Hybrid Multi-Descriptor and Deep Belief Network Model for Acute Lymphoblastic Leukaemia Diagnosis
Saif Ali Abd Alradha Alsaidi1, Ali Hakem Alsaeedi2,3 , Hussein Al-Khamees4,
Riyadh Rahef Nuiaa Al Ogaili1,*, Zaid Abdi Alkareem Alyasseri5,6, Mazin Abed Mohammed7
1College of Computer Science and Information Technology, Wasit University, Al-Kut, Wasit, Iraq
2Department of Computer Techniques, Imam Kadhum College, Diwaniyah, Iraq
3College of Computer Science and Information Technology, University of Al-Qadisiyah, Diwaniyah, Iraq
4College of Engineering and Technologies, Al-Mustaqbal University, Babil, Iraq
5Information Technology Research and Development Center (ITRDC), University of Kufa, Najaf, Iraq
6College of Engineering, University of Warith Al-Anbiyaa, Karbala, Iraq
7Department of Artificial Intelligence, College of Computer Science and Information Technology, University of Anbar, Anbar, 31001, Iraq
Emails: salsaidi@uowasit.edu.iq; ali.alsaeedi@qu.edu.iq; Hussein.Alkhamees@uomus.edu.iq; riyadh@uowaasit.edu.iq; zaid.alyasseri@uokufa.edu.iq; Mazinalshujeary@uoanbar.edu.iq
Abstract
The nature of images can differ in texture, contrast, illumination, noise levels, and structural patterns. The descriptor suitable for one image may not be optimal for another. Therefore, this paper proposes a new hybrid diagnostic model that combines multi-descriptor feature extraction with a Deep Belief Network. It is used to classify Acute Lymphoblastic Leukaemia. The proposed model consists of two phases: feature extraction and classification. Three descriptors, Histogram of Oriented Gradients, Scale-Invariant Feature Transform, and Convolutional Neural Network are employed in the feature extraction phase. Each descriptor captures different aspects of the image using distinct computational techniques. The Deep Belief Network was trained on each group of features individually. Three trained Deep Belief Network were produced with each data extract by descriptors. The membership function between the training set and the test data determines which DBN will be selected. The model was tested and evaluated on the 10,661 Leukaemia images of the C-NMC_Leukaemia dataset. It consists of two classes of images: 7272 images of Leukaemia cancer and 3389 of the Benign. Experimental results showed that the proposed model achieved an accuracy outperforming several recent methods. The accuracy of the proposed model reaches 96.87%, while the best accuracy of the recent works is 94.91%.
Keywords: Acute Lymphoblastic Leukaemia; Multi-Descriptor Feature Extraction; computer-aided diagnosis; Deep Belief Network; Medical Image Classification