Memory-aware curriculum federated learning for breast cancer classification

Jiménez-Sánchez, Amelia; Tardy, Mickael; Ballester, Miguel Ángel González; Mateus, Diana; Piella, Gemma

doi:10.1016/j.cmpb.2022.107318

Cited by 56 publications

(24 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common target disease was cancer (17 studies, one of which [34] involved thyroid nodules) [21][22][23][24][25][26][27][28][29][30][31][32][33][34]56,69,73]. The second most common target disease was COVID-19 (12 studies) due to the recent worldwide COVID-19 pandemic [35][36][37][38][39][40][41][42][43][71][72][73].…”

Section: Target Diseasesmentioning

confidence: 99%

Survey of Medical Applications of Federated Learning

Choi,

Cha,

Lee

et al. 2024

Healthc Inform Res

View full text Add to dashboard Cite

Objectives: Medical artificial intelligence (AI) has recently attracted considerable attention. However, training medical AI models is challenging due to privacy-protection regulations. Among the proposed solutions, federated learning (FL) stands out. FL involves transmitting only model parameters without sharing the original data, making it particularly suitable for the medical field, where data privacy is paramount. This study reviews the application of FL in the medical domain.Methods: We conducted a literature search using the keywords "federated learning" in combination with "medical," "healthcare," or "clinical" on Google Scholar and PubMed. After reviewing titles and abstracts, 58 papers were selected for analysis. These FL studies were categorized based on the types of data used, the target disease, the use of open datasets, the local model of FL, and the neural network model. We also examined issues related to heterogeneity and security.Results: In the investigated FL studies, the most commonly used data type was image data, and the most studied target diseases were cancer and COVID-19. The majority of studies utilized open datasets. Furthermore, 72% of the FL articles addressed heterogeneity issues, while 50% discussed security concerns.Conclusions: FL in the medical domain appears to be in its early stages, with most research using open data and focusing on specific data types and diseases for performance verification purposes. Nonetheless, medical FL research is anticipated to be increasingly applied and to become a vital component of multi-institutional research.

show abstract

Section: Target Diseasesmentioning

confidence: 99%

Survey of Medical Applications of Federated Learning

Choi,

Cha,

Lee

et al. 2024

Healthc Inform Res

View full text Add to dashboard Cite

show abstract

“…Regarding breast imaging, only two papers [33], [34] have evaluated breast density classification. The authors employed a client server-based FL method with federated averaging VOLUME 4, 2016 (FedAvg) [7], which combines local stochastic gradient descent (SGD) on each site with a server that performs model averaging.…”

Section: B Federated Learningmentioning

confidence: 99%

“…Moreover, this study did not apply any domain adaptation techniques to compensate for the domain shift of different pixel intensity distributions. The authors [33] opted for a different approach by working on high-resolution mammograms with federated domain adversarial learning [34]. In addition, they [34] applied curriculum learning in FL to boost classification performance while improving domain alignment and explicitly handling domain shift with federated adversarial domain adaptation.…”

Section: B Federated Learningmentioning

confidence: 99%

“…The authors [33] opted for a different approach by working on high-resolution mammograms with federated domain adversarial learning [34]. In addition, they [34] applied curriculum learning in FL to boost classification performance while improving domain alignment and explicitly handling domain shift with federated adversarial domain adaptation. The paper employs three datasets of Full Field Digital Mammography (FFDM), and the experimental results shown that the proposed memory-aware curriculum method is beneficial to further improve classification performance.…”

Section: B Federated Learningmentioning

confidence: 99%

See 1 more Smart Citation

A Transfer Learning Approach to Breast Cancer Classification in a Federated Learning Framework

et al. 2023

View full text Add to dashboard Cite

Artificial intelligence (AI) technologies have seen strong development. Many applications now use AI to diagnose breast cancer. However, most new research has only been conducted in centralized learning (CL) environments, which entails the risk of privacy breaches. Moreover, the accurate identification and localization of lesions and tumor prediction using AI technologies is expected to increase patients' likelihood of survival. To address these difficulties, we developed a federated learning (FL) facility that extracts features from participating environments rather than a CL facility. This study's novel contributions include (i) the application of transfer learning to extract data features from the region of interest (ROI) in an image, which aims to enable careful pre-processing and data enhancement for data training purposes; (ii) the use of synthetic minority oversampling technique (SMOTE) to process data, which aims to more uniformly classify data and improve diagnostic prediction performance for diseases; (iii) the application of FeAvg-CNN + MobileNet in an FL framework to ensure customer privacy and personal security; and (iv) the presentation of experimental results from different deep learning, transfer learning and FL models with balanced and imbalanced mammography datasets, which demonstrate that our solution leads to much higher classification performance than other approaches and is viable for use in AI healthcare applications.

show abstract

“…Kim et al 2 were among the first to report an FL analytic framework to transform electronic medical data into computational phenotypes without sharing patient-level data between the participating sites. Similarly, Jiménez-Sánchez et al 3 demonstrated the feasibility of an FL-based computational framework for classifying breast cancer on high-resolution mammograms across multiple institutions. Dang et al 4 analyzed the eICU synergetic database using FL framework models to predict patient mortality in critical care settings.…”

mentioning

confidence: 98%