Generative adversarial networks (GAN)-based data augmentation of rare liver cancers: The SFR 2021 Artificial Intelligence Data Challenge

Mulé, Sebastien; Lawrance, Littisha; Belkouchi, Younes; Vilgrain, Valérie; Lewin, M.; Trillaud, Hervé; Hoeffel, Christine; Laurent, V.; Ammari, Samy; Morand, Eric; Faucoz, Orphée; Tenenhaus, Arthur; Cotten, Anne; Méder, Jean-François; Talbot, Hugues; Luciani, Alain; Lassau, Nathalie

doi:10.1016/j.diii.2022.09.005

Cited by 11 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research article [41] proposed a GAN-based framework for information encoding in acoustic data for modeling lexical learning. The article [42] showcased a novel GAN-based methodology for augmenting data pertaining to rare liver cancers and depicted an exemplary performance across various evaluation metrics.…”

Section: Methodsmentioning

confidence: 99%

An Empirical Analysis of Diffusion, Autoencoders, and Adversarial Deep Learning Models for Predicting Dementia Using High-Fidelity MRI

Gajjar,

Garg,

Desai

et al. 2024

IEEE Access

View full text Add to dashboard Cite

This study explores cutting-edge computational technologies and intelligent methods to create realistic synthetic data, focusing on dementia-centric Magnetic Resonance Imaging (MRI) scans related to Alzheimer's and Parkinson's diseases. The research delves into Generative Adversarial Networks (GANs), Variational Autoencoders, and Diffusion Models, comparing their efficacy in generating synthetic MRI scans. Using datasets from Alzheimer's and Parkinson's patients, the study reveals intriguing findings. In the Alzheimer dataset, diffusion models produced non-dementia images with the lowest Frechet Inception Distance (FID) score at 92.46, while data-efficient GANs excelled in generating dementia images with an FID score of 178.53. In the Parkinson dataset, data-efficient GANs achieved remarkable FID scores of 102.71 for dementia images and 129.77 for non-dementia images. The study also introduces a novel aspect by incorporating a classification study, validating the generative metrics. DenseNets, a deep learning architecture, exhibited superior performance in disease detection compared to ResNets. Training both models on images generated by diffusion models further improved results, with DenseNet achieving accuracies of 80.84% and 92.42% in Alzheimer's and Parkinson's disease detection, respectively. The research not only presents innovative generative architectures but also emphasizes the importance of classification metrics, providing valuable insights into the synthesis and detection of neurodegenerative diseases through advanced computational techniques.

show abstract

Section: Methodsmentioning

confidence: 99%

An Empirical Analysis of Diffusion, Autoencoders, and Adversarial Deep Learning Models for Predicting Dementia Using High-Fidelity MRI

Gajjar,

Garg,

Desai

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…There are multiple examples in the literature that prove how fake images are beneficial for classification algorithms that need a significant amount of images for training when real data are not easy available [9][10][11][12]. One example is the work of Mulé et al [4], whih showed that generative models are effective in constructing images of uncommon medical cases. In their research, the authors produced a substantial amount of fake images depicting macrotrabecular-massive hepatocellular carcinoma from a restricted number of cases.…”

Section: Related Work 21 Image Generationmentioning

confidence: 99%

“…The sequences of images produced by the proposed model have various applications. The most frequent use is data augmentation for training other machine learning models that perform classification, prediction, and detection tasks [3,4]. This objective is particularly valuable in this field of study because acquiring such data is often highly costly both in terms of time and materials [5].…”

Section: Introductionmentioning

confidence: 99%

Temporal Development GAN (TD-GAN): Crafting More Accurate Image Sequences of Biological Development

Celard,

Seara Vieira,

Sorribes-Fdez

et al. 2023

Information

View full text Add to dashboard Cite

In this study, we propose a novel Temporal Development Generative Adversarial Network (TD-GAN) for the generation and analysis of videos, with a particular focus on biological and medical applications. Inspired by Progressive Growing GAN (PG-GAN) and Temporal GAN (T-GAN), our approach employs multiple discriminators to analyze generated videos at different resolutions and approaches. A new Temporal Discriminator (TD) that evaluates the developmental coherence of video content is introduced, ensuring that the generated image sequences follow a realistic order of stages. The proposed TD-GAN is evaluated on three datasets: Mold, Yeast, and Embryo, each with unique characteristics. Multiple evaluation metrics are used to comprehensively assess the generated videos, including the Fréchet Inception Distance (FID), Frechet Video Distance (FVD), class accuracy, order accuracy, and Mean Squared Error (MSE). Results indicate that TD-GAN significantly improves FVD scores, demonstrating its effectiveness in generating more coherent videos. It achieves competitive FID scores, particularly when selecting the appropriate number of classes for each dataset and resolution. Additionally, TD-GAN enhances class accuracy, order accuracy, and reduces MSE compared to the default model, demonstrating its ability to generate more realistic and coherent video sequences. Furthermore, our analysis of stage distribution in the generated videos shows that TD-GAN produces videos that closely match the real datasets, offering promising potential for generating and analyzing videos in different domains, including biology and medicine.

show abstract

“…One option to increase the prevalence of rare conditions or obtain a distribution that mirrors those of the real world to better train the model is to enrich the dataset using synthetic images obtained with data augmentation techniques, but this requires further investigation. 4 Finally, AI models need to be validated over time. This is because diseases prevalence or presentation of certain conditions may also change over time due to new treatment for example.…”

mentioning

confidence: 99%

“…6 Current research suggests that AI can be used as a first reader in a few selected indications that are simple and single tasks. 4 But the radiologic community is expecting strong AI algorithms that would have capabilities similar to those of an expert radiologist. We can say that there is a long way to go to reach this goal.…”

mentioning

confidence: 99%

Applications of Artificial Intelligence in Urological Oncology Imaging: More Data Are Needed

2023

View full text Add to dashboard Cite

Generative adversarial networks (GAN)-based data augmentation of rare liver cancers: The SFR 2021 Artificial Intelligence Data Challenge

Cited by 11 publications

References 16 publications

An Empirical Analysis of Diffusion, Autoencoders, and Adversarial Deep Learning Models for Predicting Dementia Using High-Fidelity MRI

An Empirical Analysis of Diffusion, Autoencoders, and Adversarial Deep Learning Models for Predicting Dementia Using High-Fidelity MRI

Temporal Development GAN (TD-GAN): Crafting More Accurate Image Sequences of Biological Development

Applications of Artificial Intelligence in Urological Oncology Imaging: More Data Are Needed

Contact Info

Product

Resources

About