Bibliographic Details
| Title: |
An Accurate Diagnosis and Classification of Breast Mammogram Using Transfer Learning in Deep Convolutional Neural Network. |
| Authors: |
Annamalai, Thiyagarajan1 (AUTHOR) thiyagarajana@svce.ac.in, Chinnasamy, Murukesh2 (AUTHOR), Pandian, Mary Joans Samuel Soundara2 (AUTHOR) |
| Source: |
Traitement du Signal. Feb2025, Vol. 42 Issue 1, p343-352. 10p. |
| Subject Terms: |
*Artificial neural networks, *Patient care, Breast cancer, Mammograms, Transfer of training, Deep learning, Image recognition (Computer vision) |
| Abstract: |
Timely and precise identification of breast cancer (BC) is essential for enhancing patient results. This work investigates the capacity of deep learning to automate the categorization of BC using mammogram images. Our proposal involves using transfer learning with a customized Inception v3 architecture. This method utilizes pre-trained characteristics to tailor the model to the particular mammogram domain. Next, modified the last layers of the network and refined it using a mammogram dataset for classification. We assess the efficacy of our adapted Inception v3 model on a standard mammogram dataset, contrasting it with other deep learning structures and conventional machine learning techniques. The suggested technique demonstrates higher accuracy, sensitivity, and specificity in distinguishing normal and malignant breast tissue when compared to other approaches. This modified Inception v3 architecture has the capacity to strengthen the effectiveness in addition to the precision of breast cancer screening, eventually resulting in improved patient care. The proposed work is evaluated in comparison to other existing methodologies, including Inception v3, Inception v2, and VGG 16 and 19. The proposed modified Inception v3 model achieves 96.1% which is comparatively higher than the other methods. [ABSTRACT FROM AUTHOR] |
|
Copyright of Traitement du Signal is the property of International Information & Engineering Technology Association (IIETA) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Business Source Complete |
