Federated learning for COVID-19 screening from Chest X-ray images
Open accessAbstract
Today, the whole world is facing a great medical disaster that affects the health and lives of the people: the COVID-19 disease, colloquially known as the Corona virus. Deep learning is an effective means to assist radiologists to analyze the vast amount of chest X-ray images, which can potentially have a substantial role in streamlining and accelerating the diagnosis of COVID-19. Such techniques involve large datasets for training and all such data must be centralized in order to be processed. Due to medical data privacy regulations, it is often not possible to collect and share patient data in a centralized data server. In this work, we present a collaborative federated learning framework allowing multiple medical institutions screening COVID-19 from Chest X-ray images using deep learning without sharing patient data. We investigate several key properties and specificities of federated learning setting including the not independent and identically distributed (non-IID) and unbalanced data distributions that naturally arise. We experimentally demonstrate that the proposed federated learning framework provides competitive results to that of models trained by sharing data, considering two different model architectures. These findings would encourage medical institutions to adopt collaborative process and reap benefits of the rich private data in order to rapidly build a powerful model for COVID-19 screening.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Six out of 17 reviewed articles used chest X-ray images.
“According to our investigation, six articles [18], [23], [25], [27], [29], [32] have used chest X-ray images out of 17.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
Feki et al. [18] proposed a collaborative FL for COVID-19 screening from chest X-ray images, cooperating with multiple medical institutions without sharing their data.
“Feki et al. [18] proposed a collaborative FL for COVID-19 screening from chest X-ray images; they cooperated with multiple medical institutions without sharing their data.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
Four reviewed papers [16], [18], [20], [26] used very small amounts of data: 153, 216, 370, and 180 samples respectively.
“As Table 5 shows, four papers [16], [18], [20] and [26] used very small amounts of data, their number of elements are 153, 216, 370, and 180 respectively.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
For non-IID data, [18] allocated samples among classes unequally by a ratio of 66% and 44%.
“Moreover, for non-IID data they allocated the samples among classes unequally by a ratio of 66% and 44%.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
In [18], Feki et al. divided the collected dataset into four parts for client data; for IID they used an equal number of images from both sides, client and class.
“In [18], Feki et al. divided the collected dataset into four parts for clients data, for IID, they used an equal number of images from both sides, client and class.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
Feki et al. [18] utilized HFL with a chest X-ray dataset where features were the same for all clients but samples differed.
“For example, Feki et al. [18] utilized HFL, they used a chest X-ray image dataset where features are same for all clients but samples are different.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
Feki et al. [18] performed binary classification with the highest accuracy scores: 94.4% for FL+VGG16 with data augmentation and 93.57% for FL+VGG16.
“Feki et al. [18] performed binary classification, their accuracy score is highest, for FL+VGG16 with data augmentation model 94.4% and for FL+VGG16 93.57%.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
In Feki et al. [18], non-IID data is considered.
“non-IID data considered”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
In Feki et al. [18], results comparison is given.
“comparison is given.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
In Feki et al. [18], the number of data samples is very small.
“Number of data samples is very”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
In Feki et al. [18], the proposed FL framework is well described.
“The proposed FL framework is well de-”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
Feki et al. [18] used VGG16 and ResNet50, and FedAvg as the federated algorithm.
“[18] | VGG16 and ResNet50 | FedAvg”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [18]
FL can achieve comparable performance to methods without FL under different settings (training data size, number of clients, IID/Non-IID, balanced/unbalanced) without sacrificing the privacy of end-users.
“The experimental results demonstrate that FL can achieve comparable performance to the methods without FL under these settings without sacrificing the privacy of the end-users.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [50]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 43 · Cited by 278
Research works printed but not linked: 1
- [1]McMahan H.B. Moore E. Ramage D. Hampson S.. Arcas B.A. Communication-efficient learning of deep networks from decentralized data AISTATS 2017 54
- Authors
- Feki, I., Ammar, S., Kessentini, Y., & Muhammad, K.
- Affiliations
- Digital Research Centre of Sfax (TN)
- Sejong University (KR)
- Corresponding author
- Kessentini, Yousri
- Venue
- Applied Soft Computing
- Publisher
- Elsevier BV
- Published
- 2021-07
- Volume
- 106
- Pages
- 107330
- ISSN
- 1568-4946 (ISSN-L)
- PMC
- PMC7979273
- OpenAlex
- W3138795569
- Cited by
- 278
- References
- 43
- Citations by year
- 2026: 30 · 2025: 53 · 2024: 64 · 2023: 79 · 2022: 40 · 2021: 12
- FWCI
- 25.76
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- Applied Soft Computing (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- federated learning, COVID-19 screening, chest X-ray images, medical data privacy, non-IID data, class imbalance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
