Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge.

Polyps are well-known cancer precursors identified by colonoscopy. However, variability in their size, appearance, and location makes the detection of polyps challenging. Moreover, colonoscopy surveillance and removal of polyps are highly operator-dependent procedures and occur in a highly complex organ topology. There exists a high missed detection rate and incomplete removal of colonic polyps. To assist in clinical procedures and reduce missed rates, automated methods for detecting and segmenting polyps using machine learning have been achieved in past years. However, the major drawback in most of these methods is their ability to generalise to out-of-sample unseen datasets from different centres, populations, modalities, and acquisition systems. To test this hypothesis rigorously, we, together with expert gastroenterologists, curated a multi-centre and multi-population dataset acquired from six different colonoscopy systems and challenged the computational expert teams to develop robust automated detection and segmentation methods in a crowd-sourcing Endoscopic computer vision challenge. This work put forward rigorous generalisability tests and assesses the usability of devised deep learning methods in dynamic and actual clinical colonoscopy procedures. We analyse the results of four top performing teams for the detection task and five top performing teams for the segmentation task. Our analyses demonstrate that the top-ranking teams concentrated mainly on accuracy over the real-time performance required for clinical applicability. We further dissect the devised methods and provide an experiment-based hypothesis that reveals the need for improved generalisability to tackle diversity present in multi-centre datasets and routine clinical procedures.

A multi-centre polyp detection and segmentation dataset for generalisability assessment.

Polyps in the colon are widely known cancer precursors identified by colonoscopy. Whilst most polyps are benign, the polyp's number, size and surface structure are linked to the risk of colon cancer. Several methods have been developed to automate polyp detection and segmentation. However, the main issue is that they are not tested rigorously on a large multicentre purpose-built dataset, one reason being the lack of a comprehensive public dataset. As a result, the developed methods may not generalise to different population datasets. To this extent, we have curated a dataset from six unique centres incorporating more than 300 patients. The dataset includes both single frame and sequence data with 3762 annotated polyp labels with precise delineation of polyp boundaries verified by six senior gastroenterologists. To our knowledge, this is the most comprehensive detection and pixel-level segmentation dataset (referred to as PolypGen) curated by a team of computational scientists and expert gastroenterologists. The paper provides insight into data construction and annotation strategies, quality assurance, and technical validation.

Low FODMAP diet in Egyptian patients with Crohn's disease in remission phase with functional gastrointestinal symptoms.

BACKGROUND AND AIM: Despite being in remission, functional gastrointestinal disease (FGID) in Crohn's disease (CD) patients can reduce their quality of life. The Egyptian daily diet contains a high amount of FODMAP (Fermentable Oligosaccharides, Disaccharides, Monosaccharides, And Polyols). As the low FODMAP diet has been proven to be effective in irritable bowel syndrome worldwide, it was reasonable to take a step further and begin to study the effect of low FODMAP in Egyptian CD patients with FGID. The outcomes were assessed in terms of improvement in symptoms and hence the quality of life, and the factors that led to this improvement were also recorded. METHODS: In total, 100 CD patients with FGID in the remission stage who were already on a low-fiber diet (± lactose-free diet) were selected to follow the low FODMAP diet. A structured interview was performed after 3 months with a number of scored-scale questionnaires comparing symptoms before and after the diet and the impact on quality of life. Evaluation of the adherence, satisfaction, palatability, and affordability of the diet was performed. Different demographic data were also evaluated in correspondence with improvements in the quality of life. RESULTS: The mean score of FGID improvement was 38.45 ± 21.56%. The quality of life was significantly improved; 90% of female patients versus 49.4% males had a better quality of life. The households (not working) as well as those with morning jobs (6 hours) reported an increase in quality of life. Although the Egyptian low FODMAP diet was expensive (in terms of gluten-free wheat), 67% were adherent to it (18.16 ± 6.85). CONCLUSION: As a first step in Egypt, the low FODMAP diet was effective in improving the quality of life of CD patients with FGID.