Abstract

Generally, hepatotoxicity indicates liver damage due to consumption of chemical substances. Finding the liver disease helps in the diagnosis of liver damage in early stage and also increases the lifetime of the individual. The article proposes a new method to segment the damaged portion using segmentation algorithm. The segmented area is subjected to Radon transform for extracting the coefficients indicated by a color map. It is followed by a genetic algorithm (GA) classifier to classify the abnormal portion of the liver image. In the medical field, CT scan imaging is one of the best imaging techniques to identify the abnormal growth of the cells from the CT images. It is still challenging for physicians to identify abnormal or damaged cells from CT scan images at the initial stages. Normally, the physicians diagnose liver abnormalities only in the third or fourth stages of liver disease using CT scan imaging technique. Hence, to facilitate a diagnostic technique that will identify liver disease like liver cancer in the precancerous stage; this image processing technique is proposed. The article uses the OTSU’s thresholding followed by active contour segmentation, Radon transform, and GA based classification. Finally, the performance is compared between the two segmentation methods for which Radon transform is used along with GA classifier. The performance of the proposed research work is compared in terms of peak signal-to-noise ratio and mean squared error (MSE) for OTSU’s thresholding and active-contour based segmentation. The precancerous stages are also identified with greater specificity, sensitivity, accuracy, and classification efficiency by using active-contour based segmentation and GA as compared with other algorithms.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.