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.

Background and study aim: Small-bowel tumors account for 1 % - 3 % of all gastrointestinal neoplasms. Recent studies with video capsule endoscopy (VCE) suggest that the frequency of these tumors may be substantially higher than previously reported. The aim of the study was to evaluate the frequency, clinical presentation, diagnostic/therapeutic work-up, and endoscopic appearance of small-bowel tumors in a large population of patients undergoing VCE. Patients and methods: Identification by a questionnaire of patients with VCE findings suggesting small-bowel tumors and histological confirmation of the neoplasm seen in 29 centers of 10 European Countries. Results: Of 5129 patients undergoing VCE, 124 (2.4 %) had small-bowel tumors (112 primary, 12 metastatic). Among these patients, indications for VCE were: obscure gastrointestinal bleeding (108 patients), abdominal pain (9), search for primary neoplasm (6), diarrhea with malabsorption (1). The main primary small-bowel tumor type was gastrointestinal stromal tumor (GIST) (32 %) followed by adenocarcinoma (20 %) and carcinoid (15 %); 66 % of secondary small-bowel tumors were melanomas. Of the tumors, 80.6 % were identified solely on the basis of VCE findings. 55 patients underwent VCE as the third procedure after negative bidirectional endoscopy. The lesions were single in 89.5 % of cases, and multiple in 10.5 %. Retention of the capsule occurred in 9.8 % of patients with small-bowel tumors. After VCE, 54/124 patients underwent 57 other examinations before treatment; in these patients enteroscopy, when performed, showed a high diagnostic yield. Treatment was surgery in 95 % of cases. Conclusions: Our data suggest that VCE detects small-bowel tumors in a small proportion of patients undergoing this examination, but the early use of this tool can shorten the diagnostic work-up and influence the subsequent management of these patients.

The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.

Non-celiac gluten sensitivity (NCGS) is characterized by the onset of symptoms after eating gluten-containing food. We aimed to single out NCGS subjects among subjects with functional gastrointestinal symptoms. Patients were enrolled in a multicenter double-blind placebo-controlled trial with crossover. Symptoms and quality of life were evaluated by means of 10-cm VAS and SF36. Iron parameters, transaminases and C reactive protein (CRP) were evaluated. After a three-week-long gluten-free diet (GFD), responsive patients were randomly assigned to gluten intake (5.6 g/day) or placebo for seven days, followed by crossover. The primary endpoint was the worsening of symptoms (VAS increase ≥3 cm) during gluten ingestion compared to placebo. One hundred and forty patients were enrolled and 134 (17 males, mean age 39.1 ± 11.7 years, BMI 22.4 ± 3.8) completed the first period. A total of 101 subjects (10 males, mean age 39.3 ± 11.0 years, BMI 22.3 ± 4.0) reported a symptomatic improvement (VAS score 2.3 ± 1.2 vs. 6.5 ± 2.2 before and after GFD, p = 0.001). 98 patients underwent the gluten challenge and 28 (all females, mean age 38.9 ± 12.7 years, BMI 22.0 ± 2.9) reported a symptomatic relapse and deterioration of quality of life. No parameters were found to be statistically associated with positivity to the challenge. However, 14 patients responded to the placebo ingestion. Taking into account this finding, about 14% of patients responding to gluten withdrawal showed a symptomatic relapse during the gluten challenge. This group is suspected to have NCGS.

Patients with early-onset colorectal cancer (eoCRC) are managed according to guidelines that are not age-specific. A multidisciplinary international group (DIRECt), composed of 69 experts, was convened to develop the first evidence-based consensus recommendations for eoCRC. After reviewing the published literature, a Delphi methodology was used to draft and respond to clinically relevant questions. Each statement underwent 3 rounds of voting and reached a consensus level of agreement of ≥80%. The DIRECt group produced 31 statements in 7 areas of interest: diagnosis, risk factors, genetics, pathology-oncology, endoscopy, therapy, and supportive care. There was strong consensus that all individuals younger than 50 should undergo CRC risk stratification and prompt symptom assessment. All newly diagnosed eoCRC patients should receive germline genetic testing, ideally before surgery. On the basis of current evidence, endoscopic, surgical, and oncologic treatment of eoCRC should not differ from later-onset CRC, except for individuals with pathogenic or likely pathogenic germline variants. The evidence on chemotherapy is not sufficient to recommend changes to established therapeutic protocols. Fertility preservation and sexual health are important to address in eoCRC survivors. The DIRECt group highlighted areas with knowledge gaps that should be prioritized in future research efforts, including age at first screening for the general population, use of fecal immunochemical tests, chemotherapy, endoscopic therapy, and post-treatment surveillance for eoCRC patients. The DIRECt group produced the first consensus recommendations on eoCRC. All statements should be considered together with the accompanying comments and literature reviews. We highlighted areas where research should be prioritized. These guidelines represent a useful tool for clinicians caring for patients with eoCRC.