Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation
Abstract Diabetes is a widespread condition that can lead to serious vision problems over time. Timely identification and treatment of diabetic retinopathy (DR) depend on accurately segmenting retinal vessels, which can be achieved through the invasive technique of fundus imaging. This methodology f...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01694-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849729013928427520 |
|---|---|
| author | K. Radha Yepuganti Karuna |
| author_facet | K. Radha Yepuganti Karuna |
| author_sort | K. Radha |
| collection | DOAJ |
| description | Abstract Diabetes is a widespread condition that can lead to serious vision problems over time. Timely identification and treatment of diabetic retinopathy (DR) depend on accurately segmenting retinal vessels, which can be achieved through the invasive technique of fundus imaging. This methodology facilitates the systematic monitoring and assessment of the progression of DR. In recent years, deep learning has made significant steps in various fields, including medical image processing. Numerous algorithms have been developed for segmenting retinal vessels in fundus images, demonstrating excellent performance. However, it is widely recognized that large datasets are essential for training deep learning models to ensure they can generalize well. A major challenge in retinal vessel segmentation is the lack of ground truth samples to train these models. To overcome this, we aim to generate synthetic data. This work draws inspiration from recent advancements in generative adversarial networks (GANs). Our goal is to generate multiple realistic retinal fundus images based on tubular structured annotations while simultaneously creating binary masks from the retinal fundus images. We have integrated a latent space auto-encoder to maintain the vessel morphology when generating RGB fundus images and mask images. This approach can synthesize diverse images from a single tubular structured annotation and generate various tubular structures from a single fundus image. To test our method, we utilized three primary datasets, DRIVE, STARE, and CHASE_DB, to generate synthetic data. We then trained and tested a simple UNet model for segmentation using this synthetic data and compared its performance against the standard dataset. The results indicated that the synthetic data offered excellent segmentation performance, a crucial aspect in medical image analysis, where smaller datasets are often common. This demonstrates the potential of synthetic data as a valuable resource for training segmentation and classification models for disease diagnosis. Overall, we used the DRIVE, STARE, and CHASE_DB datasets to synthesize and evaluate the proposed image-to-image translation approach and its segmentation effectiveness. |
| format | Article |
| id | doaj-art-c5e7a65d0fb14491afc67636e1ef5fd0 |
| institution | DOAJ |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-c5e7a65d0fb14491afc67636e1ef5fd02025-08-20T03:09:20ZengBMCBMC Medical Imaging1471-23422025-05-0125111710.1186/s12880-025-01694-1Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentationK. Radha0Yepuganti Karuna1School of Electronics Engineering, Vellore Institute of TechnologySchool of Electronics Engineering, VIT-AP UniversityAbstract Diabetes is a widespread condition that can lead to serious vision problems over time. Timely identification and treatment of diabetic retinopathy (DR) depend on accurately segmenting retinal vessels, which can be achieved through the invasive technique of fundus imaging. This methodology facilitates the systematic monitoring and assessment of the progression of DR. In recent years, deep learning has made significant steps in various fields, including medical image processing. Numerous algorithms have been developed for segmenting retinal vessels in fundus images, demonstrating excellent performance. However, it is widely recognized that large datasets are essential for training deep learning models to ensure they can generalize well. A major challenge in retinal vessel segmentation is the lack of ground truth samples to train these models. To overcome this, we aim to generate synthetic data. This work draws inspiration from recent advancements in generative adversarial networks (GANs). Our goal is to generate multiple realistic retinal fundus images based on tubular structured annotations while simultaneously creating binary masks from the retinal fundus images. We have integrated a latent space auto-encoder to maintain the vessel morphology when generating RGB fundus images and mask images. This approach can synthesize diverse images from a single tubular structured annotation and generate various tubular structures from a single fundus image. To test our method, we utilized three primary datasets, DRIVE, STARE, and CHASE_DB, to generate synthetic data. We then trained and tested a simple UNet model for segmentation using this synthetic data and compared its performance against the standard dataset. The results indicated that the synthetic data offered excellent segmentation performance, a crucial aspect in medical image analysis, where smaller datasets are often common. This demonstrates the potential of synthetic data as a valuable resource for training segmentation and classification models for disease diagnosis. Overall, we used the DRIVE, STARE, and CHASE_DB datasets to synthesize and evaluate the proposed image-to-image translation approach and its segmentation effectiveness.https://doi.org/10.1186/s12880-025-01694-1Vessel segmentationDiabetic retinopathy (DR)Early diagnosisGenerative adversarial modelsData generation |
| spellingShingle | K. Radha Yepuganti Karuna Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation BMC Medical Imaging Vessel segmentation Diabetic retinopathy (DR) Early diagnosis Generative adversarial models Data generation |
| title | Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation |
| title_full | Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation |
| title_fullStr | Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation |
| title_full_unstemmed | Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation |
| title_short | Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation |
| title_sort | latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation |
| topic | Vessel segmentation Diabetic retinopathy (DR) Early diagnosis Generative adversarial models Data generation |
| url | https://doi.org/10.1186/s12880-025-01694-1 |
| work_keys_str_mv | AT kradha latentspaceautoencodergenerativeadversarialmodelforretinalimagesynthesisandvesselsegmentation AT yepugantikaruna latentspaceautoencodergenerativeadversarialmodelforretinalimagesynthesisandvesselsegmentation |