Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification
Convolutional neural networks and deep learning models represent the gold standard in medical image classification. Their innovative architectures have led to notable breakthroughs in image classification and feature extraction performance. However, these advancements often remain underutilized in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Molecular Diversity Preservation International
2023
|
| Subjects: | |
| Online Access: | http://eprints.uanl.mx/27803/1/493.pdf |
| _version_ | 1824420827474427904 |
|---|---|
| author | Berrones Reyes, Mayra Cristina Salazar Aguilar, María Angélica Castillo Olea, Cristian |
| author_facet | Berrones Reyes, Mayra Cristina Salazar Aguilar, María Angélica Castillo Olea, Cristian |
| author_sort | Berrones Reyes, Mayra Cristina |
| collection | Repositorio Institucional |
| description | Convolutional neural networks and deep learning models represent the gold standard in medical image classification. Their innovative architectures have led to notable breakthroughs in image classification and feature extraction performance. However, these advancements often remain
underutilized in the medical imaging field due to the scarcity of sufficient labeled data which are needed to leverage these new features fully. While many methodologies exhibit stellar performance on benchmark data sets like DDSM or Minimias, their efficacy drastically decreases when applied to real-world data sets. This study aims to develop a tool to streamline mammogram classification that maintains high reliability across different data sources. We use images from the DDSM data set and a proprietary data set, YERAL, which comprises 943 mammograms from Mexican patients. We evaluate the performance of ensemble learning algorithms combined with prevalent deep learning models such as Alexnet, VGG-16, and Inception. The computational results demonstrate the effectiveness of the proposed methodology, with models achieving 82% accuracy without overtaxing our hardware capabilities, and they also highlight the efficiency of ensemble algorithms in enhancing accuracy
across all test cases. |
| format | Article |
| id | eprints-27803 |
| institution | UANL |
| language | English |
| publishDate | 2023 |
| publisher | Molecular Diversity Preservation International |
| record_format | eprints |
| spelling | eprints-278032024-12-09T15:08:40Z http://eprints.uanl.mx/27803/ Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification Berrones Reyes, Mayra Cristina Salazar Aguilar, María Angélica Castillo Olea, Cristian R Medicina en General Convolutional neural networks and deep learning models represent the gold standard in medical image classification. Their innovative architectures have led to notable breakthroughs in image classification and feature extraction performance. However, these advancements often remain underutilized in the medical imaging field due to the scarcity of sufficient labeled data which are needed to leverage these new features fully. While many methodologies exhibit stellar performance on benchmark data sets like DDSM or Minimias, their efficacy drastically decreases when applied to real-world data sets. This study aims to develop a tool to streamline mammogram classification that maintains high reliability across different data sources. We use images from the DDSM data set and a proprietary data set, YERAL, which comprises 943 mammograms from Mexican patients. We evaluate the performance of ensemble learning algorithms combined with prevalent deep learning models such as Alexnet, VGG-16, and Inception. The computational results demonstrate the effectiveness of the proposed methodology, with models achieving 82% accuracy without overtaxing our hardware capabilities, and they also highlight the efficiency of ensemble algorithms in enhancing accuracy across all test cases. Molecular Diversity Preservation International 2023 Article PeerReviewed text en cc_by_nc_nd http://eprints.uanl.mx/27803/1/493.pdf http://eprints.uanl.mx/27803/1.haspreviewThumbnailVersion/493.pdf Berrones Reyes, Mayra Cristina y Salazar Aguilar, María Angélica y Castillo Olea, Cristian (2023) Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification. Applied Sciences, 13 (17). pp. 1-15. ISSN 2076-3417 http://doi.org/10.3390/app13179639 doi:10.3390/app13179639 |
| spellingShingle | R Medicina en General Berrones Reyes, Mayra Cristina Salazar Aguilar, María Angélica Castillo Olea, Cristian Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification |
| thumbnail | https://rediab.uanl.mx/themes/sandal5/images/online.png |
| title | Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification |
| title_full | Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification |
| title_fullStr | Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification |
| title_full_unstemmed | Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification |
| title_short | Use of Ensemble Learning to Improve Performance of Known Convolutional Neural Networks for Mammography Classification |
| title_sort | use of ensemble learning to improve performance of known convolutional neural networks for mammography classification |
| topic | R Medicina en General |
| url | http://eprints.uanl.mx/27803/1/493.pdf |
| work_keys_str_mv | AT berronesreyesmayracristina useofensemblelearningtoimproveperformanceofknownconvolutionalneuralnetworksformammographyclassification AT salazaraguilarmariaangelica useofensemblelearningtoimproveperformanceofknownconvolutionalneuralnetworksformammographyclassification AT castillooleacristian useofensemblelearningtoimproveperformanceofknownconvolutionalneuralnetworksformammographyclassification |