Brain tumor detection in the Spark system

<span lang="EN-US">Machine learning (ML) and computer vision systems revolutionized the world, especially deep (DL) for convolutional neural networks, which has proven breakthroughs in brain tumor (BT) diagnosis. This study investigates a network (CNN) approach image classification BT detection using EfficientNetB1 architecture with global average pooling (GAP) layers big data setting. A layer is done softMax layer. The system created Apache Spark environment. unified ultra-fast analysis engine large-scale processing. It mainly dedicated to (DL). Experiments are carried out magnetic resonance imaging (MRI) dataset containing 3,264 MRI scans predict performance of model. decomposed into two datasets. model's was assessed compared existing models, it yielded high precision, f1-score. In our work, we have achieved an accuracy 97% 98% on 3,064 images.</span>