Delaunay triangulation-based pit density estimation for the classification of polyps in high-magnification chromo-colonoscopy

Abstract

Highlights► Exploiting the visual nature of pit patterns on the colonic mucosa. ► Roughly four times faster compared to a previously developed approach. ► Significantly higher classification rates compared to our previous work. ► More robust against overfitting when compared to other methods.

Exploring Deep Learning and Transfer Learning for Colonic Polyp Classification

“…Kudo et al [7] proposed the so-called “pit-pattern” scheme to help in diagnosing tumorous lesions once suspicious areas have been detected. In this scheme, the mucosal surface of the colon can be classified into 5 different types designating the size, shape, and distribution of the pit structure [8, 9]. …”

“…In the literature, existing computer-aided diagnosis techniques generally make use of feature extraction methods of color, shape, and texture in combination with machine learning classifiers to perform the classification of colon polyps [9, 11, 12]. For example, the dual-tree complex wavelet transform DT-CWT features proved to be quite suitable for the distinction of different types of polyps as can be seen in many works like, for example, [13–15].…”

“…The main difficulty of the feature extraction methods is the proper characterization of these patterns due to several factors as the lack or excess of illumination, the blurring due to movement or water injection, and the appearance of polyps [5, 9]. Also, to find a robust and a global feature extractor that summarizes and represents all these pit-pattern structures in a single vector is very difficult and Deep Learning can be a good alternative to surpass these problems.…”

Hybrid detection of lung nodules on CT scan images

“…LIDC is a standard lung nodule database available to the public in the National Biomedical Imaging Archive (NBIA). 20 The LIDC database was collected by the National Cancer Institute and purposely used for developing a CAD method for lung cancer screening studies and diagnosis. The database contains lung nodules that were annotated by four experienced radiologists (who participated in the LIDC project) in a two-phase reading procedure.…”

Small Colorectal Polyps

“…Since the ability of the human eye and brain largely depends on knowledge and training and is therefore at risk for error, several working groups have tried to develop image recognition software to classify polyps automatically [17]. …”