Identification of malignancy in lung using artificial neural network. (1st January 2022)

• Record Type: Journal Article
• Authors: Kumari, S. Lalitha; Pandian, R.
• Is Part Of: International journal of bioinformatics research and applications. Volume 17:Number 5(2021)
• Page Start: 415
• Page End: 423
• Publication Date: 2022-01-01
• Subjects: GLCM -- grey level co occurrence matrix -- Haralick -- classification accuracy -- MSE -- mean square error -- SSE -- sum squared error -- MSEREG -- mean square error with regularised; Bioinformatics -- Periodicals; 570.285
• Languages: English
• ISSNs: 1744-5485

Abstract

Earlier diagnosis of cancer cell growth leads to save lots of precious human lives. It is necessary to develop some automated tool, in order to detect malignant state at the beginning stage itself. Many algorithms had been proposed earlier by many researchers in the past, but, the accuracy of prediction is always a challenging task. In this work, an artificial neural network based methodology is proposed to find the abnormal growth of lung tissues. Higher probability of detection is taken as an objective to get an automated tool, with great accuracy. Manual interpretation always leads to misdiagnosis. Optimal feature sets derived from Haralick grey level co occurrence matrix and used as the dimension reduction way for feeding neural network. In this work, a binary classifier neural network has been proposed to identify the normal images out of all the images. The capability of the proposed neural network has been quantitatively computed using confusion matrix.