Optimal Deep Transfer Learning Model for Histopathological Breast Cancer燙lassification

Earlier recognition of breast cancer is crucial to decrease the severity and optimize survival rate. One commonly utilized imaging modalities for histopathological images. Since manual inspection images a challenging task, automated tools using deep learning (DL) artificial intelligence (AI) approaches need be designed. The latest advances DL models help in accomplishing maximum image classification performance several application areas. In this view, study develops Deep Transfer Learning with Rider Optimization Algorithm Histopathological Classification Breast Cancer (DTLRO-HCBC) technique. proposed DTLRO-HCBC technique aims categorize existence To accomplish this, undergoes pre-processing data augmentation increase quantitative analysis. Then, optimal SqueezeNet model employed feature extractor hyperparameter tuning process carried out Adadelta optimizer. Finally, rider optimization feed forward neural network (RO-DFFNN) was classification. RO algorithm applied optimally adjusting weight bias values DFFNN For demonstrating greater approach, sequence simulations were outcomes reported its promising over current state art approaches.