iResSENet

This repository contains the original implementation of "iResSENet: An Accurate Convolutional Neural Network for Retinal Blood Vessel Segmentation".

• Email: promaprogga16@gmail.com

🔗 Paper

This code implements the paper:

Progga, P.H., Shatabda, S. (2023). iResSENet: An Accurate Convolutional Neural Network for Retinal Blood Vessel Segmentation. In Neural Information Processing. ICONIP 2022. Lecture Notes in Computer Science, vol 13625. Springer, Cham. https://doi.org/10.1007/978-3-031-30111-7_48

If you find this work is helpful for your research, please cite our paper [PDF].

• View the Preprint

🔗 Copying

We share this code only for research use. If you find any problem or inappropriate content in this code, feel free to contact.

🔗 Use

1. Data Preparation

Download the Retinal datasets and their masks: DRIVE (Link), CHASE_DB1 (Link), HRF (Link) and STARE (Link).

2. Model and Evaluation

iResSENet, a novel deep learning-based architecture based on U-Net architecture. The proposed method enhances U-Net in three aspects. It replaces the encoder blocks with residual connections in addition to 1×1 convolutional layers and channel-based attention.

Model code available in here (tensorflow)

🔗 Citation Request

If you use 'iResSENet' in your project, please cite the following paper-

@inproceedings{progga2023iressenet,
  title={iResSENet: An Accurate Convolutional Neural Network for Retinal Blood Vessel Segmentation},
  author={Progga, Proma Hossain and Shatabda, Swakkhar},
  booktitle={Neural Information Processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22--26, 2022, Proceedings, Part III},
  pages={567--578},
  year={2023},
  organization={Springer}
}