Optimal Deep Transfer Learning-Based Human-Centric Biomedical Diagnosis for Acute Lymphoblastic Leukemia Detection

Abstract

Human-centric biomedical diagnosis (HCBD) becomes a hot research topic in the healthcare sector, which assists physicians in the disease diagnosis and decision-making process. Leukemia is a pathology that affects younger people and adults, instigating early death and a number of other symptoms. Computer-aided detection models are found to be useful for reducing the probability of recommending unsuitable treatments and helping physicians in the disease detection process. Besides, the rapid development of deep learning (DL) models assists in the detection and classification of medical-imaging-related problems. Since the training of DL models necessitates massive datasets, transfer learning models can be employed for image feature extraction. In this view, this study develops an optimal deep transfer learning-based human-centric biomedical diagnosis model for acute lymphoblastic detection (ODLHBD-ALLD). The presented ODLHBD-ALLD model mainly intends to detect and classify acute lymphoblastic leukemia using blood smear images. To accomplish this, the ODLHBD-ALLD model involves the Gabor filtering (GF) technique as a noise removal step. In addition, it makes use of a modified fuzzy c-means (MFCM) based segmentation approach for segmenting the images. Besides, the competitive swarm optimization (CSO) algorithm with the EfficientNetB0 model is utilized as a feature extractor. Lastly, the attention-based long-short term memory (ABiLSTM) model is employed for the proper identification of class labels. For investigating the enhanced performance of the ODLHBD-ALLD approach, a wide range of simulations were executed on open access dataset. The comparative analysis reported the betterment of the ODLHBD-ALLD model over the other existing approaches.

Biomedical Diagnosis of Leukemia Using a Deep Learner Classifier

“…Even so, our approach detects and classifies ALL and AML with higher accuracy, precision, and recall. ese results indicate that the proposed algorithm herein outperforms the implemented method in [22].…”

“…In [ 22 ], Hamza et al implemented a method to detect and classify ALL using an optimal deep transfer learning method. Blood smear images were utilized for detection and classification purposes.…”

BO-ALLCNN: Bayesian-Based Optimized CNN for Acute Lymphoblastic Leukemia Detection in Microscopic Blood Smear Images

“…It records an equal classification accuracy as the Decision Tree classifier of [ 44 ]. However, our Bayesian-based optimized CNN outperforms all optimized deep learning-based leukemia detectors in [ 53 , 54 , 55 , 56 ]. In general, the comparison reveals that the introduced Bayesian-based optimized CNN achieves superior classification performance over existing deep learning systems developed for ALL diagnosis.…”

“…Recent methods used for CNN structure optimization in the medical field include the hybrid sine–cosine algorithm [ 49 ], chimp optimization algorithm [ 50 ], and Whale Optimization [ 51 ]. Some recent studies used several optimization approaches to select optimal features for leukemia classification problems [ 52 , 53 , 54 , 55 , 56 ]. For instance, Abdeldaim et al [ 53 ] used the bio-inspired Salp Swarm Optimization Algorithm to select the optimal features from the classification of ALL using several classical ML classifiers.…”

“…On the ALL-IDB2 database, the introduced methods recorded 93.5% for accuracy, 95.3% for the sensitivity, and 93.9% for the specificity, respectively. The work of Hamza et al [ 56 ] utilized the competitive swarm optimization (CSO) algorithm to optimize the hyperparameters of an attention-based long-short term memory model for the identification of ALL. They used the EfficientNetB0 algorithm to extract and select features from smear images after noise filtering and segmentation.…”