vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff21782b0000005163040001000700 Pancreatic Cancer (PC) may be a leading reason behind death worldwide and its prognosis is extremely poor within the present scenario. There are numerous methods and techniques for tumor identification in brain, breast, lungs, but limited work was done on pancreatic tumor detection. Pancreatic tumor image classification is usually provided by computer-aided screening (CAD), diagnosis and quantitative evaluations in radiology images like CT and MRI. Tumor classification through these methods may help to trace, predict and endorse customized therapy as part of effective treatment, without invasions of cancer. Nowadays, Convolutional Neural Networks (CNN) have shown promising results for precise pancreatic image classification. As a prominent, the algorithms are required to work out and classify the categories of pancreatic tumors at early stages for saving most of the life. Because of the various shapes, huge sample size, processing and analyzing big databases, new statistical methods are to be implemented. On the opposite hand, detection of tumors within the medical images also become difficult since the standard of input images. This paper mainly concentrates on a study of carcinoma and also the recent research on tumor detection and classification in medical images. The convolution neural network (CNN) developed in recent years has been widely utilized in the sector of image processing because it's good at handling image classification and recognition problems and has brought great improvement within the accuracy of the many machine learning tasks. One in every of the foremost powerful approaches to resolve image recognition and classification problem is that the CNN. The experimental results demonstrate that the proposed approach can improve the performance of the classification accuracy.
S Arulmozhi, R Shankar, S Duraisamy
Chikkanna Government Arts College, India
CNN, Classification, Deep Learning, Medical Image Analysis, Pancreatic Cancer, Adenocarcinomas
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 11 , Issue: 1 , Pages: 2217-2223 )
Date of Publication :
August 2020
Page Views :
215
Full Text Views :
4
|