Application of Deep Learning in Neuroradiology: Brain Haemorrhage Classification Using Transfer Learning

Abstract

In this paper, we address the problem of identifying brain haemorrhage which is considered as a tedious task for radiologists, especially in the early stages of the haemorrhage. The problem is solved using a deep learning approach where a convolutional neural network (CNN), the well-known AlexNet neural network, and also a modified novel version of AlexNet with support vector machine (AlexNet-SVM) classifier are trained to classify the brain computer tomography (CT) images into haemorrhage or nonhaemorrhage images. The aim of employing the deep learning model is to address the primary question in medical image analysis and classification: can a sufficient fine-tuning of a pretrained model (transfer learning) eliminate the need of building a CNN from scratch? Moreover, this study also aims to investigate the advantages of using SVM as a classifier instead of a three-layer neural network. We apply the same classification task to three deep networks; one is created from scratch, another is a pretrained model that was fine-tuned to the brain CT haemorrhage classification task, and our modified novel AlexNet model which uses the SVM classifier. The three networks were trained using the same number of brain CT images available. The experiments show that the transfer of knowledge from natural images to medical images classification is possible. In addition, our results proved that the proposed modified pretrained model “AlexNet-SVM” can outperform a convolutional neural network created from scratch and the original AlexNet in identifying the brain haemorrhage.

CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection

“…Finally, a layer is added after fully-connected layers to classify the given data. This last layer classifies 1000 objects using the Softmax function [54] , [55] , [56] .…”

“…Although the new dataset differs from the network’s previous training data content, the low-level features are similar. By transferring the parameters of the pre-trained model, the new model can gain a powerful feature extraction capability, and the training calculations and memory cost of the new model can be reduced [55] . An example architecture for a transfer learning is shown in Fig.…”

A Preliminary Intergenerational Photo Conversation Support System based on Fine-tuning VGG16 Model

“…Although photos have been augmented on the content and number of photos, the data set is still too small for a deep learning model. For small amounts of data, data augmentation, transfer learning, fine-tuning, or a combination of several methods is generally used as in [21][22][23][24]. It used rotation, skewing and elastic distortion augmentation methods for images and then used a pre-trained CNN model as feature extractor and SVM as a category classifier.…”

Deep Ensemble Model for Classification of Novel Coronavirus in Chest X-Ray Images

“…These models have shown superior generalization ability to solve complex problems of computer-vision, especially in the biological and medical fields such as medical image identification [ 39 ], organs recognition [ 40 ], bacterial colony classification [ 35 , 39 ], and disease identification [ 41 ]. CNNs have shown exceptional results in medical imaging domain than other traditional networks [ 41 , 42 ].…”