UTHealth - Fundus and Synthetic OCT-A Dataset (UT-FSOCTA)

<p><strong>Introduction</strong></p> <p>Vessel segmentation in fundus images is essential in the diagnosis and prognosis of retinal diseases and the identification of image-based biomarkers. However, creating a vessel segmentation map can be a tedious and time consuming process, requiring careful delineation of the vasculature, which is especially hard for microcapillary plexi in fundus images. Optical coherence tomography angiography (OCT-A) is a relatively novel modality visualizing blood flow and microcapillary plexi not clearly observed in fundus photography. Unfortunately, current commercial OCT-A cameras have various limitations due to their complex optics making them more expensive, less portable, and with a reduced field of view (FOV) compared to fundus cameras. Moreover, the vast majority of population health data collection efforts do not include OCT-A data.</p> <p>We believe that strategies able to map fundus images to en-face OCT-A can create precise vascular vessel segmentation with less effort.</p> <p>In this dataset, called UTHealth - Fundus and Synthetic OCT-A Dataset (UT-FSOCTA), we include fundus images and en-face OCT-A images for 112 subjects. The two modalities have been manually aligned to allow for training of medical imaging machine learning pipelines. This dataset is accompanied by a manuscript that describes an approach to generate fundus vessel segmentations using OCT-A for training (Coronado et al., 2022). We refer to this approach as &quot;Synthetic OCT-A&quot;.</p> <p><strong>Fundus Imaging</strong></p> <p>We include 45 degree macula centered fundus images that cover both macula and optic disc. All images were acquired using a OptoVue iVue fundus camera without pupil dilation.</p> <p>The full images are available at the <code>fov45/fundus</code> directory. In addition, we extracted the FOVs corresponding to the en-face OCT-A images collected in <code>cropped/fundus/disc</code> and <code>cropped/fundus/macula</code>.</p> <p><strong>Enface OCT-A</strong></p> <p>We include the en-face OCT-A images of the superficial capillary plexus. All images were acquired using an OptoVue Avanti OCT camera with OCT-A reconstruction software (AngioVue). Low quality images with errors in the retina layer segmentations were not included.</p> <p>En-face OCTA images are located in <code>cropped/octa/disc</code> and <code>cropped/octa/macula</code>. In addition, we include a denoised version of these images where only vessels are included. This has been performed automatically using the ROSE algorithm (Ma et al. 2021). These can be found in <code>cropped/GT_OCT_net/noThresh</code> and <code>cropped/GT_OCT_net/Thresh</code>, the former contains the probabilities of the ROSE algorithm the latter a binary map.</p> <p><strong>Synthetic OCT-A</strong></p> <p>We train a custom conditional generative adversarial network (cGAN) to map a fundus image to an en face OCT-A image. Our model consists of a generator synthesizing en face OCT-A images from corresponding areas in fundus photographs and a discriminator judging the resemblance of the synthesized images to the real en face OCT-A samples. This allows us to avoid the use of manual vessel segmentation maps altogether.</p> <p>The full images are available at the <code>fov45/synthetic_octa</code> directory. Then, we extracted the FOVs corresponding to the en-face OCT-A images collected in <code>cropped/synthetic_octa/disc</code> and <code>cropped/synthetic_octa/macula</code>. In addition, we performed the same denoising ROSE algorithm (Ma et al. 2021) used for the original enface OCT-A images, the results are available in <code>cropped/denoised_synthetic_octa/noThresh</code> and <code>cropped/denoised_synthetic_octa/Thresh</code>, the former contains the probabilities of the ROSE algorithm the latter a binary map.</p> <p><strong>Other Fundus Vessel Segmentations Included</strong></p> <p>In this dataset, we have also included the output of two recent vessel segmentation algorithms trained on external datasets with manual vessel segmentations. SA-Unet (Li et. al, 2020) and IterNet (Guo et. al, 2021).</p> <ul> <li> <p>SA-Unet. The full images are available at the <code>fov45/SA_Unet</code> directory. Then, we extracted the FOVs corresponding to the en-face OCT-A images collected in <code>cropped/SA_Unet/disc</code> and <code>cropped/SA_Unet/macula</code>.</p> </li> <li> <p>IterNet. The full images are available at the <code>fov45/Iternet</code> directory. Then, we extracted the FOVs corresponding to the en-face OCT-A images collected in <code>cropped/Iternet/disc</code> and <code>cropped/Iternet/macula</code>.</p> </li> </ul> <p><strong>Train/Validation/Test Replication</strong></p> <p>In order to replicate or compare your model to the results of our paper, we report below the data split used.</p> <ul> <li> <p>Training subjects IDs: 1 - 25</p> </li> <li> <p>Validation subjects IDs: 26 - 30</p> </li> <li> <p>Testing subjects IDs: 31 - 112</p> </li> </ul> <p><strong>Data Acquisition</strong></p> <p>This dataset was acquired at the Texas Medical Center - Memorial Hermann Hospital in accordance with the guidelines from the Helsinki Declaration and it was approved by the UTHealth IRB with protocol HSC-MS-19-0352.</p> <p><strong>User Agreement</strong></p> <p>The UT-FSOCTA dataset is free to use for non-commercial scientific research only. In case of any publication the following paper needs to be cited</p> <pre><code> Coronado I, Pachade S, Trucco E, Abdelkhaleq R, Yan J, Salazar-Marioni S, Jagolino-Cole A, Bahrainian M, Channa R, Sheth SA, Giancardo L. Synthetic OCT-A blood vessel maps using fundus images and generative adversarial networks. Sci Rep 2023;13:15325. https://doi.org/10.1038/s41598-023-42062-9. </code></pre> <p><strong>Funding</strong></p> <p>This work is supported by the Translational Research Institute for Space Health through NASA Cooperative Agreement NNX16AO69A.</p> <p><strong>Research Team and Acknowledgements</strong></p> <p>Here are the people behind this data acquisition effort:</p> <p>Ivan Coronado, Samiksha Pachade, Rania Abdelkhaleq, Juntao Yan, Sergio Salazar-Marioni, Amanda Jagolino, Mozhdeh Bahrainian, Roomasa Channa, Sunil Sheth, Luca Giancardo</p> <p>We would also like to acknowledge for their support: the Institute for Stroke and Cerebrovascular Diseases at UTHealth, the VAMPIRE team at University of Dundee, UK and Memorial Hermann Hospital System.</p> <p><strong>References</strong></p> <pre><code>Coronado I, Pachade S, Trucco E, Abdelkhaleq R, Yan J, Salazar-Marioni S, Jagolino-Cole A, Bahrainian M, Channa R, Sheth SA, Giancardo L. Synthetic OCT-A blood vessel maps using fundus images and generative adversarial networks. Sci Rep 2023;13:15325. https://doi.org/10.1038/s41598-023-42062-9. C. Guo, M. Szemenyei, Y. Yi, W. Wang, B. Chen, and C. Fan, "SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation," in 2020 25th International Conference on Pattern Recognition (ICPR), Jan. 2021, pp. 1236–1242. doi: 10.1109/ICPR48806.2021.9413346. L. Li, M. Verma, Y. Nakashima, H. Nagahara, and R. Kawasaki, "IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks," 2020 IEEE Winter Conf. Appl. Comput. Vis. WACV, 2020, doi: 10.1109/WACV45572.2020.9093621. Y. Ma et al., "ROSE: A Retinal OCT-Angiography Vessel Segmentation Dataset and New Model," IEEE Trans. Med. Imaging, vol. 40, no. 3, pp. 928–939, Mar. 2021, doi: 10.1109/TMI.2020.3042802. </code></pre>