Pix2pix Conditional Generative Adversarial Networks for Scheimpflug Camera Color-Coded Corneal Tomography Image Generation
| Autor: | Hazem Abdelmotaal, Khaled Abdelazeem, Ahmed F. Omar, Ahmed A. Abdou, Dalia Mohamed El-Sebaity |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Keratoconus Image generation Mean squared error synthesized images Computer science Scheimpflug principle Biomedical Engineering convolutional neural network Convolutional neural network Article pix2pix 03 medical and health sciences 0302 clinical medicine medicine Humans Computer Simulation Tomography Retrospective Studies Contextual image classification business.industry image augmentation Pattern recognition Corneal tomography medicine.disease scheimpflug camera corneal tomography images Ophthalmology 030104 developmental biology 030221 ophthalmology & optometry Artificial intelligence Neural Networks Computer generative adversarial networks business Tomography X-Ray Computed color-coded images |
| Zdroj: | Translational Vision Science & Technology |
| ISSN: | 2164-2591 |
| Popis: | Purpose To assess the ability of pix2pix conditional generative adversarial network (pix2pix cGAN) to create plausible synthesized Scheimpflug camera color-coded corneal tomography images based upon a modest-sized original dataset to be used for image augmentation during training a deep convolutional neural network (DCNN) for classification of keratoconus and normal corneal images. Methods Original images of 1778 eyes of 923 nonconsecutive patients with or without keratoconus were retrospectively analyzed. Images were labeled and preprocessed for use in training the proposed pix2pix cGAN. The best quality synthesized images were selected based on the Frechet inception distance score, and their quality was studied by calculating the mean square error, structural similarity index, and the peak signal-to-noise ratio. We used original, traditionally augmented original and synthesized images to train a DCNN for image classification and compared classification performance metrics. Results The pix2pix cGAN synthesized images showed plausible subjectively and objectively assessed quality. Training the DCNN with a combination of real and synthesized images allowed better classification performance compared with training using original images only or with traditional augmentation. Conclusions Using the pix2pix cGAN to synthesize corneal tomography images can overcome issues related to small datasets and class imbalance when training computer-aided diagnostic models. Translational Relevance Pix2pix cGAN can provide an unlimited supply of plausible synthetic Scheimpflug camera color-coded corneal tomography images at levels useful for experimental and clinical applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|