On the Effectiveness of Generative Adversarial Networks as HEp-2 Image Augmentation Tool

Majtner, Tomáš; Bajić, Buda; Lindblad, Joakim; Sladoje, Nataša; Blanes-Vidal, Victoria; Nadimi, Esmaeil S.

doi:10.1007/978-3-030-20205-7_36

Cited by 14 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This implying that GANs' capacity of generating diverse data is still limited due to mode dropping and collapsing. Similar findings were observed by [45] who used DCGAN for generating HEp-2 cell images. However, unlike their combined augmentation methods' results, within some data-size limits, using InfoWGANGP generated data as a complementary augmentation method is found to be beneficial to improve the classification performance.…”

Section: Classsupporting

confidence: 85%

“…To the best of our knowledge, the work proposed by Majtner et al [45] is the only published study that has proposed to explore using GAN-based synthesized images as a data augmentation method for HEp-2 cell-level classification task. In their work, an individual DCGAN [10] model was trained for each HEp-2 class in the I3A dataset [4] to cope with the high within-class heterogeneity of HEp-2 data.…”

Section: Gans For Hep-2 Image Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Studying the Applicability of Generative Adversarial Networks on HEp-2 Cell Image Augmentation

2021

View full text Add to dashboard Cite

The Anti-Nuclear Antibodies (ANAs) testing is the primary serological diagnosis screening test for autoimmune diseases. ANAs testing is conducted mainly by the Indirect Immunofluorescence (IIF) on Human Epithelial cell-substrate (HEp-2) protocol. However, due to its high variability, humansubjectivity, and low throughput, there is an insistent need to develop an efficient Computer-Aided Diagnosis system (CADs) to automate this protocol. Many recently proposed Convolutional Neural Networks (CNNs) demonstrated promising results in HEp-2 cell image classification, which is the main task of the HE-p2 IIF protocol. However, the lack of large labeled datasets is still the main challenge in this field. This work provides a detailed study of the applicability of using generative adversarial networks (GANs) algorithms as an augmentation method. Different types of GANs were employed to synthesize HEp-2 cell images to address the data scarcity problem. For systematic comparison, empirical quantitative metrics were implemented to evaluate different GAN models' performance of learning the real data representations. The results of this work showed that though the high visual similarity with the real images, GANs' capacity to generate diverse data is still limited. This deficiency in the generated data diversity is found to be of a crucial impact when used as a standalone method for augmentation. However, combining limited-size GANsgenerated data with classic augmentation improves the classification accuracy across different variants of CNNs. Our results demonstrated a competitive performance for the overall classification accuracy and the mean class accuracy of the HEp-2 cell image classification task.INDEX TERMS Computer-aided diagnosis systems (CADs), Convolutional Neural Networks (CNNs), Data augmentation, Data diversity, Evaluation metrics, Generative adversarial networks (GANs), HEp-2 cell image classification.

show abstract

Section: Classsupporting

confidence: 85%

Section: Gans For Hep-2 Image Classificationmentioning

confidence: 99%

Studying the Applicability of Generative Adversarial Networks on HEp-2 Cell Image Augmentation

2021

View full text Add to dashboard Cite

show abstract

“…Generic DNN based methods use the popular DNN architectures to perform CL-HEP2IC. The methods proposed in [10,14,23,24,43] are of this kind. Since the generic CNNs are primarily designed for the general image classification tasks such as ImageNet classification [32], pre-processing techniques such as image enhancement and DA (i.e., data augmentation) are carefully considered in most of these papers to achieve high CL-HEP2IC performance.…”

Section: Cell-level Hep-2 (Cl-hep2ic) Methods That Use Dnn As a Class...mentioning

confidence: 99%

Deep Learning based HEp-2 Image Classification: A Comprehensive Review

Rahman,

Wang,

Sun

et al. 2019

Preprint

View full text Add to dashboard Cite

Classification of HEp-2 cell patterns plays a significant role in the indirect immunofluorescence test for identifying autoimmune diseases in the human body. Many automatic HEp-2 cell classification methods have been proposed in recent years, amongst which deep learning based methods have shown impressive performance. This paper provides a comprehensive review of the existing deep learning based HEp-2 cell image classification methods. These methods perform HEp-2 image classification in two levels, namely, cell-level and specimen-level. Both levels are covered in this review. In each level, the methods are organized with a deep network usage based taxonomy. The core idea, notable achievements, and key advantages and weakness of each method are critically analyzed. Furthermore, a concise review of the existing HEp-2 datasets that are commonly used in the literature is given. The paper ends with an overview of the current state-of-the-arts and a discussion on novel opportunities and future research directions in this field. It is hoped that this paper would give readers a comprehensive reference of this novel, challenging, and thriving field.

show abstract

“…Conventional methods were dominating until recently; examples are ensembles of support vector machines (SVMs) [31] and a method based on spatial shape index descriptor with local orientation adaptive descriptor [32]. Latest publications, however, focus on deep learning‐based approaches [33–37].…”

Section: Related Workmentioning

confidence: 99%

Generalised deep learning framework for HEp‐2 cell recognition using local binary pattern maps

et al. 2020

Self Cite

View full text Add to dashboard Cite

The authors propose a novel HEp‐2 cell image classifier to improve the automation process of patients' serum evaluation. The authors' solution builds on the recent progress in deep learning based image classification. They propose an ensemble approach using multiple state‐of‐the‐art architectures. They incorporate additional texture information extracted by an improved version of local binary patterns maps, αLBP‐maps, which enables to create a very effective cell image classifier. This innovative combination is trained on three publicly available datasets and its general applicability is demonstrated through the evaluation on three independent test sets. The presented results show that their approach leads to a general improvement of performance on average on the three public datasets.

show abstract

On the Effectiveness of Generative Adversarial Networks as HEp-2 Image Augmentation Tool

Cited by 14 publications

References 20 publications

Studying the Applicability of Generative Adversarial Networks on HEp-2 Cell Image Augmentation

Studying the Applicability of Generative Adversarial Networks on HEp-2 Cell Image Augmentation

Deep Learning based HEp-2 Image Classification: A Comprehensive Review

Generalised deep learning framework for HEp‐2 cell recognition using local binary pattern maps

Contact Info

Product

Resources

About