Federated learning based Covid‐19 detection

Chowdhury, Deepraj; Banerjee, Soham; Sannigrahi, Madhushree; Chakraborty, Arka; Das, Anik; Dey, Aritra; Dwivedi, Ashutosh Dhar

doi:10.1111/exsy.13173

Cited by 22 publications

(12 citation statements)

References 25 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…66 With an average AUC greater than 0.92, EXAM successfully predicts outcomes at 24 and 72 h after patients initially present to the emergency room. 66 Chowdhury et al 67 developed DL models (Xception, ResNet50, DenseNet121, and InceptionV3) using 1823 images consisting of COVID-19 pneumonia, non-COVID-19 pneumonia, and healthy controls. They implemented FL through a pre-trained transfer learning model.…”

Section: Discussionmentioning

confidence: 99%

Differential privacy preserved federated learning for prognostic modeling in COVID‐19 patients using large multi‐institutional chest CT dataset

Shiri,

Salimi,

Sirjani

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundNotwithstanding the encouraging results of previous studies reporting on the efficiency of deep learning (DL) in COVID‐19 prognostication, clinical adoption of the developed methodology still needs to be improved. To overcome this limitation, we set out to predict the prognosis of a large multi‐institutional cohort of patients with COVID‐19 using a DL‐based model.PurposeThis study aimed to evaluate the performance of deep privacy‐preserving federated learning (DPFL) in predicting COVID‐19 outcomes using chest CT images.MethodsAfter applying inclusion and exclusion criteria, 3055 patients from 19 centers, including 1599 alive and 1456 deceased, were enrolled in this study. Data from all centers were split (randomly with stratification respective to each center and class) into a training/validation set (70%/10%) and a hold‐out test set (20%). For the DL model, feature extraction was performed on 2D slices, and averaging was performed at the final layer to construct a 3D model for each scan. The DensNet model was used for feature extraction. The model was developed using centralized and FL approaches. For FL, we employed DPFL approaches. Membership inference attack was also evaluated in the FL strategy. For model evaluation, different metrics were reported in the hold‐out test sets. In addition, models trained in two scenarios, centralized and FL, were compared using the DeLong test for statistical differences.ResultsThe centralized model achieved an accuracy of 0.76, while the DPFL model had an accuracy of 0.75. Both the centralized and DPFL models achieved a specificity of 0.77. The centralized model achieved a sensitivity of 0.74, while the DPFL model had a sensitivity of 0.73. A mean AUC of 0.82 and 0.81 with 95% confidence intervals of (95% CI: 0.79–0.85) and (95% CI: 0.77–0.84) were achieved by the centralized model and the DPFL model, respectively. The DeLong test did not prove statistically significant differences between the two models (p‐value = 0.98). The AUC values for the inference attacks fluctuate between 0.49 and 0.51, with an average of 0.50 ± 0.003 and 95% CI for the mean AUC of 0.500 to 0.501.ConclusionThe performance of the proposed model was comparable to centralized models while operating on large and heterogeneous multi‐institutional datasets. In addition, the model was resistant to inference attacks, ensuring the privacy of shared data during the training process.

show abstract

Section: Discussionmentioning

confidence: 99%

Differential privacy preserved federated learning for prognostic modeling in COVID‐19 patients using large multi‐institutional chest CT dataset

Shiri,

Salimi,

Sirjani

et al. 2024

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Several distinct approaches have been developed to tackle the aggregation of non-IID data. These approaches make use of a variety of aggregation algorithms, such as FedMA [ 46 ], feature fusion [ 47 ], and grouping of related client models [ 39 , 48 , 49 ]. In the clustering process, similarity among client models is exploited [ 27 ], and encouraging excellent communication is one of the ways that data generalization is increased [ 22 ].…”

Section: Literature Reviewmentioning

confidence: 99%

DMFL_Net: A Federated Learning-Based Framework for the Classification of COVID-19 from Multiple Chest Diseases Using X-rays

Malik

Naeem

Loh

2023

Sensors

View full text Add to dashboard Cite

Coronavirus Disease 2019 (COVID-19) is still a threat to global health and safety, and it is anticipated that deep learning (DL) will be the most effective way of detecting COVID-19 and other chest diseases such as lung cancer (LC), tuberculosis (TB), pneumothorax (PneuTh), and pneumonia (Pneu). However, data sharing across hospitals is hampered by patients’ right to privacy, leading to unexpected results from deep neural network (DNN) models. Federated learning (FL) is a game-changing concept since it allows clients to train models together without sharing their source data with anybody else. Few studies, however, focus on improving the model’s accuracy and stability, whereas most existing FL-based COVID-19 detection techniques aim to maximize secondary objectives such as latency, energy usage, and privacy. In this work, we design a novel model named decision-making-based federated learning network (DMFL_Net) for medical diagnostic image analysis to distinguish COVID-19 from four distinct chest disorders including LC, TB, PneuTh, and Pneu. The DMFL_Net model that has been suggested gathers data from a variety of hospitals, constructs the model using the DenseNet-169, and produces accurate predictions from information that is kept secure and only released to authorized individuals. Extensive experiments were carried out with chest X-rays (CXR), and the performance of the proposed model was compared with two transfer learning (TL) models, i.e., VGG-19 and VGG-16 in terms of accuracy (ACC), precision (PRE), recall (REC), specificity (SPF), and F1-measure. Additionally, the DMFL_Net model is also compared with the default FL configurations. The proposed DMFL_Net + DenseNet-169 model achieves an accuracy of 98.45% and outperforms other approaches in classifying COVID-19 from four chest diseases and successfully protects the privacy of the data among diverse clients.

show abstract

“…Initially, they applied a min-max data normalization approach for data and later they applied an optimizer for hyperparameter optimization for the model. Some other recent work [21,22] has been done in this direction where authors worked on the privacy of healthcare data.…”

Section: Related Workmentioning

confidence: 99%

Secret learning for lung cancer diagnosis—a study with homomorphic encryption, texture analysis and deep learning

Adhikary,

Dutta,

Dwivedi

2023

Biomed. Phys. Eng. Express

Self Cite

View full text Add to dashboard Cite

Advanced lung cancer diagnoses from radiographic images include automated detection of lung cancer from CT-Scan images of the lungs. Deep learning is a popular method for decision making which can be used to classify cancerous and non-cancerous lungs from CT-Scan images. There are many experiments which show the uses of deep learning for performing such classifications but very few of them have preserved the privacy of users. Among existing methods, federated learning limits data sharing to a central server and differential privacy although increases anonymity the original data is still shared. Homomorphic encryption can resolve the limitations of both of these. Homomorphic encryption is a cryptographic technique that allows computations to be performed on encrypted data. In our experiment, we have proposed a series of textural information extraction with the implementation of homomorphic encryption of the CT-Scan images of normal, adenocarcinoma, large cell carcinoma and squamous cell carcinoma. We have further processed the encrypted data to make it classifiable and later we have classified it with deep learning. The results from the experiments have obtained a classification accuracy of 0.9347.

show abstract

Federated learning based Covid‐19 detection

Cited by 22 publications

References 25 publications

Differential privacy preserved federated learning for prognostic modeling in COVID‐19 patients using large multi‐institutional chest CT dataset

Differential privacy preserved federated learning for prognostic modeling in COVID‐19 patients using large multi‐institutional chest CT dataset

DMFL_Net: A Federated Learning-Based Framework for the Classification of COVID-19 from Multiple Chest Diseases Using X-rays

Secret learning for lung cancer diagnosis—a study with homomorphic encryption, texture analysis and deep learning

Contact Info

Product

Resources

About