Prior Guided Fundus Image Quality Enhancement Via Contrastive Learning

Cheng, Pujin; Lin, Li; Huang, Yijin; Lyu, Junyan; Tang, Xiaoying

doi:10.1109/isbi48211.2021.9434005

Cited by 10 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Image Quality Enhancement: Given the importance of fundus images for medical diagnosis, the quality of the image is paramount for accuracy, especially in automated computerbased applications [13], [20]. This section details some applications of AI (primarily GAN) in fundus image quality enhancement.…”

Section: A Applications Of DL On Fundus Imagesmentioning

confidence: 99%

“…Managed to improve overall precision of blood vessel segmentation by 0.736%. Similarly, in Cheng et al [13], GAN was used to enhance degraded fundus images. The GAN structure was modified to incorporate a contrastive loss function in the encoder (generator) network.…”

Section: A Applications Of DL On Fundus Imagesmentioning

confidence: 99%

“…Early intervention (screening and treatment) can prevent blindness [7]. Fundus images provide an interesting non-invasive diagnostic opportunity as the retina's intricate structure provides a non-invasive wealth of information for ophthalmic diagnosis [8]- [13].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Lightweight Generative Adversarial Network Fundus Image Synthesis

Aziz

Sulaiman

Zabidi

et al. 2022

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Blindness is a global health problem that affects billions of lives. Recent advancements in Artificial Intelligence (AI), (Deep Learning (DL)) has the intervention potential to address the blindness issue, particularly as an accurate and non-invasive technique for early detection and treatment of Diabetic Retinopathy (DR). DL-based techniques rely on extensive examples to be robust and accurate in capturing the features responsible for representing the data. However, the number of samples required is tremendous for the DL classifier to learn properly. This presents an issue in collecting and categorizing many samples. Therefore, in this paper, we present a lightweight Generative Neural Network (GAN) to synthesize fundus samples to train AI-based systems. The GAN was trained using samples collected from publicly available datasets. The GAN follows the structure of the recent Lightweight GAN (LGAN) architecture. The implementation and results of the LGAN training and image generation are described. Results indicate that the trained network was able to generate realistic high-resolution samples of normal and diseased fundus images accurately as the generated results managed to realistically represent key structures and their placements inside the generated samples, such as the optic disc, blood vessels, exudates, and others. Successful and unsuccessful generation samples were sorted manually, yielding 56.66% realistic results relative to the total generated samples. Rejected generated samples appear to be due to inconsistencies in shape, key structures, placements, and color.

show abstract

Section: A Applications Of DL On Fundus Imagesmentioning

confidence: 99%

Section: A Applications Of DL On Fundus Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Lightweight Generative Adversarial Network Fundus Image Synthesis

Aziz

Sulaiman

Zabidi

et al. 2022

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…However, cofe-Net can only ideally model a limited type of degradation factors-it may fail when there are more complicated degradations. Cheng et al [29] proposed EPC-GAN by training both GAN loss and contrastive loss to make use of high-level features in the fundus domain. A fundus prior loss based on a pretrained diabetic retinopathy classification network was introduced to avoid information modification and over-enhancement.…”

Section: Fundus Image Enhancementmentioning

confidence: 99%

“…Yifan J et al [15] proposed an unreferenced self-feature-preserving loss to preserve the image content features based on the observation that classification results are not very sensitive when pixel intensity range changes, which means that features extracted from both low light images and corresponding normal light images share the same feature space. Pujin C et al [29] designed a fundus prior loss by pre-training a DR classification model to keep the fundus semantic information stable before and after enhancement, because deep features related to pathological areas should be preserved after enhancement.…”

Section: Classification Prior Loss Guided Generatormentioning

confidence: 99%

A Novel Un-Supervised GAN for Fundus Image Enhancement with Classification Prior Loss

2022

View full text Add to dashboard Cite

Fundus images captured for clinical diagnosis usually suffer from degradation factors due to variation in equipment, operators, or environment. These degraded fundus images need to be enhanced to achieve better diagnosis and improve the results of downstream tasks. As there is no paired low- and high-quality fundus image, existing methods mainly focus on supervised or semi-supervised learning methods for color fundus image enhancement (CFIE) tasks by utilizing synthetic image pairs. Consequently, domain gaps between real images and synthetic images arise. With respect to existing unsupervised methods, the most important low scale pathological features and structural information in degraded fundus images are prone to be erased after enhancement. To solve these problems, an unsupervised GAN is proposed for CFIE tasks utilizing adversarial training to enhance low quality fundus images. Synthetic image pairs are no longer required during the training. A specially designed U-Net with skip connection in our enhancement network can effectively remove degradation factors while preserving pathological features and structural information. Global and local discriminators adopted in the GAN lead to better illumination uniformity in the enhanced fundus image. To better improve the visual quality of enhanced fundus images, a novel non-reference loss function based on a pretrained fundus image quality classification network was designed to guide the enhancement network to produce high quality images. Experiments demonstrated that our method could effectively remove degradation factors in low-quality fundus images and produce a competitive result compared with previous methods in both quantitative and qualitative metrics.

show abstract