A novel enhanced softmax loss function for brain tumour detection using deep learning
| Autor: | Sunil Maharjan, Abeer Alsadoon, Thair Al-Dala'in, Omar Hisham Alsadoon, P. W. C. Prasad |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0301 basic medicine
Computer science Neuroimaging Overfitting Convolutional neural network Multiclass classification 03 medical and health sciences 0302 clinical medicine Deep Learning Image Interpretation Computer-Assisted Humans Artificial neural network business.industry Brain Neoplasms General Neuroscience Deep learning Pattern recognition Sigmoid function Magnetic Resonance Imaging ComputingMethodologies_PATTERNRECOGNITION 030104 developmental biology Binary classification Softmax function Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | Journal of neuroscience methods. 330 |
| ISSN: | 1872-678X |
| Popis: | Background and Aim In deep learning, the sigmoid function is unsuccessfully used for the multiclass classification of the brain tumour due to its limit of binary classification. This study aims to increase the classification accuracy by reducing the risk of overfitting problem and supports multi-class classification. The proposed system consists of a convolutional neural network with modified softmax loss function and regularization. Results Classification accuracy for the different types of tumours and the processing time were calculated based on the probability score of the labeled data and their execution time. Different accuracy values and processing time were obtained when testing the proposed system using different samples of MRI images. The result shows that the proposed solution is better compared to the other systems. Besides, the proposed solution has higher accuracy by almost 2 % and less processing time of 40∼50 ms compared to other current solutions. Conclusion The proposed system focused on classification accuracy of the different types of tumours from the 3D MRI images. This paper solves the issues of binary classification, the processing time, and the issues of overfitting of the data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect