Segmentation of dental X-ray images in medical imaging using neutrosophic orthogonal matrices

- We focused on enhancing the accuracy of segmentation from dental X-Ray images.
- A new fuzzy clustering based on neutrosophic orthogonal matrix was given.
- It computes inner products of cutting matrix and segments by orthogonal principle.
- It was validated on real dental datasets of Hanoi Medical University Hospital.
- It has better accuracy than the relevant methods.

Over the last few decades, the advance of new technologies in computer equipment, cameras and medical devices became a starting point for the shape of medical imaging systems. Since then, many new medical devices, e.g. the X-Ray machines, computed tomography scans, magnetic resonance imaging, etc., accompanied with operational algorithms inside has contributed greatly to successful diagnose of clinical cases. Enhancing the accuracy of segmentation, which plays an important role in the recognition of disease patterns, has been the focus of various researches in recent years. Segmentation using advanced fuzzy clustering to handle the problems of common boundaries between clusters would tackle many challenges in medical imaging. In this paper, we propose a new fuzzy clustering algorithm based on the neutrosophic orthogonal matrices for segmentation of dental X-Ray images. This algorithm transforms image data into a neutrosophic set and computes the inner products of the cutting matrix of input. Pixels are then segmented by the orthogonal principle to form clusters. The experimental validation on real dental datasets of Hanoi Medical University Hospital, Vietnam showed the superiority of the proposed method against the relevant ones in terms of clustering quality.