Retraction Note: GraphCovidNet: A graph neural network based model for detecting COVID-19 from CT scans and X-rays of chest

Saha, Pritam; Mukherjee, Debadyuti; Singh, Pawan Kumar; Ahmadian, Ali; Феррара, Массимилиано; Sarkar, Ram

doi:10.1038/s41598-021-02469-8

Cited by 16 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aksoy and Salman [33] analysed chest X-ray images of 1019 patients using Capsule Networks (CapsNet) model, designed can detect COVID-19 disease with an accuracy rate of 98.02%. Saha et al [34] proposed GraphCovidNet model to detect COVID-19 from CT-scans and CXRs of the afected patients & evaluated this model on four standard datasets: SARS-COV-2 Ct-Scan dataset, COVID-CT dataset, combination of covid-chestxray-dataset, Chest X-ray Images (Pneumonia) dataset and CMSC-678-MLProject dataset. The model shows an impressive accuracy of 99% for all the datasets and its prediction capability becomes 100% accurate for the binary classification problem of detecting COVID-19 scans.…”

Section: Related Work On Ai Approaches For Covid-19 Detectionmentioning

confidence: 99%

COVID-WideNet—A capsule network for COVID-19 detection

Gupta

Siddiqui²,

Huang³

et al. 2022

Applied Soft Computing

View full text Add to dashboard Cite

Section: Related Work On Ai Approaches For Covid-19 Detectionmentioning

confidence: 99%

COVID-WideNet—A capsule network for COVID-19 detection

Gupta

Siddiqui²,

Huang³

et al. 2022

Applied Soft Computing

View full text Add to dashboard Cite

“…In addition to image features, Song et al (2021) and Liang et al (2021) used the site of acquisition along with other features to build a multi-center graph to combat domain shift and improve COVID-19 detection. Instead of modeling a patient population, Saha et al (2021) converted edges detected in chest CT and Xray images to graphs and leveraged these for detecting COVID-19. Huang et al (2021) used GCNs to refine the bottleneck features for the binary segmentation of COVID-19 infections.…”

Section: Gcns For Covid-19mentioning

confidence: 99%

U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction

Keicher¹,

Burwinkel²,

Bani-Harouni³

et al. 2021

Preprint

View full text Add to dashboard Cite

During the first wave of COVID-19, hospitals were overwhelmed with the high number of admitted patients. An accurate prediction of the most likely individual disease progression can improve the planning of limited resources and finding the optimal treatment for patients. However, when dealing with a newly emerging disease such as COVID-19, the impact of patient-and disease-specific factors (e.g. body weight or known co-morbidities) on the immediate course of disease is by and large unknown. In the case of COVID-19, the need for intensive care unit (ICU) admission of pneumonia patients is often determined only by acute indicators such as vital signs (e.g. breathing rate, blood oxygen levels), whereas statistical analysis and decision support systems that integrate all of the available data could enable an earlier prognosis. To this end, we propose a holistic graph-based approach combining both imaging and non-imaging information. Specifically, we introduce a multimodal similarity metric to build a population graph for clustering patients and an image-based end-to-end Graph Attention Network to process this graph and predict the COVID-19 patient outcomes: admission to ICU, need for ventilation and mortality. Additionally, the network segments chest CT images as an auxiliary task and extracts image features and radiomics for feature fusion with the available metadata. Results on a dataset collected in Klinikum rechts der Isar in Munich, Germany show that our approach outperforms single modality and non-graph baselines. Moreover, our clustering and graph attention allow for increased understanding of the patient relationships within the population graph and provide insight into the network's decision-making process.

show abstract

“…In recent years, Graph Neural Networks (GNNs) have shown satisfying performance in a plethora of real-world applications, e.g., medical diagnosis [27] and credit risk scoring [30], to name a few. In practice, the depth and the number of parameters of GNNs largely Figure 1: A comparison of exhibited bias between teacher and student models based on two representative GNN knowledge distillation frameworks (CPF and GraphAKD).…”

Section: Introductionmentioning

confidence: 99%

Graph-Free Knowledge Distillation for Graph Neural Networks

Deng

Zhang

2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Knowledge distillation (KD) transfers knowledge from a teacher network to a student by enforcing the student to mimic the outputs of the pretrained teacher on training data. However, data samples are not always accessible in many cases due to large data sizes, privacy, or confidentiality. Many efforts have been made on addressing this problem for convolutional neural networks (CNNs) whose inputs lie in a grid domain within a continuous space such as images and videos, but largely overlook graph neural networks (GNNs) that handle non-grid data with different topology structures within a discrete space. The inherent differences between their inputs make these CNN-based approaches not applicable to GNNs. In this paper, we propose to our best knowledge the first dedicated approach to distilling knowledge from a GNN without graph data. The proposed graph-free KD (GFKD) learns graph topology structures for knowledge transfer by modeling them with multinomial distribution. We then introduce a gradient estimator to optimize this framework. Essentially, the gradients w.r.t. graph structures are obtained by only using GNN forward-propagation without back-propagation, which means that GFKD is compatible with modern GNN libraries such as DGL and Geometric. Moreover, we provide the strategies for handling different types of prior knowledge in the graph data or the GNNs. Extensive experiments demonstrate that GFKD achieves the state-of-the-art performance for distilling knowledge from GNNs without training data.

show abstract

Retraction Note: GraphCovidNet: A graph neural network based model for detecting COVID-19 from CT scans and X-rays of chest

Abstract: Editor's Note: this Article has been retracted; the Retraction Note is available at https://doi.org/10.1038/s41598-021-87523-1

Cited by 16 publications

References 0 publications

COVID-WideNet—A capsule network for COVID-19 detection

COVID-WideNet—A capsule network for COVID-19 detection

U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction

Graph-Free Knowledge Distillation for Graph Neural Networks

Contact Info

Product

Resources

About