Deformable registration of retinal fluorescein angiogram sequences using vasculature structures

Perez-Rovira, Adria; Trucco, Emanuele; Wilson, Peter J.; Liu, Jiang

doi:10.1109/iembs.2010.5627094

Cited by 7 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, in the method by Chen et al [20], Harris corner points are used as features instead. In the method proposed by Perez-Rovira et al [21], the junction-based results are refined by expanding the matches to include full vessel information. Shin et al [22] describe a similar two-step matching approach for coronary vessels that move considerably.…”

Section: Previous Workmentioning

confidence: 99%

“…The changes in appearance may hinder methods based on feature matching in the pixel domain [20]. It is reasonable to extract the vessel map first, and then perform registration based on the normalized map, as has been proposed in previous methods [17], [21]. However, vessels are generally small in area, with extremely repetitive structures, being more vulnerable to the aperture problem when attempting to apply local matching.…”

Section: A Registration and Vessel Extraction Of Fa Framesmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal Registration of Fundus Images With Fluorescein Angiography for Fine-Scale Vessel Segmentation

et al. 2020

View full text Add to dashboard Cite

Background and objective: The analysis of retinal vessels in fundus images is vital in the diagnosis of retinal diseases and early diagnosis of chronic vascular diseases and diabetes. Automatic vessel segmentation relies on costly expert annotations that may have limitations in the level of detail. We develop an automatic method to generate highly-accurate vessel segmentation including fine-scale vessels. Methods: We present a new framework for fine-scale vessel segmentation from fundus images through registration and segmentation of corresponding fluorescein angiography (FA) images. We first register and aggregate the extracted vessels highlighted from the fluorescent dye in the FA frames. This FA vessel mask is then registered to the fundus image based on an initial fundus vessel mask. Post-processing is performed to refine the final vessel mask. Registration of the FA frames, and registration of FA vessel mask to the fundus image, are performed by similar coarse-to-fine hierarchical frameworks comprising both projective and deformable registration. Two convolutional neural networks with identical network structures, both trained on public datasets but with different configurations, are used for vessel segmentation of both the FA frames and the fundus images. Results: Qualitative examples support the robustness and accuracy of the proposed method. Quantitative evaluations, including the area-under-curve (AUC) of the receiver operating characteristic (ROC) curve are presented. Although fair comparisons cannot be made due to a lack of similar methods and adequate public datasets, we demonstrate that the proposed method with an AUC ROC of 0.979, outperforms a state-of-the-art automatic vessel segmentation method trained on publicly available datasets at 0.956. Conclusions: The proposed method generates accurate vessel segmentation results containing filamentary vessels that are virtually indiscernible to the naked eye in color retinal fundus images.INDEX TERMS Fundus images, fluorescein angiography, multi-modal registration, vessel segmentation.

show abstract

Section: Previous Workmentioning

confidence: 99%