Automatic classification of acetowhite temporal patterns to identify precursor lesions of cervical cancer

4th National Meeting in Chaos, Complex System and Time Series

Gutiérrez-Fragoso, K.^1 ; Acosta-Mesa, H.G.^2 ; Cruz-Ramírez, N.^2 ; Hernández-Jiménez, R.^3

Biomedical Research Center, Universidad Veracruzana, Mexico^1

School of Physics and Artificial Intelligence, Department of Artificial Intelligence, Universidad Veracruzana, Mexico^2

Obstetrician and Gynaecologist, Private Practice, Mexico^3

关键词: Automatic classification;    Automatic method;    Classification methods;    Histological analysis;    Performance analysis;    Precursor lesions;    Temporal approach;    Temporal dynamics;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/475/1/012004/pdf
DOI  :  10.1088/1742-6596/475/1/012004

来源: IOP

【 摘 要 】

Cervical cancer has remained, until now, as a serious public health problem in developing countries. The most common method of screening is the Pap test or cytology. When abnormalities are reported in the result, the patient is referred to a dysplasia clinic for colposcopy. During this test, a solution of acetic acid is applied, which produces a color change in the tissue and is known as acetowhitening phenomenon. This reaction aims to obtaining a sample of tissue and its histological analysis let to establish a final diagnosis. During the colposcopy test, digital images can be acquired to analyze the behavior of the acetowhitening reaction from a temporal approach. In this way, we try to identify precursor lesions of cervical cancer through a process of automatic classification of acetowhite temporal patterns. In this paper, we present the performance analysis of three classification methods: kNN, Naive Bayes and C4.5. The results showed that there is similarity between some acetowhite temporal patterns of normal and abnormal tissues. Therefore we conclude that it is not sufficient to only consider the temporal dynamic of the acetowhitening reaction to establish a diagnosis by an automatic method. Information from cytologic, colposcopic and histopathologic disciplines should be integrated as well.