Data augmentation for skin lesion using self-attention based progressive generative adversarial network

Abdelhalim, Ibrahim Saad Aly; Mohamed, Mamdouh; Mahdy, Yousef B.

doi:10.1016/j.eswa.2020.113922

Cited by 85 publications

(59 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A deep convolutional GAN (DCGAN) is based on the vanilla GAN by replacing the building block with fully convolutional layers [ 10 ]. Wasserstein GAN is an improved version of the vanilla GAN that uses a metric of the distance between two probability distributions (Wasserstein distance) as a loss function [ 12 ]. PGGAN is an extension of the vanilla GAN with a progressively growing generator and discriminator to generate realistic high-resolution images.…”

Section: Reviewmentioning

confidence: 99%

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

et al. 2022

View full text Add to dashboard Cite

Background Recent advances in deep learning techniques have led to improved diagnostic abilities in ophthalmology. A generative adversarial network (GAN), which consists of two competing types of deep neural networks, including a generator and a discriminator, has demonstrated remarkable performance in image synthesis and image-to-image translation. The adoption of GAN for medical imaging is increasing for image generation and translation, but it is not familiar to researchers in the field of ophthalmology. In this work, we present a literature review on the application of GAN in ophthalmology image domains to discuss important contributions and to identify potential future research directions. Methods We performed a survey on studies using GAN published before June 2021 only, and we introduced various applications of GAN in ophthalmology image domains. The search identified 48 peer-reviewed papers in the final review. The type of GAN used in the analysis, task, imaging domain, and the outcome were collected to verify the usefulness of the GAN. Results In ophthalmology image domains, GAN can perform segmentation, data augmentation, denoising, domain transfer, super-resolution, post-intervention prediction, and feature extraction. GAN techniques have established an extension of datasets and modalities in ophthalmology. GAN has several limitations, such as mode collapse, spatial deformities, unintended changes, and the generation of high-frequency noises and artifacts of checkerboard patterns. Conclusions The use of GAN has benefited the various tasks in ophthalmology image domains. Based on our observations, the adoption of GAN in ophthalmology is still in a very early stage of clinical validation compared with deep learning classification techniques because several problems need to be overcome for practical use. However, the proper selection of the GAN technique and statistical modeling of ocular imaging will greatly improve the performance of each image analysis. Finally, this survey would enable researchers to access the appropriate GAN technique to maximize the potential of ophthalmology datasets for deep learning research.

show abstract

Section: Reviewmentioning

confidence: 99%

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This approach allows chaining transformation operations together to create new images 96 and makes Augmentor a popular choice. 97 , 98 , 99 …”

Section: Going Aimentioning

confidence: 99%

“…This approach allows chaining transformation operations together to create new images 96 and makes Augmentor a popular choice. [97][98][99] Our Augmentor pipeline included rotations (À15 -15 ), shearing (À15 -15 ), skewing (0%-20%), and horizontal flips. Figure 2 displays an illustration of the output of each operation.…”

Section: Ll Open Accessmentioning

confidence: 99%

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

Nakhle

Harfouche

2021

Patterns

View full text Add to dashboard Cite

Summary High-throughput image-based technologies are now widely used in the rapidly developing field of digital phenomics and are generating ever-increasing amounts and diversity of data. Artificial intelligence (AI) is becoming a game changer in turning the vast seas of data into valuable predictions and insights. However, this requires specialized programming skills and an in-depth understanding of machine learning, deep learning, and ensemble learning algorithms. Here, we attempt to methodically review the usage of different tools, technologies, and services available to the phenomics data community and show how they can be applied to selected problems in explainable AI-based image analysis. This tutorial provides practical and useful resources for novices and experts to harness the potential of the phenomic data in explainable AI-led breeding programs.

show abstract

“…The proposed LU-net model performed recall 1.00%, precision 97%, F-score 98%, specificity 95%, and the accuracy of 98% for detecting tumors. Abdelhalim et al [19] proposed the self-attention mechanism to detect skin melanoma images used for convolutional neural networks based on dimensionality reduction and to achieve better results. The proposed self-attention model performed macro recall 64.7%, AUC 79.3%, macro precision 50.1%, macro F-score 53.4%, average training time in minutes is 16.3, and the accuracy of this model is 66.1% for dimensionality reduction.…”

Section: Literature Surveymentioning

confidence: 99%

A Comparative Study on Augmented Analytics Using Deep Learning Techniques

Anusha

Kiruthika

2021

Smart Innovation, Systems and Technologies

View full text Add to dashboard Cite

Image augmentation is the most recognized type of data augmentation and intrinsic development for transforming image diversities in the training dataset that belongs to a similar class as the novel image. In the area of image augmentation handling, a collection of operations is shifting, flipping, zooming, cropping, rotation, and transformation in color space. A wide range of applications frequently used the aspects of deep learning are industry, science, and government domain, namely adaptive testing, image classification, computer vision, object detection, and face recognition and has achieved substantial development and accomplishment of deep learning. This study concentrates on the most important challenges present in the image estimation level that have a significant effect on dimension reduction, pooling, and edge detection. The deep learning methods involved here are convolution neural network (CNN), generative adversarial network (GAN), and deep convolution neural network (DCNN). Finally, a comparative study has performed a massive literature survey on various deep learning models.

show abstract

Data augmentation for skin lesion using self-attention based progressive generative adversarial network

Cited by 85 publications

References 26 publications

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

A Comparative Study on Augmented Analytics Using Deep Learning Techniques

Contact Info

Product

Resources

About