Hybrid DSSCS and convolutional neural network for peripheral blood cell recognition system. Issue 17 (11th March 2021)

• Record Type: Journal Article
• Authors: Joshi, Shivani; Kumar, Rajiv; Dwivedi, Avinash
• Is Part Of: IET image processing. Volume 14:Issue 17(2020)
• Page Start: 4450
• Page End: 4460
• Publication Date: 2021-03-11
• Subjects: image segmentation -- cellular biophysics -- medical image processing -- blood -- feature extraction -- image classification -- optimisation -- convolutional neural nets -- neural net architecture -- deep learning (artificial intelligence) -- binary codes -- performance evaluation; classification accuracy -- fine‐tuning process -- state‐of‐the‐art peripheral blood cell image recognition system -- cat swarm‐based optimised convolutional neural networks -- peripheral blood cell data -- parameter tuning problems -- optimisation problem -- salp swarm optimiser -- cat swarm optimiser -- classification performance improvement -- global classification accuracy -- automatic classification -- DSCSS‐optimised CNN approach -- blood cell image data -- binary coding technique -- DSSCS‐CNN method -- hybrid disruption‐based salp‐swarm and cat‐swarm -- deep learning architecture -- hyperparameter problem -- Vgg‐16 architecture; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.0370
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : In this study, an efficient a deep learning architecture‐based peripheral blood cell image recognition and classification is proposed using hybrid disruption‐based salp‐swarm and cat swarm (DSSCS)‐based optimized convolutional neural networks (DSSCSCNNs) method. The DSSCSCNN method is employed to overcome the hyperparameter problem in CNN and it also helps this model to work on small peripheral blood cell data sets. In the DSSCSCNN method, the authors develop a binary coding technique that converts parameter tuning problems into an optimization problem. The original salp swarm algorithm is enhanced using a disruptive operator and salp swarm optimization algorithm to form the novel DSSCS algorithm which increases the diversity of the search space by providing higher classification accuracy. In this study, the CNNs use Vgg‐16 architecture is used for training purposes. The global classification accuracy obtained when trained with the Vgg‐16 model is 97%. This method establishes a fine‐tuning process to develop a classifier trained using 15, 976 images acquired from clinical practice. The proposed model gives improved performance in terms of accuracy, specificity, and sensitivity. In the WBC determination, the proposed approach has shown 100% achievement. It also provides the best overall classification accuracy of 99%.