Whale Optimization-Driven Generative Convolutional Neural Network Framework for Anaemia Detection from Blood Smear Images

Anaemia is a frequent blood disorder marked by reduction in the quantity of haemoglobin or number red cells blood. Quick and accurate anaemia detection crucial for fast action effective treatment. In this research, we provide new structure called Whale Optimization-Driven Generative Convolutional Neural Network (WO-GCNN) using smear pictures. To increase accuracy, WO-GCNN system combines strength generative models convolutional neural networks (CNNs). order to create artificial images learn underlying data distribution, models, such as Adversarial Networks (GANs), are used. Improve functionality applying Optimisation Algorithm (WOA), which based on hunting behaviours humpback whales. optimal set CNN weights, WOA effectively achieves compromise between exploitation exploration. The framework accelerates convergence speed increases overall performance incorporating into training process. On sizable dataset pictures obtained from clinical settings, assess suggested system. A highly approach early identification produced combining CNNs with optimisation. By enabling identification, proposed has potential have substantial impact field medical image analysis enhance patient care. It can be useful tool personnel, supporting them making decisions giving patients urgent interventions.