Hybrid Metaheuristics With Deep Learning-Based Fusion Model for Biomedical Image Analysis

Biomedical image analysis has played a pivotal role in modern healthcare by facilitating automated analysis and interpretation of medical images. Biomedical image classification is the process of automatically labelling or categorizing medical images based on their content. In recent years, this field has received considerable attention because of the abundance of bio-medical image data and the potential for deep learning (DL) algorithms to assist medical staff in identifying diseases and making treatment decisions. DL methods are mostly convolutional neural networks (CNN) has illustrated outstanding performance in analyzing and classifying biomedical images. Therefore, this study presents a new Hybrid Metaheuristics with Deep Learning based Fusion Model Biomedical Image Analysis (HMDL-MFMBIA) technique. The HMDL-MFMBIA technique initially performs image pre-processing and Swin-UNet-based segmentation. Besides, a fusion of multiple DL-based feature extractors takes place using Xception and Residual Network (ResNet) model. Moreover, a hybrid salp swarm algorithm (HSSA) was employed for the optimal hyperparameter selection of the DL models. Finally, the gated recurrent unit (GRU) algorithm can be exploited for the detection and classification of bio-medical images. A widespread of simulated is conducted to establish the enhanced biomedical image classification results of the HMDL-MFMBIA method. The simulation outcomes inferred the greater outcome of the HMDL-MFMBIA algorithm over other DL models.