Application of S-Transform on Hyper kurtosis based Modified Duo Histogram Equalized DIC images for Pre-cancer Detection
This work addresses precancer detection in medical imaging for clinicians, but it appears incremental as it builds on existing histogram equalization and S-transform methods.
The study tackled the problem of detecting precancerous activity in DIC images by applying S-transform to hyper kurtosis-based modified histogram equalized images, resulting in enhanced contrast and the ability to observe significant amplitude variations in time-frequency domains that reflect tissue inhomogeneity.
Our proposed hyper kurtosis based histogram equalized DIC images enhances the contrast by preserving the brightness. The evolution and development of precancerous activity among tissues are studied through S-transform (ST). The significant variations of amplitude spectra can be observed due to increased medium roughness from normal tissue were observed in time-frequency domain. The randomness and inhomogeneity of the tissue structures among human normal and different grades of DIC tissues is recognized by ST based timefrequency analysis. This study offers a simpler and better way to recognize the substantial changes among different stages of DIC tissues, which are reflected by spatial information containing within the inhomogeneity structures of different types of tissue.