Vascular Bifurcation-Based Image Stitching Applied to Low-Resolution Retinal Images

• Guilherme G. S. Nunes UFMA
• João D. S. Almeida UFMA
• Darlan B. P. Quitanilha UFMA
• António Cunha Universidade de Trás-os-Montes e Alto Douro

DOI: https://doi.org/10.5753/sbcas.2025.7312

Abstract

Image stitching is a technique that allows combining multiple images, forming a single image with a wide field of view. In the context of retinography, this technique is crucial to capture a detailed view of the retina, allowing broader examinations to be performed. In this work, we present a method for stitching low-resolution images, using bifurcation points as image features. The proposed method presents an increase in the correspondences obtained in relation to the detectors in the literature, obtaining the RMSE result with a reduction of approximately 14% compared to SIFT (24.29) and ORB (24.32). Furthermore, the proposed method obtained a higher average PSNR, reaching 26.27 for glaucoma images, 26.72 for normal images and 26.71 for images of suspected patients, while the methods based on SIFT and ORB presented lower values, confirming the effectiveness of the proposed approach.

References

Abu-Ain, W., Abdullah, S. N. H. S., Bataineh, B., Abu-Ain, T., and Omar, K. (2013). Skeletonization algorithm for binary images. Procedia Technology, 11:704–709.

Agarwal, S. et al. (2022). Detection and mosaicing techniques for low-quality retinal videos. MDPI Sensors, 22(5):2059.

Burt, P. J. and Adelson, E. H. (1983). A multiresolution spline with application to image mosaics. ACM Transactions on Graphics (TOG), 2(4):217–236.

Costa, E. d. P. F., Gomes, T. M., Mendes, T. A., Campos, M. A. G., Bertrand, R. H. C., and Pinto, L. M. (2019). Perfil epidemiológico e prognóstico visual do trauma ocular em um centro de referência da região nordeste do brasil. Rev Bras Oftalmol., 78(5):310–314.

Feng, X., Cai, G., Gou, X., Yun, Z., Wang, W., and Yang, W. (2020). Retinal mosaicking with vascular bifurcations detected on vessel mask by a convolutional network. healthcare engineering.

Fischler, M. A. and Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395.

Fonseca, P., Araújo, A., Almeida, J., and Júnior, G. B. (2022). Treinando rede neural profunda com divisão proporcional de imagens para segmentação de estruturas da retina. In Anais do XXII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 1–12, Porto Alegre, RS, Brasil. SBC.

Gonzalez, R. C. (2009). Digital image processing. Pearson education india.

Hu, R., Chalakkal, R. J., Linde, G., and Dhupia, J. S. (2022). Multi-image stitching for smartphone-based retinal fundus stitching. In 2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), pages 179–184.

Jalili, J., Hejazi, S. M., Riazi-Esfahani, M., Eliasi, A., Ebrahimi, M., Seydi, M., Fard, M. A., and Ahmadian, A. (2020). Retinal image mosaicking using scale-invariant feature transformation feature descriptors and Voronoi diagram. Journal of Medical Imaging, 7(4):044001.

Jocher, G. (2023). Yolov8: State-of-the-art object detection. Acesso em: 17 fev. 2025.

Köhler, T., Heinrich, A., Maier, A., Hornegger, J., and Tornow, R. P. (2016). Super-resolved retinal image mosaicing. In 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), pages 1063–1067. IEEE.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.

Russo, A., Morescalchi, F., Costagliola, C., Delcassi, L., Semeraro, F., et al. (2015). A novel device to exploit the smartphone camera for fundus photography. Journal of ophthalmology, 2015.

Santos, L., Almeida, M., Almeida, J., Braz, G., Camara, J., and Cunha, A. (2024). Image stitching of low-resolution retinography using fundus blur filter and homography convolutional neural network. Information, 15(10).

Sarkar, A. (2021). Retinal-vessel-segmentation-using-variants-of-unet.

Wu, Y., Szymanska, M., Hu, Y., Fazal, M. I., Jiang, N., Yetisen, A. K., and Cordeiro, M. F. (2022). Measures of disease activity in glaucoma. Biosensors and Bioelectronics, 196:113700.