Magnetic Resonance Imaging (MRI) aims to identify a tumor at earlier stages of the disease, when treatment can be more successful. Despite the existence of screening programmes worldwide, the interpretation of MRIs is affected by high rates of false positives and false negative. Recently deep learning has been playing a major role in the field of computer aided diagnosis. One of its applications is the reduction of human judgment in the diagnosis of diseases. Especially, brain tumor diagnosis requires high accuracy, where errors in judgment may lead to disaster. For this reason, brain tumor classification is an important challenge for medical applications. Currently several methods exist for tumor classification but they all lack high accuracy. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in predicting if an MRI contains or not a brain tumor. To assess its performance in the clinical setting. We show an absolute accuracy of 76.8% in predicting if an MRI contains a cancer or a general non-tumor pathology.
lrnzgiusti/Heterogeneous_XNN
Magnetic Resonance Imaging (MRI) for Brain Tumor Classification
PythonApache-2.0