Brain tumor classification for MR images using transfer learning and fine-tuning

[Display omitted] The proposed research framework for brain tumor MR images classification using pre-trained deep CNN (VGG19) transfer learning and block-wise fine-tuning. •In this research, we have focused on multiclass brain tumors classification for MR images using pre-trained Convolutional Neural Network (CNN) and adopted transfer learning.•To achieve enhance classification results, we proposed block-wise fine-tuning strategy, gradually goes deep down into earlier blocks of the CNN, and monitor the performance improvement.•The proposed method is evaluated on publically available CE-MRI dataset consists of three types of brain tumors (glioma, meningioma, and pituitary) with highest percentage among all brain tumors in clinical practice.•We are using pre-trained CNN because of the small sample size of the CE-MRI dataset.•We have adopted five-fold cross-validation test to ensure the robustness of proposed method. We have performed numerous experiments for brain tumor classification, evaluated the performance of the proposed method, compared our results with state-of-the-art conventional machine learning and deep learning using CNNs for brain tumor classification on the same dataset of CE-MRI. Accurate and precise brain tumor MR images classification plays important role in clinical diagnosis and decision making for patient treatment. The key challenge in MR images classification is the semantic gap between the low-level visual information captured by the MRI machine and the high-level information perceived by the human evaluator. The traditional machine learning techniques for classification focus only on low-level or high-level features, use some handcrafted features to reduce this gap and require good feature extraction and classification methods. Recent development on deep learning has shown great progress and deep convolution neural networks (CNNs) have succeeded in the images classification task. Deep learning is very powerful for feature representation that can depict low-level and high-level information completely and embed the phase of feature extraction and classification into self-learning but require large training dataset in general. For most of the medical imaging scenario, the training datasets are small, therefore, it is a challenging task to apply the deep learning and train CNN from scratch on the small dataset. Aiming this problem, we use pre-trained deep CNN model and propose a block-wise fine-tuning strategy based on transfer learning.