Wireless Capsule Endoscopic Image Classification using Seeker Optimization Algorithm with Deep Learning Model

Wireless Capsule Endoscopy (WCE) is a non-invasive diagnostic imaging algorithm used to examine the gastrointestinal (GI) tract. The WCE is a small device that is swallowed and captures images of the GI tract as it passes through the digestive system. These images can be used to diagnose various GI disorders, as well as celiac, ulcerative colitis, and crohn ailments. Deep learning techniques have been effectively applied for the image classification in various domains, including medical imaging. In the case of WCE, deep learning can be used to classify the images captured by the device to aid in diagnosis. This research study focuses on the design of Wireless Capsule Endoscopic Image Classification using Seeker Optimization Algorithm with Deep Learning (WCEIC-SOADL) technique. The proposed WCEIC-SOADL model employs median filtering (MF) technique. Besides, the EfficientNet-B0 model is utilized for extracting feature vectors and the SOA can be applied as a hyperparameter optimizer. Moreover, the Elman Neural Network (ENN) approach was exploited to perform classification process. A total set of stimulations were achieved to depict the promising achievement of the WCEIC-SOADL model. The relative research accentuated the superior outcomes of the WCEIC-SOADL method over recent DL algorithms.