Brain tumor classification using deep CNN features via transfer learning

Brain tumor classification is an important problem in computer-aided diagnosis (CAD) for medical applications. This paper focuses on a 3-class classification problem to differentiate among glioma, meningioma and pituitary tumors, which form three prominent types of brain tumor. The proposed classification system adopts the concept of deep transfer learning and uses a pre-trained GoogLeNet to extract features from brain MRI images. Proven classifier models are integrated to classify the extracted features. The experiment follows a patient-level five-fold cross-validation process, on MRI dataset from figshare. The proposed system records a mean classification accuracy of 98%, outperforming all state-of-the-art methods. Other performance measures used in the study are the area under the curve (AUC), precision, recall, F-score and specificity. In addition, the paper addresses a practical aspect by evaluating the system with fewer training samples. The observations of the study imply that transfer learning is a useful technique when the availability of medical images is limited. The paper provides an analytical discussion on misclassifications also.

[1]  Ling Shao,et al.  Transfer Learning for Visual Categorization: A Survey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Ümit Budak,et al.  Transfer learning based histopathologic image classification for breast cancer detection , 2018, Health Information Science and Systems.

[3]  Adam Krzyzak,et al.  Mass detection in digital breast tomosynthesis data using convolutional neural networks and multiple instance learning , 2018, Comput. Biol. Medicine.

[4]  Tati L. R. Mengko,et al.  Brain Tumor Classification Using Convolutional Neural Network , 2018, IFMBE Proceedings.

[5]  Hui Feng,et al.  CNN-SVM for Microvascular Morphological Type Recognition with Data Augmentation , 2016, Journal of Medical and Biological Engineering.

[6]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Jianfeng Lu,et al.  Content-Based Brain Tumor Retrieval for MR Images Using Transfer Learning , 2019, IEEE Access.

[8]  Ikhlas Abdel-Qader,et al.  Brain Tumor Classification via Statistical Features and Back-Propagation Neural Network , 2018, 2018 IEEE International Conference on Electro/Information Technology (EIT).

[9]  Sanjeev Kumar,et al.  Classification of Brain MRI Tumor Images: A Hybrid Approach , 2017, ITQM.

[10]  Yu-Chen Chen,et al.  A Deep Learning-Based Radiomics Model for Differentiating Benign and Malignant Renal Tumors1 , 2018, Translational oncology.

[11]  Ulas Bagci,et al.  Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches , 2018, IEEE Transactions on Medical Imaging.

[12]  Erik Blasch,et al.  Combining Convolutional and Recurrent Neural Networks for Human Skin Detection , 2017, IEEE Signal Processing Letters.

[13]  Rachna Jain,et al.  Convolutional neural network based Alzheimer’s disease classification from magnetic resonance brain images , 2019, Cognitive Systems Research.

[14]  Hedieh Sajedi,et al.  Brain Tumor Classification via Convolutional Neural Network and Extreme Learning Machines , 2018, 2018 8th International Conference on Computer and Knowledge Engineering (ICCKE).

[15]  Yang Yang,et al.  Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning , 2018, Front. Neurosci..

[16]  Odelin Charron,et al.  Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network , 2018, Comput. Biol. Medicine.

[17]  Qianjin Feng,et al.  Enhanced Performance of Brain Tumor Classification via Tumor Region Augmentation and Partition , 2015, PloS one.

[18]  Qianjin Feng,et al.  Retrieval of Brain Tumors by Adaptive Spatial Pooling and Fisher Vector Representation , 2016, PloS one.

[19]  Lawrence O. Hall,et al.  Exploring deep features from brain tumor magnetic resonance images via transfer learning , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[20]  Konstantinos N. Plataniotis,et al.  Capsule Networks for Brain Tumor Classification Based on MRI Images and Coarse Tumor Boundaries , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  Chao Yang,et al.  A Survey on Deep Transfer Learning , 2018, ICANN.

[22]  U. Rajendra Acharya,et al.  Application of deep transfer learning for automated brain abnormality classification using MR images , 2019, Cognitive Systems Research.

[23]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[24]  Lawrence O. Hall,et al.  Fine-tuning convolutional deep features for MRI based brain tumor classification , 2017, Medical Imaging.

[25]  Tao Zhou,et al.  Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs , 2018, Comput. Biol. Medicine.

[26]  Geethu Mohan,et al.  MRI based medical image analysis: Survey on brain tumor grade classification , 2018, Biomed. Signal Process. Control..