Inflammatory Bowel Disease (IBD) is a chronic inflammation of the gastrointestinal tract. IBD is classified into two main types, Crohn's disease (CD) and ulcerative colitis (UC). The prevalence of CD and UC is the highest in Europe with 322 and 505 per 100,000 people respectively (Molodecky et al., 2012). Conventionally, the severity of IBD is diagnosed by histopathological examination performed by an experienced pathologist. Morphological changes such as crypt distortion, the presence of infiltrates in the lamina propria, and erosion of the epithelial layer are used as inflammatory markers to predict the stage of the disease and plan clinical therapy. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an original essay Over the past decade, label-free multiphoton microscopy (MPM) has been recognized as a real-time in vivo imaging technique for IBD. Its greater penetration depth, high spatial resolution and molecular specificity have accelerated the diagnosis of IBD. MPM techniques such as two-photon excited fluorescence (TPEF) and second harmonic generation (SHG) together with coherent anti-stokes Raman scattering (CARS) can be used to visualize molecular changes associated with IBD (Schürmann et al., 2013).Chernavskaia et al. used CARS/TPEF/SHG intensity-related properties and crypt morphology to assign the histological index to a tissue section from an IBD patient. In their study, the mucosal and crypt regions were annotated by an experienced pathologist, a time-consuming and labor-intensive task (Chernavskaia et al., 2016). Therefore, an automatic segmentation of the crypt region and mucosa using a multimodal image is a prerequisite for estimating the histological index associated with different stages of IBD. However, automatic segmentation of the crypt region and mucosa is a very challenging task due to several factors. reasons. First, the morphology of the crypt changes between patients with different pathological activity. The crypt structure is distorted for patients with a higher IBD stage. Second, the crypts are located within the mucosal region and thus the two regions overlap, which makes classification even more challenging. Third, identifying clear boundaries of the crypt structure is difficult because the crypts are very close to each other. Finally, there is limited availability of annotated medical data capturing various tissue structures of an IBD patient. Therefore, segmenting these regions by image processing and classical machine learning techniques is inefficient. Semantic segmentation using deep convolutional neural network (DCNN) has achieved successful results in the past. Deep neural networks such as U-Net and SegNet have been used for biomedical image segmentation and are the gold standard for pixel-wise segmentation. In this paper, we propose automatic segmentation of multimodal images into four regions using a DCNN. Furthermore, we compare the segmentation results obtained from DCNN with the classical machine learning approach. Please note: this is just an example. Get a custom paper from our expert writers now. Get a Custom Essay The paper is organized as follows, in section (2) we present previous work related to gland segmentation using histological images, in section (3) we present our multimodal image dataset and our workflow of segmentation. This is followed by (5).