International Journal For Multidisciplinary Research

E-ISSN: 2582-2160     Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 6 Issue 6 November-December 2024 Submit your research before last 3 days of December to publish your research paper in the issue of November-December.

Breast Thermograms Analysis using Deep Neural Network

Author(s) M.KOWSALYA, P.SUMATHI
Country India
Abstract Breast cancer is one of the leading causes of mortality among women globally. Early identification of this kind of cancer is important for a successful treatment outcome. A variety of screening techniques can be used to identify breast cancer. Thermography is possible for early diagnosis that uses thermal cameras with great resolution and sensitivity. The goal is to develop a system that automatically captures and classifies thermographic imaging of the breast as normal or abnormal. In this method,the detection and classification of breast cancer from thermography images usingadeeplearning-based convolution neural network using the VGG-19 algorithm. Breast cancer detection is performed using CNN with the help of Google collaboratory (Google Colab). Finally, as the result of experimental studies, the major focus is on the performance accuracy of the train and test dataset, and the graph is plotted between the training and validation accuracy.The VGG-19 network achieved the highesttestperformanceof 99.80% in breast cancer detection and to classify cancer using the DMR Mastology Research dataset.
Keywords Breast cancer, Thermography, image processing, Convolutional Neural Networks, Deep Learning, VGG19, Thermal images.
Field Engineering
Published In Volume 5, Issue 4, July-August 2023
Published On 2023-07-31
Cite This Breast Thermograms Analysis using Deep Neural Network - M.KOWSALYA, P.SUMATHI - IJFMR Volume 5, Issue 4, July-August 2023. DOI 10.36948/ijfmr.2023.v05i04.4772
DOI https://doi.org/10.36948/ijfmr.2023.v05i04.4772
Short DOI https://doi.org/gskd3n

Share this