publications

2023

1. IJIE

   Investigation of ConViT on COVID-19 Lung Image Classification and the Effects of Image Resolution and Number of Attention Heads

   Pun Liang Thon, Joel Chia Ming Than, Norliza M. Noor, and 2 more authors

   International Journal of Integrated Engineering, Jul 2023

   Abs DOI Bib

   COVID-19 has been one of the popular foci in the research community since its first outbreak in China, 2019. Radiological patterns such as ground glass opacity (GGO) and consolidations are often found in CT scan images of moderate to severe COVID-19 patients. Therefore, a deep learning model can be trained to distinguish COVID-19 patients using their CT scan images. Convolutional Neural Networks (CNNs) has been a popular choice for this type of classification task. Another potential method is the use of vision transformer with convolution, resulting in Convolutional Vision Transformer (ConViT), to possibly produce on par performance using less computational resources. In this study, ConViT is applied to diagnose COVID-19 cases from lung CT scan images. Particularly, we investigated the relationship of the input image pixel resolutions and the number of attention heads used in ConViT and their effects on the model’s performance. Specifically, we used 512x512, 224x224 and 128x128 pixels resolution to train the model with 4 (tiny), 9 (small) and 16 (base) number of attention heads used. An open access dataset consisting &nbsp;of 2282 COVID-19 CT images and 9776 Normal CT images from Iran is used in this study. By using 128x128 image pixels resolution, training using 16 attention heads, the ConViT model has achieved an accuracy of 98.01%, sensitivity of 90.83%, specificity of 99.69%, positive predictive value (PPV) of 95.58%, negative predictive value (NPV) of 97.89% and F1-score of 94.55%. The model has also achieved improved performance over other recent studies that used the same dataset. In conclusion, this study has shown that the ConViT model can play a meaningful role to complement RT-PCR test on COVID-19 close contacts and patients.</p>

   @article{thonInvestigationConViTCOVID192023,
     title = {Investigation of {{ConViT}} on {{COVID-19 Lung Image Classification}} and the {{Effects}} of {{Image Resolution}} and {{Number}} of {{Attention Heads}}},
     author = {Thon, Pun Liang and Than, Joel Chia Ming and M. Noor, Norliza and Han, Jun and Then, Patrick},
     year = {2023},
     month = jul,
     journal = {International Journal of Integrated Engineering},
     volume = {15},
     number = {3},
     pages = {54--63},
     doi = {10.30880/ijie.2023.15.03.005},
   }

2022

1. IEEE EMBS IECBES

   Explainable COVID-19 Three Classes Severity Classification Using Chest X-Ray Images

   P. L. Thon, J. C. M. Than, R. M. Kassim, and 3 more authors

   In 2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Dec 2022

   Abs DOI Bib

   COVID-19 has been raging for almost three years ever since its first outbreak. It is without a doubt that it is a common human goal to end the pandemic and how it was before it started. Many efforts have been made to work toward this goal. In computer vision, works have been done to aid medical professionals into faster and more effective procedures when dealing with the disease. For example, disease diagnosis and severity prediction using chest imaging. At the same time, vision transformer is introduced and quickly stormed its way into one of the best deep learning models ever developed due to its ability to achieve good performance while being resources friendly. In this study, we investigated the performance of ViT on COVID19 severity classification using an open-source CXR images dataset. We applied different augmentation and transformation techniques to the dataset to see ViT’s ability to learn the features of the different severity levels of the disease. It is concluded that training ViT using the horizontally flipped images added to the original dataset gives the best overall accuracy of 0.862. To achieve explainability, we have also applied Grad-CAM to the best performing model to make sure it is looking at relevant region of the CXR image upon predicting the class label.

   @inproceedings{thonExplainableCOVID19Three2022,
     title = {Explainable {{COVID-19 Three Classes Severity Classification Using Chest X-Ray Images}}},
     booktitle = {2022 {{IEEE-EMBS Conference}} on {{Biomedical Engineering}} and {{Sciences}} ({{IECBES}})},
     author = {Thon, P. L. and Than, J. C. M. and Kassim, R. M. and Yunus, A. and Noor, N. M. and Then, P.},
     year = {2022},
     month = dec,
     pages = {312--317},
     publisher = {IEEE},
     address = {Kuala Lumpur, Malaysia},
     doi = {10.1109/IECBES54088.2022.10079667},
     isbn = {978-1-6654-9469-4},
   }

2021

1. IEEE NBEC

   Preliminary Study on Patch Sizes in Vision Transformers (ViT) for COVID-19 and Diseased Lungs Classification

   Joel C. M. Than, Pun Liang Thon, Omar Mohd Rijal, and 4 more authors

   In 2021 IEEE National Biomedical Engineering Conference (NBEC), Nov 2021

   Abs DOI Bib

   COVID-19 and lung diseases have been the major focus of research currently due to the pandemic’s reach and effect. Deep Learning (DL) is playing a large role today in various fields from disease classification to drug response identification. The conventional DL method used for images is the Convolutional Neural Network (CNN). A potential method that will replace the usage of CNNs is Transformer specifically Vision Transformers (ViT). This study is a preliminary exploration to determine the performance of using ViT on diseased lungs, COVID-19 infected lungs, and normal lungs. This study was performed on two datasets. The first dataset was a publicly accessible dataset from Iran that has a large cohort of patients. The second dataset was a Malaysian dataset. These images were utilized to verify the usage of ViT and its effectiveness. Images were segregated into several sized patches (16x16, 32x32, 64x64, 128x128, 256x256) pixels. To determine the performance of ViT method, performance metrics of accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) and F1-score. From the results of this study, ViT is a promising method with a peak accuracy of 95.36%.

   @inproceedings{thanPreliminaryStudyPatch2021,
     title = {Preliminary {{Study}} on {{Patch Sizes}} in {{Vision Transformers}} ({{ViT}}) for {{COVID-19}} and {{Diseased Lungs Classification}}},
     booktitle = {2021 {{IEEE National Biomedical Engineering Conference}} ({{NBEC}})},
     author = {Than, Joel C. M. and Thon, Pun Liang and Rijal, Omar Mohd and Kassim, Rosminah M. and Yunus, Ashari and Noor, Norliza M. and Then, Patrick},
     year = {2021},
     month = nov,
     pages = {146--150},
     publisher = {IEEE},
     doi = {10.1109/NBEC53282.2021.9618751},
     isbn = {978-1-6654-3607-6}
   }