Abstract
White Blood Cell (WBC) Leukaemia is caused by excessive production of leukocytes in the bone marrow, and image-based detection of malignant WBCs is important for its detection. Convolutional Neural Networks (CNNs) present the current state-of-the-art for this type of image classification, but their computational cost for training and deployment can be high. We here present an improved hybrid approach for efficient classification of WBC Leukemia. We first extract features from WBC images using VGGNet, a powerful CNN architecture, pre-trained on ImageNet. The extracted features are then filtered using a statistically enhanced Salp Swarm Algorithm (SESSA). This bio-inspired optimization algorithm selects the most relevant features and removes highly correlated and noisy features. We applied the proposed approach to two public WBC Leukemia reference datasets and achieve both high accuracy and reduced computational complexity. The SESSA optimization selected only 1 K out of 25 K features extracted with VGGNet, while improving accuracy at the same time. The results are among the best achieved on these datasets and outperform several convolutional network models. We expect that the combination of CNN feature extraction and SESSA feature optimization could be useful for many other image classification tasks.
Highlights
IntroductionIn17, transfer learning was used to overcome limitations of previously published models for breast cancer detection in cytology images on standard benchmark datasets
Other work builds on a combination of multiple deep learning architectures to improve the usefulness of transfer learning for cell-based image classification[18,19]
We developed a Statistically Enhanced Salp Swarm Algorithm (SESSA) to improve classification performance by excluding correlated and noisy features and selecting only the most relevant features
Summary
In17, transfer learning was used to overcome limitations of previously published models for breast cancer detection in cytology images on standard benchmark datasets These approaches have in common that they use a large number of features (up to 100 K) from pre-trained CNN models. The main focus of our manuscript is to present a novel method for image feature selection based on improved swarm optimization and to show that it outperforms many existing approaches for classification of WBCs to detect leukemia. We focus on this application since it is a challenging problem with high medical relevance, for which good benchmark datasets are available. Such methods will play an increasingly important role in image-based clinical diagnosis in the near future
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
