Automatic classification of small bowel mucosa alterations in celiac disease for confocal laser endomicroscopy

Abstract

Celiac disease (CD) is an immune-mediated enteropathy triggered by exposure to gluten and similar proteins, affecting genetically susceptible persons, increasing their risk of different complications. Small bowels mucosa damage due to CD involves various degrees of endoscopically relevant lesions, which are not easily recognized: their overall sensitivity and positive predictive values are poor even when zoom-endoscopy is used. Confocal Laser Endomicroscopy (CLE) allows skilled and trained experts to qualitative evaluate mucosa alteration such as a decrease in goblet cells density, presence of villous atrophy or crypt hypertrophy. We present a method for automatically classifying CLE images into three different classes: normal regions, villous atrophy and crypt hypertrophy. This classification is performed after a features selection process, in which four features are extracted from each image, through the application of homomorphic filtering and border identification through Canny and Sobel operators. Three different classifiers have been tested on a dataset of 67 different images labeled by experts in three classes (normal, VA and CH): linear approach, Nave-Bayes quadratic approach and a standard quadratic analysis, all validated with a tenfold cross validation. Linear classification achieves 82.09% accuracy (class accuracies: 90.32% for normal villi, 82.35% for VA and 68.42% for CH, sensitivity: 0.68, specificity 1.00), Nave Bayes analysis returns 83.58% accuracy (90.32% for normal villi, 70.59% for VA and 84.21% for CH, sensitivity: 0.84 specificity: 0.92), while the quadratic analysis achieves a final accuracy of 94.03% (96.77% accuracy for normal villi, 94.12% for VA and 89.47% for CH, sensitivity: 0.89, specificity: 0.98).

Image computing for fibre-bundle endomicroscopy: A review

“…(eCLE) (Boschetto et al, 2016a) Oropharyngeal Pathological epithelium. Jaremenko et al, 2015;Vo et al, 2017) Brain Brain tumours (glioma and meningioma).…”

“…Classification of frames on pre-determined, clinically defined cohorts based on their content is currently the most investigated area of FBEµ image computing research. An abundance of studies have applied binary as well as multi-class classification on endomicroscopic images of a range of organ systems in an attempt to identify cancer in ovarian epithelium (Srivastava et al, 2005;Srivastava et al, 2008), abnormalities in distal lung alveolar structures (Desir et al, 2012a;Désir et al, 2010;Desir et al, 2012b;Hebert et al, 2012;Heutte et al, 2016;Koujan et al, 2018;Petitjean et al, 2009;Saint-Réquier et al, 2009), informative frames in brain (Izadyyazdanabadi et al, 2017a;Izadyyazdanabadi et al, 2017b) and pulmonary videos (Leonovych et al, 2018;Perperidis et al, 2016), cancerous nodules in the airways (Gil et al, 2017;He et al, 2012;Rakotomamonjy et al, 2014) and distal lung (Seth et al, 2016), pathological epithelium in the oropharyngeal cavity (Aubreville et al, 2017;Jaremenko et al, 2015;Vo et al, 2017) , changes in oesophageal epithelium in cases of Barrett's oesophagus (Ghatwary et al, 2017;Hong et al, 2017;Veronese et al, 2013;Wu et al, 2017), adenocarcinoma (Ştefănescu et al, 2016), colorectal polyps (André et al, 2012b;Zubiolo et al, 2014) and celiac disease (Boschetto et al, 2016a) in intestinal epithelium, neoplastic tissue in breast nodules (Gu et al, 2017), as well as two types of common brain tumours, glioblastoma and meningioma (Kamen et al, 2016;Murthy et al, 2017;Wan et al, 2015).…”

“…Classification of endomicroscopic images has predominantly concentrated in binary cases, with a very limited number of studies having attempted multi-class classification (Boschetto et al, 2016a;Ghatwary et al, 2017;Hong et al, 2017;Koujan et al, 2018;Veronese et al, 2013;Wu et al, 2017;Zubiolo et al, 2014). To this end, (Boschetto et al, 2016a) employed a multi-class Naïve Bayes classifier. (Koujan et al, 2018) adopted the One-Versus-All (OVA) Error Correcting Output Codes (ECOC), a popular method (along with other ECOCs such as One-Versus-One and Ordinal) for multi-class classification using binary classifiers.…”