Confocal laser endomicroscopy for the differential diagnosis of ulcerative colitis and Crohn’s disease: a pilot study

ABSTRACT Introduction: Endoscopic evaluation, particularly the macroscopic mucosal and histological results of ileocolic biopsies, is essential for the management of inflammatory bowel disease. Endoscopic appearance is not always sufficient to differentiate Crohn’s disease and ulcerative colitis, but there are some characteristics that favor one or another diagnosis. Both diseases have an increased incidence of colorectal carcinoma; so, surveillance colonoscopy is important for detecting early neoplastic lesions. Objective: To update the importance of endoscopy in the evaluation, diagnosis and prognosis of inflammatory bowel disease. Method: Search was done in the scientific literature of the TRIP database, chosen from clinical questions (PICO) with the following descriptors: “inflammatory bowel disease”, “endoscopy/colonoscopy”, “Crohn’s disease”, “ulcerative colitis” and “diagnosis/treatment”. Results: Endoscopic investigation in patients with chronic colitis is quite accurate for the differential diagnosis between ulcerative colitis and Crohn’s disease. Endoscopy is indicated for ulcerative colitis during severe crisis due to its prognostic value. Another accepted indication for endoscopy in inflammatory bowel disease is its use in the screening for dysplastic lesion. Conclusion: Ileocolonoscopy allows an accurate diagnosis of Crohn’s disease or ulcerative colitis in up to 90% of cases. The healing of the mucosa assessed by endoscopy after treatments despite not being consensus is still the gold-standard in the evaluation of remission of the disease. Colonoscopy is essential for long-term cancer surveillance and in the future the implementation of Confocal Laser Endomicroscopy seems to be very promising in assessing the initial dysplasia.

Download Full-text

Prediction of clinical outcome in Crohn's disease with confocal laser endomicroscopy: a prospective, observational, follow-up study

Zeitschrift für Gastroenterologie ◽

10.1055/s-0034-1386254 ◽

2014 ◽

Vol 52 (08) ◽

Author(s):

GE Tontini ◽

J Mudter ◽

M Vieth ◽

R Atreya ◽

C Günther ◽

...

Keyword(s):

Crohn’S Disease ◽

Crohn's Disease ◽

Clinical Outcome ◽

Confocal Laser Endomicroscopy ◽

Confocal Laser ◽

Follow Up Study

Download Full-text

Creatine Supplementation for Patients with Inflammatory Bowl Diseases: A Scientific Rationale for a Clinical Trial

Nutrients ◽

10.3390/nu13051429 ◽

2021 ◽

Vol 13 (5) ◽

pp. 1429

Author(s):

Theo Wallimann ◽

Caroline H. T. Hall ◽

Sean P. Colgan ◽

Louise E. Glover

Keyword(s):

Ulcerative Colitis ◽

Clinical Trial ◽

Crohn’S Disease ◽

Pilot Study ◽

Crohn's Disease ◽

Single Case ◽

Initial Period ◽

Creatine Supplementation

Based on theoretical considerations, experimental data with cells in vitro, animal studies in vivo, as well as a single case pilot study with one colitis patient, a consolidated hypothesis can be put forward, stating that “oral supplementation with creatine monohydrate (Cr), a pleiotropic cellular energy precursor, is likely to be effective in inducing a favorable response and/or remission in patients with inflammatory bowel diseases (IBD), like ulcerative colitis and/or Crohn’s disease”. A current pilot clinical trial that incorporates the use of oral Cr at a dose of 2 × 7 g per day, over an initial period of 2 months in conjunction with ongoing therapies (NCT02463305) will be informative for the proposed larger, more long-term Cr supplementation study of 2 × 3–5 g of Cr per day for a time of 3–6 months. This strategy should be insightful to the potential for Cr in reducing or alleviating the symptoms of IBD. Supplementation with chemically pure Cr, a natural nutritional supplement, is well tolerated not only by healthy subjects, but also by patients with diverse neuromuscular diseases. If the outcome of such a clinical pilot study with Cr as monotherapy or in conjunction with metformin were positive, oral Cr supplementation could then be used in the future as potentially useful adjuvant therapeutic intervention for patients with IBD, preferably together with standard medication used for treating patients with chronic ulcerative colitis and/or Crohn’s disease.

Download Full-text

Deep Learning Algorithm for the Confirmation of Mucosal Healing in Crohn’s Disease, Based on Confocal Laser Endomicroscopy Images

Journal of Gastrointestinal and Liver Diseases ◽

10.15403/jgld-3212 ◽

2021 ◽

Vol 30 (1) ◽

pp. 59-65

Author(s):

Anca Loredana Udristoiu ◽

Daniela Stefanescu ◽

Gabriel Gruionu ◽

Lucian Gheorghe Gruionu ◽

Andreea Valentina Iacob ◽

...

Keyword(s):

Crohn’S Disease ◽

Deep Learning ◽

Crohn's Disease ◽

Colonic Mucosa ◽

Mucosal Healing ◽

Machine Learning Algorithms ◽

Confocal Laser Endomicroscopy ◽

Confocal Laser ◽

Normal Colonic Mucosa ◽

Test Accuracy

Background and Aims: Mucosal healing (MH) is associated with a stable course of Crohn’s disease (CD) which can be assessed by confocal laser endomicroscopy (CLE). To minimize the operator’s errors and automate assessment of CLE images, we used a deep learning (DL) model for image analysis. We hypothesized that DL combined with convolutional neural networks (CNNs) and long short-term memory (LSTM) can distinguish between normal and inflamed colonic mucosa from CLE images. Methods: The study included 54 patients, 32 with known active CD, and 22 control patients (18 CD patients with MH and four normal mucosa patients with no history of inflammatory bowel diseases). We designed and trained a deep convolutional neural network to detect active CD using 6,205 endomicroscopy images classified as active CD inflammation (3,672 images) and control mucosal healing or no inflammation (2,533 images). CLE imaging was performed on four colorectal areas and the terminal ileum. Gold standard was represented by the histopathological evaluation. The dataset was randomly split in two distinct training and testing datasets: 80% data from each patient were used for training and the remaining 20% for testing. The training dataset consists of 2,892 images with inflammation and 2,189 control images. The testing dataset consists of 780 images with inflammation and 344 control images of the colon. We used a CNN-LSTM model with four convolution layers and one LSTM layer for automatic detection of MH and CD diagnosis from CLE images. Results: CLE investigation reveals normal colonic mucosa with round crypts and inflamed mucosa with irregular crypts and tortuous and dilated blood vessels. Our method obtained a 95.3% test accuracy with a specificity of 92.78% and a sensitivity of 94.6%, with an area under each receiver operating characteristic curves of 0.98. Conclusions: Using machine learning algorithms on CLE images can successfully differentiate between inflammation and normal ileocolonic mucosa and can be used as a computer aided diagnosis for CD. Future clinical studies with a larger patient spectrum will validate our results and improve the CNN-SSTM model.

Download Full-text