to decide whether a specific polyp is risky (i.e. it can be turn into cancer) or not. To overcome the limits of human classification skill, a digital image processing method was developed by the authors of this paper. This paper summarizes the preprocessing method of this software, which is not a trivial task, because during the inspection of a patient, the diagnostician has limited control of light and geometry. Therefore the surface of the polyp is not uniformly illuminated, and prominent flares could appear on the images quite often. These circumstances makes it hard to detect the surface patterns precisely. In this paper a lot of variants for this preprocessing task is presented. The best of them appears to reproduce the geometrical parameters of the patterns in 1--5\% relative error which is enough for the classification method. The proposed method can be applied to another problems, where the precise measurement of patterns in highly variable illuminating conditions is needed.

Introduction: Early endoscopic diagnosis and endoscopic therapy are very important in cases of acute gastrointestinal bleeding. Hemospray is an inorganic powder with hemostatic properties recently proposed for the treatment of acute gastrointestinal bleeding. Aim: The aim of the authors was to report the first Hungarian experience obtained with Hemospray in patients with acute gastrointestinal bleeding. Method: During a 14-month period 10 acute upper gastrointestinal bleeder patients were treated endoscopically with Hemospray in 11 settings. In 5 patients previous endoscopic hemostatic methods failed and in the remaining 5 patients Hemospray was administrated as a first-line therapy. Results: Primary hemostasis was achieved in 9 of the 10 patients treated with Hemospray. Two patients died during hospitalization (uncontrolled arterial bleeding in one patient and hepatic encephalopathy in the other one patient). Primary hemostasis and hemodynamic stability were achieved in each of the 4 patients who had thrombopenia. Conclusions: Hemospray as a rescue therapy may ensure primary hemostasis in severe acute gastrointestinal bleeding even in cases with thrombopenia. Orv. Hetil., 2015, 156(13), 528–531.

AIM: To investigate the effect of mesalazine granules on small intestinal injury induced by naproxen using capsule endoscopy (CE).

Although capsule retention is a known complication of small bowel capsule endoscopy, initial studies with colon capsule endoscopy (CCE) have not reported any capsule retention or sticking neither in the small bowel nor in the colon. We report a complication of CCE when the stuck colon capsule was passed through the malignant colon stricture and removed by the aid of a flexible colonoscope. During CCE in a 76-year-old iron deficiency anemia patient the real-time viewing system indicated the colon capsule to be stuck in a malignant ascending colon stricture for more than two hours. With the aim to avoid complete capsule retention, immediate colonoscopy was performed. The stuck capsule was caught by a polypectomy snare, passed through the tumor stricture and finally removed from the large bowel. The current case describes the usefulness of the real-time viewing system. Similar situations may occur during the forthcoming spread of CCE and the present case is an example of how to manage the potentially risky stuck colon capsule condition.