WOA-HDCN-SWS: whale optimization algorithm based hierarchical dense connection network for the prognosis of Sturge-Weber syndrome

One of the rare neurocutaneous disorder marked by port-wine stains and neurological deficits is called Sturge-Weber Syndrome (SWS). The manual diagnosis of brain disorders involves an extensive amount of time and relies significantly on the availability of domain experts. Building efficient automated methods for the recognition and categorization of multiple kinds of neurological disorders is therefore crucial. AI advancements enhance its management by improving diagnostics, surgical planning, and outcomes, supporting multidisciplinary approaches to address seizures, cognitive impairments, and motor deficits effectively. Therefore, this study proposes to present a novel and efficient approach designed using the combination of swarm optimization based technique and transfer learning (TL) model. The purpose is to classify SWS in three types by processing MRI images of the brain. Whale Optimization Algorithm (WOA) method is applied for the optimal feature selection in medical image and then classified using Hierarchical Dense Connection Network-201 (HDCN-201) model.The effectiveness of the proposed approach is assessed using several performance metrics, such as accuracy, precision, recall, f1-score, and Cohen Kappa score. The findings showed that the proposed approach performed with an accuracy of 97.19%. As a result, the suggested method precisely detects SWS and can aid physicians in making an early diagnosis.