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

Abstract

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.

Role of ultra‐high definition endoscopy (endomicroscopy and endocytoscopy) and real‐time histologic examination in inflammatory bowel disease: Scoping review

“…Several studies (seven prospective and two retrospective) have investigated the CLE features of inflammation. These include crypt architectural abnormalities, microvascular alterations, inflammatory cell infiltration in lamina propria, and increased vascular permeability as evidenced by fluorescein leakage in lamina propria 1,3–10 . Additional markers of inflammation included evidence of microerosions and decrease in goblet cells 1 .…”

“…These include crypt architectural abnormalities, microvascular alterations, inflammatory cell infiltration in lamina propria, and increased vascular permeability as evidenced by fluorescein leakage in lamina propria. 1,[3][4][5][6][7][8][9][10] Additional markers of inflammation included evidence of microerosions and decrease in goblet cells. 1 These markers have been used for documenting mucosal healing in both ulcerative colitis (UC) and Crohn's disease (CD) (Table 1).…”

Inflammatory bowel disease–associated intestinal fibrosis

“…Following a recent discussion at the Stenosis Therapy and Antifibrotic Research Consortium, a four-tiered system (none, mild, moderate, and severe) was constructed to include an evaluation of the inflammatory and fibrotic components of each mural layer [ 55 ]. In this artificial intelligence era, researchers have endeavored to develop a deep learning model to evaluate intestinal fibrosis in surgical specimens for postoperative recurrence prediction [ 65 , 66 ].…”

A systematic review on application of deep learning in digestive system image processing

“…However, CLE requires accurate image interpretation, which only experienced endoscopic physicians can do. Udristoiu’s team designed the DL system can distinguish between ulcerated and healed Crohn’s disease patients in CLE pictures [ 29 ]. Still, the algorithm was unable to determine active ulcers from inactive ulcers.…”