Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance quality medical images by intensifying radiation dose. High dose provokes cancer, which forces experts to use limited radiation. Using abrupt generates noise in CT scans. propose an optimal Convolutional Neural Network model Gaussian removed better classification and increased training accuracy. Experimental demonstration on LUNA16 dataset size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, area under ROC curve (AUC) performance are taken as evaluation metrics. conducted a comparison numerous platforms, like Apache Spark, GPU, CPU, depreciate time without compromising accuracy percentage. Our results show integrated with deep learning framework, suitable parallel computation high