Publications

Rahman, Md Fashiar, Tzu-Liang Tseng, Michael Pokojovy, Peter McCaffrey, Eric Walser, Scott Moen, Alex Vo, and Johnny C. Ho. "Machine-Learning-Enabled Diagnostics with Improved Visualization of Disease Lesions in Chest X-ray Images." Diagnostics 14, no. 16 (2024): 1699
DOI: https://www.mdpi.com/2075-4418/14/16/1699

This study uses a deep learning model based on VGG-16 to classify chest X-rays into COVID-19, pneumonia, or normal with 96.44% accuracy. It includes image enhancement, region cropping, and data augmentation to improve results. A new method called ML-Grad-CAM helps highlight infected areas for better understanding and diagnosis. A Severity Assessment Index is also introduced to measure how serious the infection is.

Afrin, Humayra, Stephanie Vargas Esquivel, Raj Kumar, Md Ikhtiar Zahid, Beu Oporeza, Md Fashiar Rahman, Thomas Boland, and Md Nurunnabi. "β-glucan-mediated oral codelivery of 5FU and bcl2 siRNA attenuates stomach cancer." ACS applied materials & interfaces 15, no. 27 (2023): 32188-32200.
DOI: https://pubs.acs.org/doi/10.1021/acsami.3c03528

This paper presents a new oral delivery system using β-glucan to treat stomach cancer by sticking to the stomach lining and slowly releasing chemotherapy (5FU) and gene-silencing therapy (Bcl2 siRNA). In mouse models, this approach improved cancer remission, reduced tumor size, and showed fewer side effects compared to conventional treatments.

Zhuang, Yan, Md Fashiar Rahman, Yuxin Wen, Michael Pokojovy, Peter McCaffrey, Alexander Vo, Eric Walser, Scott Moen, Honglun Xu, and Tzu-Liang Tseng. "An interpretable multi-task system for clinically applicable COVID-19 diagnosis using CXR." Journal of X-Ray Science and Technology 30, no. 5 (2022): 847-862.
DOI: https://doi.org/10.3233/XST-221151

This paper proposes an AI-based system that detects lungs and classifies chest X-rays into COVID-19, pneumonia, or normal using deep learning. Tested on over 15,000 images, it achieved high accuracy and sensitivity, offering a fast, reliable, and interpretable alternative to traditional COVID-19 testing.

Wen, Yuxin, Md Fashiar Rahman, Yan Zhuang, Michael Pokojovy, Honglun Xu, Peter McCaffrey, Alexander Vo, Eric Walser, Scott Moen, and Tzu-Liang Bill Tseng. "Time-to-event modeling for hospital length of stay prediction for COVID-19 patients." Machine learning with applications 9 (2022): 100365.
DOI: https://doi.org/10.1016/j.mlwa.2022.100365

This paper uses survival analysis to predict hospital length of stay for COVID-19 patients using detailed individual clinical data. Six models were tested and compared, aiming to improve hospital efficiency and patient care by better handling censored medical data.

Habibur Rahman, Md, Md Fashiar Rahman, and Tzu-Liang Tseng. "Estimation of fuel consumption and selection of the most carbon-efficient route for cold-chain logistics." International Journal of Systems Science: Operations & Logistics 10, no. 1 (2023): 2075043.
DOI: https://www.tandfonline.com/doi/full/10.1080/23302674.2022.2075043

This paper develops a model to reduce fuel use and carbon emissions in cold-chain logistics while keeping food quality. Testing different transport routes showed that single-route transportation was the most eco-friendly, cutting fuel use by up to 64.52% compared to other options.

Rahman, Md Fashiar, Yan Zhuang, Tzu-Liang Bill Tseng, Michael Pokojovy, Peter McCaffrey, Eric Walser, Scott Moen, and Alex Vo. "Improving lung region segmentation accuracy in chest X-ray images using a two-model deep learning ensemble approach." Journal of Visual Communication and Image Representation 85 (2022): 103521.
DOI: https://doi.org/10.1016/j.jvcir.2022.103521

This paper introduces a deep learning method to improve lung segmentation in chest X-rays by splitting images into patches, segmenting them separately with CNN and modified U-Net models, then combining and refining results with image processing. The approach outperformed existing methods on multiple datasets.

Zhuang, Yan, Md Fashiar Rahman, Yuxin Wen, Michael Pokojovy, Peter McCaffrey, Alexander Vo, Eric Walser, Scott Moen, Honglun Xu, and Tzu-Liang Tseng. "An interpretable multi-task system for clinically applicable COVID-19 diagnosis using CXR." Journal of X-Ray Science and Technology 30, no. 5 (2022): 847-862.
DOI: https://doi.org/10.3233/XST-22115

This paper proposes an AI-based system for early COVID-19 detection from chest X-ray images as a faster, more accessible alternative to lab testing. Using lung detection, deep transfer learning, and interpretable heatmaps, the model classifies images into COVID-19, pneumonia, or normal with high accuracy and sensitivity.

Rahman, Md Fashiar, Yan Zhuang, Tzu-Liang Bill Tseng, Michael Pokojovy, Peter McCaffrey, Eric Walser, Scott Moen, and Alex Vo. "Improving lung region segmentation accuracy in chest X-ray images using a two-model deep learning ensemble approach." Journal of Visual Communication and Image Representation 85 (2022): 103521.
DOI: https://doi.org/10.1016/j.jvcir.2022.103521

This paper presents a deep learning method to improve lung segmentation in chest X-rays by splitting images into smaller patches, processing them with CNN and modified U-Net models, then combining and refining the results using image processing. The approach achieved better accuracy than existing methods on multiple datasets.

Rahman, Md Fashiar, Yan Zhuang, Tzu-Liang Bill Tseng, Michael Pokojovy, Peter McCaffrey, Eric Walser, Scott Moen, and Alex Vo. "Improving lung region segmentation accuracy in chest X-ray images using a two-model deep learning ensemble approach." Journal of Visual Communication and Image Representation 85 (2022): 103521.
DOI: https://doi.org/10.1017/S0890060421000330

This paper introduces a system that uses Mask R-CNN to automatically detect and segment fillers (fibers and particles) in SEM images for quality inspection and morphology analysis. A new SEM image simulation method is used to generate training data, enabling the model to handle overlapping and unclear fillers with high accuracy on both simulated and real images.

Wen, Yuxin, Md Fashiar Rahman, Honglun Xu, and Tzu-Liang Bill Tseng. "Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective." Measurement 187 (2022): 110276.
DOI: https://doi.org/10.1016/j.measurement.2021.110276

This paper reviews recent progress in data-driven machine prognostics for predictive maintenance. It summarizes key methods, practical applications, and discusses challenges, opportunities, and future trends to help researchers and industry professionals better understand and apply these approaches.

Rahman, Md Fashiar, Jianguo Wu, and Tzu Liang Bill Tseng. "Automatic morphological extraction of fibers from SEM images for quality control of short fiber-reinforced composites manufacturing." CIRP Journal of Manufacturing Science and Technology 33 (2021): 176-187.
DOI: https://doi.org/10.1016/j.cirpj.2021.03.010

This paper presents five automated methods to extract straight fibers from SEM images for analyzing fiber morphology in composites. These approaches address challenges like overlapping and cross-linking and are evaluated through simulations and real case studies to ensure accuracy and robustness for quality control and process optimization.