# Evaluating the Quality and Diversity of DCGAN-based Generatively Synthesized Diabetic Retinopathy Imagery

arXiv: https://arxiv.org/abs/2208.05593 · HTML: https://mlsanity.com/paper/2208.05593/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 77 references that are in the map.
- First posted on arXiv 10 Aug 2022.

## Builds on (most cited first, 18 of 18)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [Improving GANs Using Optimal Transport](https://mlsanity.com/paper/1803.05573/) (2018)
- [How good is my GAN?](https://mlsanity.com/paper/1807.09499/) (2018)
- [A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability](https://mlsanity.com/paper/2008.09772/) (2020)
- [Learning to Generate Images with Perceptual Similarity Metrics](https://mlsanity.com/paper/1511.06409/) (2015)
- [Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection](https://mlsanity.com/paper/1905.13456/) (2019)
- [Enhanced Balancing GAN: Minority-class Image Generation](https://mlsanity.com/paper/2011.00189/) (2020)
- [DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images](https://mlsanity.com/paper/1912.04670/) (2019)
- [Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images](https://mlsanity.com/paper/1902.09856/) (2019)
- [Addressing the Intra-class Mode Collapse Problem using Adaptive Input Image Normalization in GAN-based X-ray Images](https://mlsanity.com/paper/2201.10324/) (2022)
- [Combating COVID-19 using Generative Adversarial Networks and Artificial Intelligence for Medical Images: A Scoping Review](https://mlsanity.com/paper/2205.07236/) (2022)

## Built on by (most cited first, 2 of 2)

- [InceptionCaps: A Performant Glaucoma Classification Model for Data-scarce Environment](https://mlsanity.com/paper/2312.00803/) (2023)
- [MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification](https://mlsanity.com/paper/2510.22070/) (2025)

## Abstract (arXiv)

Publicly available diabetic retinopathy (DR) datasets are imbalanced, containing limited numbers of images with DR. This imbalance contributes to overfitting when training machine learning classifiers. The impact of this imbalance is exacerbated as the severity of the DR stage increases, affecting the classifiers' diagnostic capacity. The imbalance can be addressed using Generative Adversarial Networks (GANs) to augment the datasets with synthetic images. Generating synthetic images is advantageous if high-quality and diversified images are produced. To evaluate the quality and diversity of synthetic images, several evaluation metrics, such as Multi-Scale Structural Similarity Index (MS-SSIM), Cosine Distance (CD), and Fr'echet Inception Distance (FID) are used. Understanding the effectiveness of each metric in evaluating the quality and diversity of GAN-based synthetic images is critical to select images for augmentation. To date, there has been limited analysis of the appropriateness of these metrics in the context of biomedical imagery. This work contributes an empirical assessment of these evaluation metrics as applied to synthetic Proliferative DR imagery generated by a Deep Convolutional GAN (DCGAN). Furthermore, the metrics' capacity to indicate the quality and diversity of synthetic images and a correlation with classifier performance is undertaken. This enables a quantitative selection of synthetic imagery and an informed augmentation strategy. Results indicate that FID is suitable for evaluating the quality, while MS-SSIM and CD are suitable for evaluating the diversity of synthetic imagery. Furthermore, the superior performance of Convolutional Neural Network (CNN) and EfficientNet classifiers, as indicated by the F1 and AUC scores, for the augmented datasets demonstrates the efficacy of synthetic imagery to augment the imbalanced dataset.