ABSTRACT
In this trending world of data loads, the medical field has also become a significant boom in all areas. Most of the areas have been refined to cope with the hi-tech world except for some areas where storage has been a great issue. Those areas in the medical field are found out to revamp its operation through the cloud-based network. Radiologists and physicians are one to one entity that depends upon each has many challenges in which neurological disorders took enough area. Several areas in image analysis are yet to be nourished especially segmentation and classification. In the arena of medical image analysis, there is high scope in segmentation and classification. The deep learning (DL)-based approach is proposed for analyzing and finding neurocutaneous syndromes. The new concept of cloud-based convolution neural network (CCNN) has been proposed. The noteworthy of this work is to develop a more accurate result compared to the conventional approach. This type of network learning is a different approach of certain types of neurocutaneous syndromes. A decision tree classification is an added advantage in CNN which gives solution for many different types of symptoms other than the MRI images. A set of pre-trained GoogLeNet libraries is used for the analysis of MRI images for this work. This idea achieves almost an accuracy of 95%, which really overcomes the current scenarios. In a practical aspect, the clinical findings itself confirm the syndrome, for more accuracy in the result. This study is a useful technique in areas where medical images are limited to the process. This chapter provides you a more innovative cloud convolutional neural network (CNN) for neurocutaneous syndrome in the biomedical field, which is under severe research.
