A Segmentation Based Robust Deep Learning Framework for Multimodal Retinal Image Registration
| Autor: | Yiqian Wang, Manuel J. Amador-Patarroyo, Truong Q. Nguyen, Dirk-Uwe Bartsch, Melina Cavichini, Cheolhong An, Mahima Jhingan, William R. Freeman, Christopher P Long, Junkang Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Retinal image registration Image registration 02 engineering and technology Fundus (eye) Convolutional neural network 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Robustness (computer science) Outlier 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Computer vision Artificial intelligence business |
| Zdroj: | ICASSP |
| DOI: | 10.1109/icassp40776.2020.9054077 |
| Popis: | Multimodal image registration plays an important role in diagnosing and treating ophthalmologic diseases. In this paper, a deep learning framework for multimodal retinal image registration is proposed. The framework consists of a segmentation network, feature detection and description network, and an outlier rejection network, which focuses only on the globally coarse alignment step using the perspective transformation. We apply the proposed framework to register color fundus images with infrared reflectance images and compare it with the state-of-the-art conventional and learning-based approaches. The proposed framework demonstrates a significant improvement in robustness and accuracy reflected by a higher success rate and Dice coefficient compared to other coarse alignment methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|