Volume 21 • Issue 2 • PP: 159-169 • 2026
Enhancement Medical Image using U-Net Model in Three Dimensional Vitreoretinal Surgery
View PDF Abstract
Vitreoretinal surgery is highly dependent on good visualization of fragile retinal surfaces for the purpose of accurate and safe operation. However, the image quality of current 3D heads-up display systems is often suboptimal, such as low contrast or inadequate sharpness, which is likely to decrease the accuracy of operation and prolong the operation duration. Improving intraoperative image quality continues to be a challenge for the advancement of the surgical results. In this paper, we advocate a deep learning-based solution to optimal imaging parameter guidance for the prospect of 3D HU-image guided VR surgery, seeking to improve vitreoretinal surface visibility during the surgery. A hybrid model that combines a U-Net-based image enhancement with a ViT for feature refinement has been learned using 212 manually optimized still frames (extracted from the ERM surgical video). The performance of the algorithm was quantitatively assessed through peak signal-to-noise ratio (PSNR) and the structural similarity index map (SSIM) and qualitatively evaluated in terms of the improvement in sharpness, brightness, and contrast. Moreover, the in-cabin usability of optimized images was investigated in an intraoperative survey. For in-vitro validation, 121 anonymous high-resolution ERM fundus images were analyzed with a 3D display coupled with the algorithm. The SSIM and PSNR of the model were 36.45±4.90 and 0.91±0.05, respectively, which indicated considerable improvements in image sharpness, brightness, and contrast. Visible ERM size and color contrast ratio were significantly enhanced in optimized images in the in-vitro studies. The results demonstrate that the developed algorithm can perform digital image enhancement effectively and has promise in the real-time applications during the 3D heads-up vitreoretinal surgeries.
Keywords
References
[1] M. Balas, V. Ramalingam, B. Pandya, A. Abdelaal, and R. B. Shi, “Adaptive optics imaging in ophthalmology: Redefining vision research and clinical practice,” JFO Open Ophthalmol., vol. 7, p. 100116, 2024, doi: 10.1016/j.jfop.2024.100116.
[2] Y. Shao, J. Ma, and Z.-Y. Wang, “Guidelines for preoperative visual function and imaging examination standards in vitreoretinal surgery,” Int. J. Ophthalmol., vol. 18, no. 5, pp. 813–831, 2025, doi: 10.18240/ijo.2025.05.06.
[3] M. J. B. A. Shalaby, M. Z. M. Abou El-Ela, and A. A. El-Halawany, “Deep learning for melanoma detection: A comprehensive review,” Health Inf. Sci. Syst., vol. 10, no. 1, p. 23, 2022, doi: 10.1007/s13755-022-00429-6.
[4] T. Li et al., “Applications of deep learning in fundus images: A review,” Med. Image Anal., vol. 69, p. 101971, 2021, doi: 10.1016/j.media.2021.101971.
[5] Z. Li et al., “Artificial intelligence in ophthalmology: The path to the real-world clinic,” Cell Reports Med., vol. 4, no. 7, p. 101095, Jul. 2023, doi: 10.1016/j.xcrm.2023.101095.
[6] M. Yousif, B. Al-Khateeb, and B. Garcia-Zapirain, “A new quantum circuits of quantum convolutional neural network for X-ray images classification,” IEEE Access, vol. 12, no. May, 2024, doi: 10.1109/ACCESS.2024.3396411.
[7] R. N. K. M. K. B. A. H. Alshahrani, M. A. M. Alharthi, and M. A. M. A. Alzahrani, “A hybrid model for the classification of skin lesions using deep learning and traditional methods,” J. Ambient Intell. Humaniz. Comput, vol. 12, pp. 1–13, 2023, doi: 10.1007/s12652-023-04567-5.
[8] S.Yang et al., “A review of image enhancement technology research,” in 2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), 2021, pp. 715–720, doi: 10.1109/MLBDBI54094.2021.00141.
[9] P. Razavi, B. Cakir, G. Baldwin, D. J. D’Amico, and J. B. Miller, “Heads-up three-dimensional viewing systems in vitreoretinal surgery: An updated perspective,” Clin. Ophthalmol, vol. 17, pp. 2539–2552, 2023, doi: 10.2147/OPTH.S424229.
[10] R. Mastropasqua, A. Quarta, M. L. Ruggeri, and L. Mastropasqua, “Enhancing precision and clarity with new digital color assistant in 3D heads-up vitreoretinal surgery,” Ophthalmol. Ther., vol. 14, no. 4, pp. 805–814, 2025, doi: 10.1007/s40123-025-01106-1.
[11] A. Melo et al., “Optimizing visualization of membranes in macular surgery with heads-up display,” Ophthalmic Surgery, Lasers Imaging Retin., vol. 51, pp. 584–587, 2020, doi: 10.3928/23258160-20201005-06.
[12] Y. Wu et al., “Indocyanine green-assisted internal limiting membrane peeling in macular hole surgery: A meta-analysis,” PLoS One, vol. 7, no. 11, p. e48405, 2012, doi: 10.1371/journal.pone.0048405.
[13] S. J. Park, J. R. Do, J. P. Shin, and D. H. Park, “Customized color settings of digitally assisted vitreoretinal surgery to enable use of lower dye concentrations during macular surgery,” Front. Med., vol. 8, p. 810070, 2021, doi: 10.3389/fmed.2021.810070.
[14] S. A. Minaker, R. H. Mason, and D. R. Chow, “Optimizing color performance of the Ngenuity 3-dimensional visualization system,” Ophthalmol. Sci., vol. 1, no. 3, p. 100054, Sep. 2021, doi: 10.1016/j.xops.2021.100054.
[15] Y. J. Kim, S. H. Hwang, K. G. Kim, and D. H. Nam, “Automated imaging of cataract surgery using artificial intelligence,” Diagnostics (Basel, Switzerland), vol. 15, no. 4, Feb. 2025, doi: 10.3390/diagnostics15040445.
[16] X. Zhao et al., “Development and quantitative assessment of deep learning-based image enhancement for optical coherence tomography,” BMC Ophthalmol., vol. 22, no. 1, p. 139, Mar. 2022, doi: 10.1186/s12886-022-02299-w.
[17] K. J. Halupka et al., “Retinal optical coherence tomography image enhancement via deep learning,” Biomed. Opt. Express, vol. 9, no. 12, pp. 6205–6221, Dec. 2018, doi: 10.1364/BOE.9.006205.
[18] S. H. Hwang, Y. J. Kim, J. B. Cho, K. G. Kim, and D. H. Nam, “Digital image enhancement using deep learning algorithm in 3D heads-up vitreoretinal surgery,” Sci. Rep., vol. 15, no. 1, pp. 1–10, 2025, doi: 10.1038/s41598-025-98801-7.
[19] T. B. Chowdhury, M. Khaliluzzaman, M. J. Uddin, K. Khanam, and M. M. Islam, “Low light enhancer: A low light image enhancement model based on U-Net using smartphone,” in 2022 International Conference on Innovations in Science, Engineering and Technology (ICISET), 2022, pp. 589–594, doi: 10.1109/ICISET54810.2022.9775888.
[20] J. Ko, S. Park, and H. G. Woo, “Optimization of vision transformer-based detection of lung diseases from chest X-ray images,” BMC Med. Inform. Decis. Mak, vol. 24, no. 1, p. 191, Jul. 2024, doi: 10.1186/s12911-024-02591-3.
Cite This Article
Choose your preferred format