Segmentation and Analysis of Diagnostic Images for Lesion Detection: Current Status and Future Potential

Abstract

In this study, we have presented an elaborate overview of various segmentation techniques found in the current medical literature for computeraided detection of lesions from different diagnostic imaging modalities. Lesions can be broadly classified as benign or malignant. Computer-aided detection of lesions solely depends on the diagnostic modality. Analysis of medical images for detection of lesions requires a high degree of accuracy and precision. Diagnostic imaging modalities can be broadly classified as invasive, non-invasive and minimally invasive. Each of the modalities has its own challenges. From each of the modalities, we have considered some challenging hazardous diseases. Amongst invasive techniques, microscopic images of the breast and cervical cancers were considered for the study. In non-invasive technique ultrasound images of breast cancer were considered and in minimally invasive technique colorectal cancer detection using colonoscopy has been considered.