Scalable Federated-Learning and Internet-of-Things enabled architecture for Chest Computer Tomography image classification

Dara, Suresh; Kanapala, Ambedkar; Babu, Arun; Dhamercherala, Swetha; Vidyarthi, Ankit; Agarwal, Ruchi

doi:10.1016/j.compeleceng.2022.108266

Cited by 7 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other papers limit themselves to training and evaluating on the MosMed dataset but are difficult to compare against due to differences in their methods and evaluation frameworks. Of note are Dara et [35]. This could artificially inflate performance due to repeated experiments.…”

Section: Methodological Deviationsmentioning

confidence: 99%

“…However, several works already cover learning from 2D slices, and learning directly from 3D representations in a high-dimensionality regime with few samples is a much more challenging problem. Finally, both Bridge et al, 2023 and Dara et al report inconsistent results, which vary strongly based on the choice of the threshold [29,35]. With an inability to optimize the threshold without considering the validation data, it is difficult to comment on the appropriate metrics to compare from there.…”

Section: Methodological Deviationsmentioning

confidence: 99%

See 1 more Smart Citation

CoSev: Data-Driven Optimizations for COVID-19 Severity Assessment in Low-Sample Regimes

Garg,

Alag,

Duncan

2024

Diagnostics

View full text Add to dashboard Cite

Given the pronounced impact COVID-19 continues to have on society—infecting 700 million reported individuals and causing 6.96 million deaths—many deep learning works have recently focused on the virus’s diagnosis. However, assessing severity has remained an open and challenging problem due to a lack of large datasets, the large dimensionality of images for which to find weights, and the compute limitations of modern graphics processing units (GPUs). In this paper, a new, iterative application of transfer learning is demonstrated on the understudied field of 3D CT scans for COVID-19 severity analysis. This methodology allows for enhanced performance on the MosMed Dataset, which is a small and challenging dataset containing 1130 images of patients for five levels of COVID-19 severity (Zero, Mild, Moderate, Severe, and Critical). Specifically, given the large dimensionality of the input images, we create several custom shallow convolutional neural network (CNN) architectures and iteratively refine and optimize them, paying attention to learning rates, layer types, normalization types, filter sizes, dropout values, and more. After a preliminary architecture design, the models are systematically trained on a simplified version of the dataset-building models for two-class, then three-class, then four-class, and finally five-class classification. The simplified problem structure allows the model to start learning preliminary features, which can then be further modified for more difficult classification tasks. Our final model CoSev boosts classification accuracies from below 60% at first to 81.57% with the optimizations, reaching similar performance to the state-of-the-art on the dataset, with much simpler setup procedures. In addition to COVID-19 severity diagnosis, the explored methodology can be applied to general image-based disease detection. Overall, this work highlights innovative methodologies that advance current computer vision practices for high-dimension, low-sample data as well as the practicality of data-driven machine learning and the importance of feature design for training, which can then be implemented for improvements in clinical practices.

show abstract

Section: Methodological Deviationsmentioning

confidence: 99%

Section: Methodological Deviationsmentioning

confidence: 99%

CoSev: Data-Driven Optimizations for COVID-19 Severity Assessment in Low-Sample Regimes

Garg,

Alag,

Duncan

2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Due to the fact that federated learning does not necessitate the exchange of personally identifiable information, it is an excellent option for institutions and nations that adhere to stringent privacy policies. Using repositories like The Cancer Genome Atlas (TCGA), analysis can be performed on the effects of IID and non-IID distributions, and the sizes of single datasets [22]. According to [22], a framework that allows for the collaborative development of machine learning models for medical image analysis through differentially private federated learning is one that is both practicable and dependable.…”

Section: Related Workmentioning

confidence: 99%

“…Using repositories like The Cancer Genome Atlas (TCGA), analysis can be performed on the effects of IID and non-IID distributions, and the sizes of single datasets [22]. According to [22], a framework that allows for the collaborative development of machine learning models for medical image analysis through differentially private federated learning is one that is both practicable and dependable.…”

Section: Related Workmentioning

confidence: 99%

Federated Learning for Healthcare: A Comprehensive Review

Dhade,

Shirke

2024

RAiSE-2023

View full text Add to dashboard Cite

show abstract

“…The result showed that the maximum accuracy of 98.59% and 95.05% was achieved via WAE. Dara et al [264] applied ResNet architecture to implement the classification algorithms to identify COVID-19. The authors used ResNet18, ResNet50, ResNet101 and compared their performance.…”

mentioning

confidence: 99%

A Systematic Review on Deep Structured Learning for COVID-19 Screening Using Chest CT from 2020 to 2022

Santosh,

GhoshRoy,

Nakarmi

2023

Healthcare

View full text Add to dashboard Cite

The emergence of the COVID-19 pandemic in Wuhan in 2019 led to the discovery of a novel coronavirus. The World Health Organization (WHO) designated it as a global pandemic on 11 March 2020 due to its rapid and widespread transmission. Its impact has had profound implications, particularly in the realm of public health. Extensive scientific endeavors have been directed towards devising effective treatment strategies and vaccines. Within the healthcare and medical imaging domain, the application of artificial intelligence (AI) has brought significant advantages. This study delves into peer-reviewed research articles spanning the years 2020 to 2022, focusing on AI-driven methodologies for the analysis and screening of COVID-19 through chest CT scan data. We assess the efficacy of deep learning algorithms in facilitating decision making processes. Our exploration encompasses various facets, including data collection, systematic contributions, emerging techniques, and encountered challenges. However, the comparison of outcomes between 2020 and 2022 proves intricate due to shifts in dataset magnitudes over time. The initiatives aimed at developing AI-powered tools for the detection, localization, and segmentation of COVID-19 cases are primarily centered on educational and training contexts. We deliberate on their merits and constraints, particularly in the context of necessitating cross-population train/test models. Our analysis encompassed a review of 231 research publications, bolstered by a meta-analysis employing search keywords (COVID-19 OR Coronavirus) AND chest CT AND (deep learning OR artificial intelligence OR medical imaging) on both the PubMed Central Repository and Web of Science platforms.

show abstract

Scalable Federated-Learning and Internet-of-Things enabled architecture for Chest Computer Tomography image classification

Cited by 7 publications

References 15 publications

CoSev: Data-Driven Optimizations for COVID-19 Severity Assessment in Low-Sample Regimes

CoSev: Data-Driven Optimizations for COVID-19 Severity Assessment in Low-Sample Regimes

Federated Learning for Healthcare: A Comprehensive Review

A Systematic Review on Deep Structured Learning for COVID-19 Screening Using Chest CT from 2020 to 2022

Contact Info

Product

Resources

About