Detection and Automated Classification of Brain Tumor Types in MRI Images using Convolutional Neural Network with Grid Search Optimization

Brain tumor is a severe cancer disease caused by uncontrollable and abnormal partitioning of cells. Timely disease detection and treatment plans lead to the increased life expectancy of patients. Automated detection and classification of brain tumor are a more challenging process which is based on the clinician’s knowledge and experience. For this fact, one of the most practical and important techniques is to use deep learning. Recent progress in the ﬁelds of deep learning has helped the clinician’s in medical imaging for medical diagnosis of brain tumor. In this paper, we present a comparison of Deep Convolutional Neural Network models for automatically binary classification query MRI images dataset with the goal of taking precision tools to health professionals based on fined recent versions of DenseNet, Xception, NASNet-A, and VGGNet. The experiments were conducted using an MRI open dataset of 3,762 images. Other performance measures used in the study are the area under precision, recall, and specificity.

Download Full-text

Deep Learning Based Tumor Type Classification Using Gene Expression Data

10.1101/364323 ◽

2018 ◽

Cited By ~ 4

Author(s):

Boyu Lyu ◽

Anamul Haque

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Tumor Type ◽

Differential Analysis ◽

Rna Seq ◽

Heat Map ◽

Standard Practices ◽

Tumor Types ◽

Pan Cancer

ABSTRACTDifferential analysis occupies the most significant portion of the standard practices of RNA-Seq analysis. However, the conventional method is matching the tumor samples to the normal samples, which are both from the same tumor type. The output using such method would fail in differentiating tumor types because it lacks the knowledge from other tumor types. Pan-Cancer Atlas provides us with abundant information on 33 prevalent tumor types which could be used as prior knowledge to generate tumor-specific biomarkers. In this paper, we embedded the high dimensional RNA-Seq data into 2-D images and used a convolutional neural network to make classification of the 33 tumor types. The final accuracy we got was 95.59%, higher than another paper applying GA/KNN method on the same dataset. Based on the idea of Guided Grad Cam, as to each class, we generated significance heat-map for all the genes. By doing functional analysis on the genes with high intensities in the heat-maps, we validated that these top genes are related to tumor-specific pathways, and some of them have already been used as biomarkers, which proved the effectiveness of our method. As far as we know, we are the first to apply convolutional neural network on Pan-Cancer Atlas for classification, and we are also the first to match the significance of classification with the importance of genes. Our experiment results show that our method has a good performance and could also apply in other genomics data.

Download Full-text

Classification of Brain Tumor using Convolutional Neural Networks

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.c5995.029320 ◽

2020 ◽

Vol 9 (3) ◽

pp. 2841-2845

Keyword(s):

Neural Network ◽

Brain Tumor ◽

Convolutional Neural Network ◽

Medical Science ◽

Activation Functions ◽

Case Scenario ◽

Aggressive Disease ◽

Fully Connected ◽

The Brain

In medical science, brain tumor is the most common and aggressive disease and is known to be risk factors that have been confirmed by research. A brain tumor is the anomalous development of cell inside the brain. One conventional strategy to separate brain tumors is by reviewing the MRI pictures of the patient's mind. In this paper, we have designed a Convolutional Neural Network (CNN) to perceive whether the image contains tumor or not. We have designed 5 different CNN and examined each design on the basis of convolution layers, max-pooling, and flattening layers and activation functions. In each design we have made some changes on layers i.e. using different pooling layers in design 2 and 4, using different activation functions in design 2 and 3, and adding more Fully Connected layers in design 5. We examine their results and compare it with other designs. After comparing their results we find a best design out of 5 based on their accuracy. Utilizing our Convolutional neural network, we could accomplish a training accuracy and validation accuracy of design 3 at 100 epochs is 99.99% and 92.34%, best case scenario.

Download Full-text