Stacking approach for accurate Invasive Ductal Carcinoma classification. (May 2022)

• Record Type: Journal Article
• Authors: Haq, Amin Ul; Li, Jian Ping; Ali, Zafar; Khan, Inayat; Khan, Ajab; Uddin, M. Irfan; Agbley, Bless Lord Y.; Khan, Riaz Ullah
• Is Part Of: Computers & electrical engineering. Volume 100(2022)
• Publication Date: 2022-05
• Subjects: Deep learning -- Breast cancer -- Clinical image data -- Transfer learning -- Data augmentation -- Stacking -- Classification -- Accuracy -- Diagnosis -- Analysis; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.107937
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: The accurate diagnosis of Breast cancer (BC) requires adequately exploiting Artificial intelligence (AI)-based methods in the diagnosing process. To tackle the issue of accurate BC diagnosis, we have proposed a deep learning-based stacking method (StackBC). In particular, we have incorporated deep learning models including Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) for the classification of Invasive Ductal Carcinoma (IDC). Additionally, Transfer Learning (TL) and Data Augmentation (DA) approaches have been incorporated to balance the dataset and adequately train the model. To further improve the predictive outputs of the model, we used the stacking technique. Among the three individual base classifiers, the performance of the GRU model was better. Hence, we selected the GRU as a meta classifier to distinguish between Non-IDC and IDC breast images. The experimental results confirmed that the StackBC method outperformed state-of-the-art methods. Graphical abstract: Highlights: Breast cancer detection and diagnostic method called Stack Breast Cancer is proposed. Our CNN, LSTM and GRU models were evaluated using a breast histology image dataset. Transfer learning and data augmentation were used to improve the models' performances. Stacking the models produced an improved model with a GRU meta predictor and performance of Stack BC model were higher compared to existing models.