Effective Screening and Classification of Cervical Precancer Biopsy Imagery

Abstract

Microscope images of biopsy samples of cervical precancers conventionally discriminated by histopathology, the current "gold standard" for cancer detection, showed that their correlation properties are segregated into different classes. The correlation domains clearly indicate increasing cellular clustering in different grades of precancer compared with their normal counterparts. This trend indicates the probability of pixel distribution of the corresponding tissue images. Because the cell density is not uniform in the higher grades, the skewness (asymmetry of a distribution), kurtosis (sharpness of a distribution), entropy (randomness), and standard deviation are affected. A combination of these parameters effectively improves the diagnosis and quantitatively classifies the normal and all the three grades of precancerous cervical tissue sections significantly. Thus, the statistical analysis of microscope images is a promising approach for early stage tumor detection and quantitative classification of precancerous grades; this can effectively supplement the qualitative analysis by the pathologist.

Detection and segmentation of cancer regions in cervical images using fuzzy logic and adaptive neuro fuzzy inference system classification method

“…Zhang et al obtained 95.1% of sensitivity, 98.3% of specificity, and 98.3% of accuracy. Jagtap et al obtained 94.8% of sensitivity, 97.1% of specificity, and 96.5% of accuracy.…”

“…Table shows the comparisons of proposed cervical cancer segmentation method with other state of arts methods as Karthiga Jaya et al, Zhang et al and Jagtap et al Karthiga Jaya et al obtained 97.42% of sensitivity, 99.36% of specificity, and 99.36% of accuracy. Zhang et al obtained 95.1% of sensitivity, 98.3% of specificity, and 98.3% of accuracy.…”

“…The authors obtained 89.48% of overall classification accuracy using this proposed CNN architecture for the classifications of cervical images. Zhang et al 14 Jagtap et al 8 used asymmetry distribution parameters for screening the cancer regions in cervical images. Initially, correlation of various regions in cervical image was performed and then statistical features were extracted from the correlated image.…”

“…Jagtap et al used asymmetry distribution parameters for screening the cancer regions in cervical images. Initially, correlation of various regions in cervical image was performed and then statistical features were extracted from the correlated image.…”

Mapping of retardance, diattenuation and polarizance vector on Poincare sphere for diagnosis and classification of cervical precancer

“…Various imaging techniques, primarily based on transmission, absorption, reflection, spontaneous emission and scattering in light‐tissue interactions, have shown to be responsive to a number of subtle alterations in various diseased tissue. Mueller matrix (MM) polarimetric imaging based on the acquisition of 16 images has shown tremendous potential in precancer detection since the last decade and is best suited for a complete characterization of the biological specimen . These MM images are further processed to extract the essential optical parameters, namely, diattenuation, retardation and depolarization through Lu‐Chipman decomposition method .…”