Real-time deep learning-based colorectal polyp localization on clinical video footage achievable with a wide array of hardware configurations.

Background and study aims Several computer-assisted polyp detection systems have been proposed, but they have various limitations, from utilizing outdated neural network architectures to a requirement for multi-graphics processing unit (GPU) processing, to validating on small or non-robust datasets. To address these problems, we developed a system based on a state-of-the-art convolutional neural network architecture able to detect polyps in real time on a single GPU and tested on both public datasets and full clinical examination recordings. Methods The study comprised 165 colonoscopy procedure recordings and 2678 still photos gathered retrospectively. The system was trained on 81,962 polyp frames in total and then tested on footage from 42 colonoscopies and CVC-ClinicDB, CVC-ColonDB, Hyper-Kvasir, and ETIS-Larib public datasets. Clinical videos were evaluated for polyp detection and false-positive rates whereas the public datasets were assessed for F1 score. The system was tested for runtime performance on a wide array of hardware. Results The performance on public datasets varied from an F1 score of 0.727 to 0.942. On full examination videos, it detected 94 % of the polyps found by the endoscopist with a 3 % false-positive rate and identified additional polyps that were missed during initial video assessment. The system's runtime fits within the real-time constraints on all but one of the hardware configurations. Conclusions We have created a polyp detection system with a post-processing pipeline that works in real time on a wide array of hardware. The system does not require extensive computational power, which could help broaden the adaptation of new commercially available systems.

The Analysis of Risk Factors in the Conversion from Laparoscopic to Open Cholecystectomy.

Laparoscopic cholecystectomy is a standard treatment for cholelithiasis. In situations where laparoscopic cholecystectomy is dangerous, a surgeon may be forced to change from laparoscopy to an open procedure. Data from the literature shows that 2 to 15% of laparoscopic cholecystectomies are converted to open surgery during surgery for various reasons. The aim of this study was to identify the risk factors for the conversion of laparoscopic cholecystectomy to open surgery. A retrospective analysis of medical records and operation protocols was performed. The study group consisted of 263 patients who were converted into open surgery during laparoscopic surgery, and 264 randomly selected patients in the control group. Conversion risk factors were assessed using logistic regression analysis that modeled the probability of a certain event as a function of independent factors. Statistically significant factors in the regression model with all explanatory variables were age, emergency treatment, acute cholecystitis, peritoneal adhesions, chronic cholecystitis, and inflammatory infiltration. The use of predictive risk assessments or nomograms can be the most helpful tool for risk stratification in a clinical scenario. With such predictive tools, clinicians can optimize care based on the known risk factors for the conversion, and patients can be better informed about the risks of their surgery.

[Colopleural fistula complicating laparotomy for perforated gastric ulcer]. / Przetoka okrezniczo-oplucnowa po laparotomii z powodu przedziurawionego wrzodu zoladka.

Colopleural fistula is a very rare clinical problem which was described barely in a few articles. Common causes of this kind of fistula are strangulated diaphragm hernias and neoplasms of the splenic flexure of the colon. We report a case of 58 years old male with colopleural fistula. Symptoms of left sided pyo and pneumothorax appeared two weeks after laparotomy for perforated peptic gastric ulcer. Chest tube was inserted and antibiotics was used. The pyothorax was evacuated almost entirely. Left sided recurrent purulent thoracic wall fistulas complicated the latter two and a half year course. Finnaly the reccurence of left sided pyothorax leaded to surgical treatment. During thoracotomy decortication and resection of cirrhotic lover lobe of the left lung was performed. In the postoperative course faecal fluid appeared in the left pleural cavity. The patient was transfer to The Surgical Department where fistula between colon and pleural cavity was confirmed by colonoscopy. During laparotomy fistula between splenic flexure of the colon penetrating through diaphragm was confirmed and excised. The patient was cured. On the basis of reviewed literature we discuss possible pathological mechanisms of creating colopleural fistula, diagnostic workup and treatment. We conclude that colonoscopic examination may be helpful in diagnosis and localization of fistula site when radiological examination fails. Colopleural fistula course may lasts with few symptoms for years.