Generative adversarial network based data augmentation to improve cervical cell classification model

Yu, Suxiang; Zhang, Shuai; Wang, Bin; Dun, Hua; Xu, Long; Huang, Xin; Shi, Ermin; Feng, Xinxing

doi:10.3934/mbe.2021090

Cited by 25 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The oldest publication on cell image augmentation is from 2017. Considering that only a single publication used the Vanilla GAN architectures [28], and that Deep Convolutional GAN (DCGAN) [29] was published in 2016, we suppose that GAN was not powerful enough to produce realistic microscopy images before 2016.…”

Section: Year Of Publicationmentioning

confidence: 99%

Generative adversarial networks in cell microscopy for image augmentation. A systematic review

Lesmes-Leon,

Dengel,

Ahmed

2023

Preprint

View full text Add to dashboard Cite

Cell microscopy is the main tool that allows researchers to study microorganisms and plays a key role in observing and understanding the morphology, interactions, and development of microorganisms. However, there exist limitations in both the techniques and the samples that impair the amount of available data to study. Generative adversarial networks (GANs) are a deep learning alternative to alleviate the data availability limitation by generating nonexistent samples that resemble the probability distribution of the real data. The aim of this systematic review is to find trends, common practices, popular datasets, and analyze the impact of GANs in image augmentation of cell microscopy images. We used ScienceDirect, IEEE Xplore, PubMed, bioRxiv, and arXiv to select English research articles that employed GANs to generate any kind of cell microscopy images independently of the main objective of the study. We conducted the data collection using 15 selected features from each study, which allowed us to analyze the results from different perspectives using tables and histograms. 32 studies met the legibility criteria, where 18 had image augmentation as the main task. Moreover, we retrieved 21 publicly available datasets. The results showed a lack of consensus with performance metrics, baselines, and datasets. Additionally, we evidenced the relevance of popular architectures such as StyleGAN and losses including Vanilla and Wasserstein adversarial loss. This systematic review presents the most popular configurations to perform image augmentation. It also highlights the importance of design good practices and gold standards to guarantee comparability and reproducibility. This review implemented the ROBIS tool to assess the risk of bias, and it was not registered in PROSPERO.

show abstract

Section: Year Of Publicationmentioning

confidence: 99%

Generative adversarial networks in cell microscopy for image augmentation. A systematic review

Lesmes-Leon,

Dengel,

Ahmed

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Lacking the learnable pixels is the physical property based on the sparsity as illustrated in Figure .1 (a), unlike the nature scene is various for interesting objects and modality, or the histopathological objects are sizable and clustered. To train with the plentiful data, on the one hand, the image augmentation on color and shape transformations or results of GAN is significant on the variant cervical dataset ( [13,14]), which is also a known trick in natural tasks ( [15]) and valid to deal with WSIs are multicohort or multicenter. On the other hand, despite there is no related work of cervical prediction, the procedure, firstly training in the primary labeled data and then complementing labels manually checked from unlabeled data predicted by trained models, is firstly proposed by [16] to efficiently augment the pathological database at the patch level.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Spatial Deep Features

Wei¹,

Cheng²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Digital gigapixel whole slide image (WSI) is widely used in clinical diagnosis, and automated WSI analysis is key for computer-aided diagnosis. Currently, analyzing the integrated descriptor of probabilities or feature maps from massive local patches encoded by ResNet classifier is the main manner for WSI-level prediction. Feature representations of the sparse and tiny lesion cells in cervical slides, however, are still challengeable for the under-promoted upstream encoders, while the unused spatial representations of cervical cells are the available features to supply the semantics analysis. As well as patches sampling with overlap and repetitive processing incur the inefficiency and the unpredictable side effect. This study designs a novel inline connection network (InCNet) by enriching the multi-scale connectivity to build the lightweight model named You Only Look Cytopathology Once (YOLCO) with the additional supervision of spatial information. The proposed model allows the input size enlarged to megapixel that can stitch the WSI without any overlap by the average repeats decreased from 10 3 ∼ 10 4 to 10 1 ∼ 10 2 for collecting features and predictions at two scales. Based on Transformer for classifying the integrated multi-scale multi-task features, the experimental results appear 0.872 AUC score better and 2.51× faster than the best conventional method in WSI classification on multicohort datasets of 2,019 slides from four scanning devices.

show abstract

“…This adversarial training process is capable of enhancing the model's resilience to adversarial attacks and perturbations in a different dataset. In recent years, GAN models have shown applications in cancer cell classifications [29]- [32] and neural cell classifications [33]. However, to the best of our knowledge, GAN has not yet been utilized in the context of cardiac cellular systems.…”

Section: Introductionmentioning

confidence: 99%

Generative Adversarial Network Model to Classify Human Induced Pluripotent Stem Cell-Cardiomyocytes based on Maturation Level

Wu,

Park,

Steiner

et al. 2024

Preprint

View full text Add to dashboard Cite

Objective: Our study develops a generative adversarial network (GAN)-based method that generates faithful synthetic image data of human cardiomyocytes at varying stages in their maturation process, as a tool to significantly enhance the classification accuracy of cells and ultimately assist the throughput of computational analysis of cellular structure and functions. Methods: Human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) were cultured on micropatterned collagen coated hydrogels of varied stiffness on which structural and optical measurements were performed to analyze their structural and functional maturation. Control groups were cultured on collagen coated glass well plates. These image recordings were used as the real data to train the GAN model. Results: The GAN approach was able to replicate true features from the real data, and inclusion of such synthetic data significantly improved the classification accuracy compared to he exclusive usage of only real experimental data limited in scale and diversity. Conclusion: The proposed model outperformed four conventional machine learning algorithms by incorporating synthetic data to improve both data generalization and classification. Significance: This work demonstrates the potential utility of integrating synthetic data to effectively address the challenges imposed by constrained data.

show abstract

Generative adversarial network based data augmentation to improve cervical cell classification model

Cited by 25 publications

References 26 publications

Generative adversarial networks in cell microscopy for image augmentation. A systematic review

Generative adversarial networks in cell microscopy for image augmentation. A systematic review

An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Spatial Deep Features

Generative Adversarial Network Model to Classify Human Induced Pluripotent Stem Cell-Cardiomyocytes based on Maturation Level

Contact Info

Product

Resources

About