Fuzzy rulebase parameter determination for stabilized KH interpolation based detection of colorectal polyps on colonoscopy images

Sziová, Brigita; Ismail, Raneem; Lilik, Ferenc; Kóczy, László T.; Nagy, Szilvia Anett

doi:10.1109/fuzz48607.2020.9177839

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, a method relying on triangular fuzzy sets and their characteristic points (infima and suprema of the supports and the highest value points) was used. These values were computed from the minimum, maximum and mean of the empirical measured data from the training set [20], later also these triangles were fitted properly to the shape of the training set's measured data's histograms [42].…”

Section: Fuzzy Sets and Inferencementioning

confidence: 99%

Application of Structural Entropy and Spatial Filling Factor in Colonoscopy Image Classification

Sziová

Nagy

Fazekas

2021

Entropy

Self Cite

View full text Add to dashboard Cite

For finding colorectal polyps the standard method relies on the techniques and devices of colonoscopy and the medical expertise of the gastroenterologist. In case of images acquired through colonoscopes the automatic segmentation of the polyps from their environment (i.e., from the bowel wall) is an essential task within computer aided diagnosis system development. As the number of the publicly available polyp images in various databases is still rather limited, it is important to develop metaheuristic methods, such as fuzzy inference methods, along with the deep learning algorithms to improve and validate detection and classification techniques. In the present manuscript firstly a fuzzy rule set is generated and validated. The former process is based on a statistical approach and makes use of histograms of the antecedents. Secondly, a method for selecting relevant antecedent variables is presented. The selection is based on the comparision of the histograms computed from the measured values for the training set. Then the inclusion of the Rényi-entropy-based structural entropy and the spatial filling factor into the set of input variables is proposed and assessed. The beneficial effect of including the mentioned structural entropy of the entropies from the hue and saturation (H and S) colour channels resulted in 65% true positive and 60% true negative rate of the classification for an advantageously selected set of antecedents when working with HSV images.

show abstract

Section: Fuzzy Sets and Inferencementioning

confidence: 99%