Publication

Abstract : Due to the morphological characteristics and other biological aspects in histopathological images, the computerized diagnosis of colon cancer in histopathology images has gained popularity. The images acquired using the histopathology microscope may differ for greater visibility by magnifications. This causes a change in morphological traits leading to intra and inter-observer variability. An automatic colon cancer diagnosis system for various magnification is therefore crucial. This work proposes a magnification independent segmentation approach based on the connected component area and double density dual tree DWT (discrete wavelet transform) coefficients are derived from the segmented region. The derived features are reduced further shortened with fuzzy c-means. Further, with the aid of artificial neural network (ANN) optimized with salp swarm optimization (SSO), images are classified into normal and abnormal ones. This magnification independent proposed framework is evaluated across four different datasets (two realtime datasets and two public datasets) with different magnifications and the outcomes of all datasets were substantial when compared with the existing techniques. The proposed framework has shown strong concordance for cancer detection and can assist pathologists with a second opinion.