Modified Salp Swarm Algorithm With Deep Learning Based Gastrointestinal Tract Disease Classification on Endoscopic Images

Nowadays, the analysis of gastrointestinal (GI) tract disease utilzing endoscopic image classification becomes an active research activity from biomedical sector. The latest technology in medical imaging is Wireless Capsule Endoscopy (WCE) for diagnosing diseases namely bleeding, ulcer, polyp, and so on. Manual diagnoses will be time taking tough practitioner; thus, authors have designed computerized approaches classifying detecting such diseases. Many groups presented various machine learning (ML) processing methods GI recent times. Conventional data augmentation are integrated with adjusted pre-trained deep convolutional neural networks (CNNs) WCI images. This study presents a Modified Salp Swarm Algorithm Deep Learning based Gastrointestinal Tract Disease Classification (MSSADL-GITDC) on Endoscopic Images. MSSADL-GITDC technique mainly focuses examination WCE images GIT classification. To accomplish this, applies median filtering (MF) smoothening. designs improved capsule network (CapsNet) model feature extraction where CapsNet modified by class attention layer (CAL). Moreover, MSSA hyperparameter tuning process performed to improve efficiency model. For classification, belief extreme (DBN-ELM) was used. Finally, backpropagation applied supervised fine DBN-ELM experimental validation takes place Kvasir-V2 database reported betterment maximum accuracy 98.03%.