Riad Hassan

riad_hassan@outlook.com

I am Riad Hassan, a passionate researcher and lecturer specializing in computer vision, medical image analysis, and deep learning. I hold an MSc from BUET (GPA 3.92/4.00, top 1%), where I developed an uncertainty-driven boundary-refined CNN for medical image segmentation.

With a proven record of publications in venues such as IEEE ISBI and Biomedical Signal Processing and Control, my research focuses on efficient deep learning network design, attention-based architectures, and adaptive loss functions. As part of the BioRAIN Research Group; Data Analytics Lab, IICT, BUET; and Computer Vision Research Cell, CSE, GUB, I contribute to cutting-edge projects in AI, Computer Vision, and Medical Imaging.

I am passionate about conducting impactful research and contributing to leading journals (TMI, PAMI, MIA, TIP) and conferences (CVPR, MICCAI, MIDL, ISBI, ICLR, ECCV). With expertise in Python, PyTorch, and large-scale experimentation, my goal is to advance the state of the art in Computer Vision, Medical Imaging and AI.

News

Sep 13, 2025	Our paper EDLDNet: An efficient dual-line decoder with multi-scale convolutional attention for multi-organ segmentation has been published in Biomedical Signal Processing and Control (Q1, IF: 4.9).
May 23, 2025	Our paper MobDenseNet: Brain tumor classification from MRI has been published in Array (Q1, IF: 4.5).
Dec 15, 2024	Our paper on Object Detection in adverse weather has been presented at STI 2024.
Nov 30, 2024	Successfully completed MSc from BUET! Thesis: Uncertainty driven boundary refined CNN for medical image segmentation.
Nov 29, 2024	New paper on prostate cancer grade classification has been presented at DICTA 2024.

Latest Posts

May 22, 2025	Box Plot vs Violin Plot: Which One is More Powerful for Research Articles?

Selected Publications

BPSC

An efficient dual-line decoder network with multi-scale convolutional attention for multi-organ segmentation

Riad Hassan, M. Rubaiyat Hossain Mondal, Sheikh Iqbal Ahamed, Fahad Mostafa, and Md Mostafijur Rahman

Biomedical Signal Processing and Control, 2026

DOI Bib PDF Code

@article{HASSAN2026108611,
  title = {An efficient dual-line decoder network with multi-scale convolutional attention for multi-organ segmentation},
  journal = {Biomedical Signal Processing and Control},
  volume = {112},
  pages = {108611},
  year = {2026},
  issn = {1746-8094},
  doi = {https://doi.org/10.1016/j.bspc.2025.108611},
  url = {https://www.sciencedirect.com/science/article/pii/S174680942501122X},
  author = {Hassan, Riad and Mondal, M. Rubaiyat Hossain and Ahamed, Sheikh Iqbal and Mostafa, Fahad and Rahman, Md Mostafijur},
  keywords = {Attention mechanisms, Computational efficiency, Deep learning, Dual-line decoder, Medical image segmentation, Multi-scale feature extraction},
}

UDBRNet: A novel uncertainty driven boundary refined network for organ at risk segmentation

Riad Hassan, M. Rubaiyat Hossain Mondal, and Sheikh Iqbal Ahamed

PLOS ONE, Jun 2024

DOI Bib Code

@article{10.1371/journal.pone.0304771,
  doi = {10.1371/journal.pone.0304771},
  author = {Hassan, Riad and Mondal, M. Rubaiyat Hossain and Ahamed, Sheikh Iqbal},
  journal = {PLOS ONE},
  publisher = {Public Library of Science},
  title = {UDBRNet: A novel uncertainty driven boundary refined network for organ at risk segmentation},
  year = {2024},
  month = jun,
  volume = {19},
  pages = {1-18},
  number = {6},
}

ISBI

Uncertainty Driven Bottleneck Attention U-Net For Organ at Risk Segmentation

Abdullah Nazib, Riad Hassan, Zahidul Islam, and Clinton Fookes

In 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Jun 2024

DOI Bib PDF Code

@inproceedings{10635587,
  author = {Nazib, Abdullah and Hassan, Riad and Islam, Zahidul and Fookes, Clinton},
  booktitle = {2024 IEEE International Symposium on Biomedical Imaging (ISBI)},
  title = {Uncertainty Driven Bottleneck Attention U-Net For Organ at Risk Segmentation},
  year = {2024},
  volume = {},
  number = {},
  pages = {1-5},
  address = {Athens, Greece},
  doi = {10.1109/ISBI56570.2024.10635587},
}