Study of cervical cancer through fractals and a method of clustering based on quantum mechanics

• Published in: Applied radiation and isotopes Vol. 150; pp. 182 - 191
• Main Authors: Hoyos, F. Torres, Martín–Landrove, M., Navarro, R. Baena, Villadiego, J. Vergara, Cardenas, J. Causil
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.08.2019
• Subjects: Adenocarcinoma - diagnostic imaging; Adenocarcinoma - pathology; Algorithm; Algorithms; Carcinoma, Squamous Cell - diagnostic imaging; Carcinoma, Squamous Cell - pathology; Cervix; Cluster Analysis; Female; Fractal; Fractals; Humans; Image Interpretation, Computer-Assisted - methods; Image Interpretation, Computer-Assisted - statistics & numerical data; Imaging, Three-Dimensional; K-means; Local roughness; Magnetic Resonance Imaging; Quantum Theory; Uterine Cervical Neoplasms - diagnostic imaging; Uterine Cervical Neoplasms - pathology; K-means; 05.45.Df; Fractal; 68.35.Ct; Cervix; Local roughness; Algorithm
• ISSN: 0969-8043; 1872-9800; 1872-9800
• DOI: 10.1016/j.apradiso.2019.05.011

Tumor growth in the cervix is a complex process. Understanding this phenomena is quite relevant in order to establish proper diagnosis and therapy strategies and a possible startpoint is to evaluate its complexity through the scaling analysis, which define the tumor growth geometry. In this work, tumor interface from primary tumors of squamous cells and adenocarcinomas for cervical cancer were extracted. Fractal dimension and local roughness exponent (Barabási and Stanley (1996)), αloc, were calculated to characterize the in vivo 3-D tumor growth. Image acquisition was carried out according to the standard protocol used for cervical cancer radiotherapy, i.e., axial, magnetic resonance T1 - weighted contrast enhanced images comprising the cervix volume for image registration. Image processing was carried out by a classification scheme based on quantum clustering algorithm (Mussa et al. (2015)) combined with the application of the K-means procedure upon contrasted images (Demirkaya et al. (2008)). The results show significant variations of the parameters depending on the tumor stage and its histological origin. •The dynamic quantum clustering algorithm is used to segment digital images.•Fractal analysis applied to cervix tumor lesions has permitted tumors grading.•Differents type cancer cervix, were analyzed to calculate local roughness exponent.•An algorithm was developed to determine the width of the tumor - host interface.•The K-means algorithm is used in digital images belonging to the DICOM standard.