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

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.

Endoscopic ultrasound elastography-- a new imaging technique for the visualization of tissue elasticity distribution.

Endoscopic ultrasound (EUS) elastography is an imaging procedure used for the visualization of tissue elasticity during usual EUS examinations. EUS elastography can be accomplished real-time with state-of-the-art ultrasound systems, with the images being represented in transparent color superimposed on the conventional gray-scale B-mode scans. The aim of this review was to introduce the potential range of applications of EUS elastography. EUS elastography might be useful for the differentiation of benign and malignant lymph nodes, with a qualitative pattern analysis and a quantitative histogram analysis of the color images being used to adequately classify the lesions. Mapping of the tissue elasticity distribution might be useful for the differential diagnosis of focal pancreatic masses, especially in the setting of chronic pancreatitis where the accuracy of EUS-guided fine needle aspiration is also low. EUS elastography might also enhance the detection and differentiation of various solid tumors (adrenal tumors, submucosal tumors, etc.) situated nearby the gastrointestinal tract. Routine use of EUS elastography thus offers supplemental information that enhances conventional EUS imaging, with a possible decrease in the number of un-necessary EUS-FNA procedures used for tissue confirmation. However, future enhancements of the EUS elastography technology, as well as prospective, randomized studies will probably establish the clinical impact of dynamic elasticity imaging.