Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification. (July 2017)

• Record Type: Journal Article
• Authors: Taghanaki, Saeid Asgari; Kawahara, Jeremy; Miles, Brandon; Hamarneh, Ghassan
• Is Part Of: Computer methods and programs in biomedicine. Volume 145(2017)
• Page Start: 85
• Page End: 93
• Publication Date: 2017-07
• Subjects: Breast cancer -- Computer aided diagnosis -- Feature reduction -- Auto-encoder -- Multi-objective optimization; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2017.04.012
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Traditionally, autoencoders are evaluated by their ability to reconstruct the input data. We propose a new autoencoder optimization objective that also considers the classification performance of candidate encodings. We optimize the multi-objective (reconstruction and classification errors) autoencoder using evolutionary computing (Non-dominated Sorting Genetic Algorithm-II). We evaluate the performance of the proposed autoencoder using 949 mammograms and five different classifiers. We demonstrate the proposed method achieves superior classification results compared to the traditional auto-encoders. Abstract: Background and objective: Feature reduction is an essential stage in computer aided breast cancer diagnosis systems. Multilayer neural networks can be trained to extract relevant features by encoding high-dimensional data into low-dimensional codes. Optimizing traditional auto-encoders works well only if the initial weights are close to a proper solution. They are also trained to only reduce the mean squared reconstruction error (MRE) between the encoder inputs and the decoder outputs, but do not address the classification error. The goal of the current work is to test the hypothesis that extending traditional auto-encoders (which only minimize reconstruction error) to multi-objective optimization for finding Pareto-optimal solutions provides more discriminative features that will improve classification performance when compared to single-objective and other multi-objective approaches (i.e. scalarized and sequential). Methods: In this paper, we introduce a novel multi-objective optimization of deep auto-encoder networks, in which the auto-encoder optimizes two objectives: MRE and mean classification error (MCE) for Pareto-optimal solutions, rather than just MRE. These two objectives are optimized simultaneously by a non-dominated sorting genetic algorithm. Results: We tested our method on 949 X-ray mammograms categorized into 12 classes. The results show that the features identified by the proposed algorithm allow a classification accuracy of up to 98.45%, demonstrating favourable accuracy over the results of state-of-the-art methods reported in the literature. Conclusions: We conclude that adding the classification objective to the traditional auto-encoder objective and optimizing for finding Pareto-optimal solutions, using evolutionary multi-objective optimization, results in producing more discriminative features.