Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model
Improved disease prediction accuracy and reliability are the main concerns in the development of models for the medical field. This study examined methods for increasing classification accuracy and proposed a precise and reliable framework for categorizing breast cancers using mammography scans. Con...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/7/3/142 |
| _version_ | 1827727174193381376 |
|---|---|
| author | Mohammad H. Alshayeji Jassim Al-Buloushi |
| author_facet | Mohammad H. Alshayeji Jassim Al-Buloushi |
| author_sort | Mohammad H. Alshayeji |
| collection | DOAJ |
| description | Improved disease prediction accuracy and reliability are the main concerns in the development of models for the medical field. This study examined methods for increasing classification accuracy and proposed a precise and reliable framework for categorizing breast cancers using mammography scans. Concatenated Convolutional Neural Networks (CNN) were developed based on three models: Two by transfer learning and one entirely from scratch. Misclassification of lesions from mammography images can also be reduced using this approach. Bayesian optimization performs hyperparameter tuning of the layers, and data augmentation will refine the model by using more training samples. Analysis of the model’s accuracy revealed that it can accurately predict disease with 97.26% accuracy in binary cases and 99.13% accuracy in multi-classification cases. These findings are in contrast with recent studies on the same issue using the same dataset and demonstrated a 16% increase in multi-classification accuracy. In addition, an accuracy improvement of 6.4% was achieved after hyperparameter modification and augmentation. Thus, the model tested in this study was deemed superior to those presented in the extant literature. Hence, the concatenation of three different CNNs from scratch and transfer learning allows the extraction of distinct and significant features without leaving them out, enabling the model to make exact diagnoses. |
| first_indexed | 2024-03-10T23:02:52Z |
| format | Article |
| id | doaj.art-b9b4449f23a344ec9b8645819358b0c5 |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-10T23:02:52Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-b9b4449f23a344ec9b8645819358b0c52023-11-19T09:34:19ZengMDPI AGBig Data and Cognitive Computing2504-22892023-08-017314210.3390/bdcc7030142Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks ModelMohammad H. Alshayeji0Jassim Al-Buloushi1Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Safat, P.O. Box 5969, Kuwait City 13060, KuwaitComputer Engineering Department, College of Engineering and Petroleum, Kuwait University, Safat, P.O. Box 5969, Kuwait City 13060, KuwaitImproved disease prediction accuracy and reliability are the main concerns in the development of models for the medical field. This study examined methods for increasing classification accuracy and proposed a precise and reliable framework for categorizing breast cancers using mammography scans. Concatenated Convolutional Neural Networks (CNN) were developed based on three models: Two by transfer learning and one entirely from scratch. Misclassification of lesions from mammography images can also be reduced using this approach. Bayesian optimization performs hyperparameter tuning of the layers, and data augmentation will refine the model by using more training samples. Analysis of the model’s accuracy revealed that it can accurately predict disease with 97.26% accuracy in binary cases and 99.13% accuracy in multi-classification cases. These findings are in contrast with recent studies on the same issue using the same dataset and demonstrated a 16% increase in multi-classification accuracy. In addition, an accuracy improvement of 6.4% was achieved after hyperparameter modification and augmentation. Thus, the model tested in this study was deemed superior to those presented in the extant literature. Hence, the concatenation of three different CNNs from scratch and transfer learning allows the extraction of distinct and significant features without leaving them out, enabling the model to make exact diagnoses.https://www.mdpi.com/2504-2289/7/3/142artificial intelligencemachine learningbreast tumorsconvolutional neural networksBayesian optimization |
| spellingShingle | Mohammad H. Alshayeji Jassim Al-Buloushi Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model Big Data and Cognitive Computing artificial intelligence machine learning breast tumors convolutional neural networks Bayesian optimization |
| title | Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model |
| title_full | Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model |
| title_fullStr | Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model |
| title_full_unstemmed | Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model |
| title_short | Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model |
| title_sort | breast cancer classification using concatenated triple convolutional neural networks model |
| topic | artificial intelligence machine learning breast tumors convolutional neural networks Bayesian optimization |
| url | https://www.mdpi.com/2504-2289/7/3/142 |
| work_keys_str_mv | AT mohammadhalshayeji breastcancerclassificationusingconcatenatedtripleconvolutionalneuralnetworksmodel AT jassimalbuloushi breastcancerclassificationusingconcatenatedtripleconvolutionalneuralnetworksmodel |