Brain Tumor Classification Using Fine-Tuned GoogLeNet Features and Machine Learning Algorithms: IoMT Enabled CAD System

In the healthcare research community, Internet of Medical Things (IoMT) is transforming the healthcare system into the world of the future internet. In IoMT enabled Computer aided diagnosis (CAD) system, the Health-related information is stored via the internet, and supportive data is provided to the patients. The development of various smart devices is interconnected via the internet, which helps the patient to communicate with a medical expert using IoMT based remote healthcare system for various life threatening diseases, e.g., brain tumors. Often, the tumors are predecessors to cancers, and the survival rates are very low. So, early detection and classification of tumors can save a lot of lives. IoMT enabled CAD system plays a vital role in solving these problems. Deep learning, a new domain in Machine Learning, has attracted a lot of attention in the last few years. The concept of Convolutional Neural Networks (CNNs) has been widely used in this field. In this paper, we have classified brain tumors into three classes, namely glioma, meningioma and pituitary, using transfer learning model. The features of the brain MRI images are extracted using a pre-trained CNN, i.e. GoogLeNet. The features are then classified using classifiers such as softmax, Support Vector Machine (SVM), and K-Nearest Neighbor (K-NN). The proposed model is trained and tested on CE-MRI Figshare and Harvard medical repository datasets. The experimental results are superior to the other existing models. Performance measures such as accuracy, specificity, and F1 score are examined to evaluate the performances of the proposed model.

I. Introduction

Nowadays, remote healthcare systems are developing widely and mitigated the communication gap between patients, and medical experts. Off late, advanced technologies like smart and wearable devices have been an instrumental part of the Internet of Medical Things (IoMT) for providing aid to the remote healthcare systems. IoMT enabled computer-aided diagnosis (CAD) system helps the medical experts to analyze the patient data remotely. It is expected that IoMT enabled CAD systems will connect the smart healthcare devices remotely and share the supportive information with medical experts. On receiving the information, immediate treatment can be given to the affected patients, and their recovery rate can be monitored by the medical staff. For example, in case of brain tumor patients, IoMT enabled CAD system can provide useful information about the tumors and its types, i.e., Malignant or Benign. Thus, early detection of brain tumor plays a vital role in proper treatment and curative intent. Manual detection and classification of brain tumors is a challenging task and have high risk of error detection, therefore requiring an expert radiologist to classify these tumors. Off late, CAD systems have been really helpful in assisting the medical experts to detect and classify the brain tumors. Manual classification is quite challenging, requiring highly professional radiologist and time intensive for large Magnetic Resonant Imaging (MRI) data classification. To address this problem, automatic classification techniques are extensively studied to classify brain tumor from MR images. Brain tumor classification from MR images using CAD technique is highly reliable for its higher accuracy. In this work, authors focus on the brain tumor classification in order to classify three different types of tumors namely meningioma, glioma and pituitary.