Liver Lesions Classification System using CNN with Improved Accuracy
DOI:
https://doi.org/10.46947/joaasr412022233Keywords:
Computer-Aided-Diagnosis(CAD); Relu (Rectified linear unit); Digital Imaging and Communication in Medicine(DICOM);Computed Tomography(CT);Convolution Neural Network(CNN).Abstract
In this paper, the liver lesions classification system for CT images use deep learning (CNN)model with
improved accuracy has proposed. The sequential model of CNN architecture with I/P convolution layer, Hidden
convolution layer, and O/P convolution layer for CT images have been used to classify liver lesions. TensorFlow-
2.0 is used to make an image with varying image qualities.The proposed network is used for CT images with an
image size of 65×65, 60×60, 50×50 for which liver lesions classification accuracy of 99%,97%,95% respectively
are achieved. The regularization technique used in proposed N/W has helped to improve the accuracy and
minimization over fitting problem. The classification accuracy improvement has justified by comparing the
proposed research work with other researcher's work.