VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1742
Title: | Classification of breast cancer for modern mammography using convolutional neural networks | Authors: | Ngo Quoc Thai | Keywords: | Breast cancer;Mammography;Convolutional neural network;Constrasted limited adaptive histogram equalisation;Polynomial curve fitting | Issue Date: | 2023 | Abstract: | Breast cancer is one of the most common types of cancer in the globe. It is difficult to detect and diagnose the mass at an early stage with high accuracy since it is necessary to provide patients with responsive, appropriate treatment. Machine learning models are being invested in and chosen in today’s modern world to address the issue of using human resources for classification or detection activities. As a result, deep learning models are being explored and implemented in the medical field, particularly in categorizing different types of breast mass. Fortunately, mammography has been shown to be effective in detecting and categorizing cancer cells in breast tissue. As a result, several image preprocessing techniques and deep learning models use mammography to develop models with exceptional accuracy. The goal of this paper is to construct and evaluate deep learning models for classifying benign and malignant breast tumors. The solution implementation strategy consists of two primary parts. Before being utilized as an input, the mammography is first preprocessed using constrained limited adaptive histogram equalization (CLAHE) and the polynomial curve fitting approach. The second step is to build convolutional neural networks and train them via transfer learning or from scratch. The results show that using deep learning models yields noticeable accuracy for MIAS, INBreast, DDSM, RSNA, and other dataset combinations. The source code for the implementation of this thesis is available via this link: https://github.com/ngoquocthai0311/breast-cancer-detection |
URI(1): | https://epub.vgu.edu.vn/handle/dlibvgu/1742 | Rights: | Attribution-ShareAlike 3.0 United States |
Appears in Collections: | Computer Science (CS) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
Classification of breast cancer for modern mammography using convolutional neural networks.pdf | 2.1 MB | Adobe PDF |
This item is licensed under a Creative Commons License