کنفرانس مهندسی برق ایران

صفحه اصلی / سی امین کنفرانس بین المللی مهندسی برق

Medial Residual Encoder Layers for Classification of Brain Tumors in Magnetic Resonance Images

نویسندگان :

Zahra Sobhaninia¹ Nader Karimi² Pejman Khadivi³ Shadrokh Samavi⁴

1- دانشگاه صنعتی اصفهان 2- دانشگاه صنعتی اصفهان 3- دانشگاه صنعتی اصفهان 4- دانشگاه صنعتی اصفهان

کلمات کلیدی :

Deep learning،Brain tumor classiﬁcation،Image classiﬁcation،Residual network

چکیده :

Correct and timely diagnosis of the brain tumor will make treatment more effective . To date, several image classification approaches have been proposed to aid diagnosis and treatment. In this work a deep learning approach has developed to increase tumor type classification accuracy in MRI images by considering medical image dataset limitation. In this regard, we offer a system based on deep learning, containing encoder blocks. In proposed approach in addition to more organized and simplicity architecture, residual approach used. encoder blocks are fed with post-max-pooling features as residual learning. Experimental evaluations of our approach shows promising results by improving the tumor classification accuracy in Magnetic resonance imaging (MRI) images using a limited medical image dataset. Experimental evaluations of this model on a dataset consisting of 3064 MR images show 95.98% accuracy, which is better than previous studies on this database.