The automatic segmentation of cell images plays a critical role in medicine and biology, as it enables faster and more accurate analysis and diagnosis. Traditional machine learning faces challenges since it requires transferring sensitive data from laboratories to the cloud, with possible risks and limitations due to patients' privacy, data-sharing regulations, or laboratory privacy guidelines. Federated learning addresses data-sharing issues by introducing a decentralized approach that removes the need for laboratories' data sharing. The learning task is divided among the participating clients, with each training a global model situated on the cloud with its local dataset. This guarantees privacy by only transmitting updated model weights to the cloud. In this study, the centralized learning approach for cell segmentation is compared with the federated one, demonstrating that they achieve similar performances. Stemming from a benchmarking of available cell segmentation models, Cellpose, having shown better recall and precision (F1=0.84) than U-Net (F1=0.50) and StarDist (F1=0.12), was used as the baseline for a federated learning testbench implementation. The results show that both binary segmentation and multi-class segmentation metrics remain high when employing both the centralized solution (F1=0.86) and the federated solution (F12clients=0.86). These results were also stable across an increasing number of clients and a reduced number of local data samples (F14clients=0.87, F116clients=0.86), proving the effectiveness of central aggregation on the cloud of locally trained models.

Federated and Centralized Machine Learning for Cell Segmentation: A Comparative Analysis / Bruschi, S.; Esposito, M.; Raggiunto, S.; Belli, A.; Pierleoni, P.. - In: ELECTRONICS. - ISSN 2079-9292. - ELETTRONICO. - 14:7(2025). [10.3390/electronics14071254]

Federated and Centralized Machine Learning for Cell Segmentation: A Comparative Analysis

Bruschi S.
;
Esposito M.
;
Raggiunto S.;Belli A.;Pierleoni P.
2025-01-01

Abstract

The automatic segmentation of cell images plays a critical role in medicine and biology, as it enables faster and more accurate analysis and diagnosis. Traditional machine learning faces challenges since it requires transferring sensitive data from laboratories to the cloud, with possible risks and limitations due to patients' privacy, data-sharing regulations, or laboratory privacy guidelines. Federated learning addresses data-sharing issues by introducing a decentralized approach that removes the need for laboratories' data sharing. The learning task is divided among the participating clients, with each training a global model situated on the cloud with its local dataset. This guarantees privacy by only transmitting updated model weights to the cloud. In this study, the centralized learning approach for cell segmentation is compared with the federated one, demonstrating that they achieve similar performances. Stemming from a benchmarking of available cell segmentation models, Cellpose, having shown better recall and precision (F1=0.84) than U-Net (F1=0.50) and StarDist (F1=0.12), was used as the baseline for a federated learning testbench implementation. The results show that both binary segmentation and multi-class segmentation metrics remain high when employing both the centralized solution (F1=0.86) and the federated solution (F12clients=0.86). These results were also stable across an increasing number of clients and a reduced number of local data samples (F14clients=0.87, F116clients=0.86), proving the effectiveness of central aggregation on the cloud of locally trained models.
2025
biological imaging; cell segmentation; data privacy; deep learning; federated learning; semantic segmentation
File in questo prodotto:
File Dimensione Formato  
Federated and Centralized Machine Learning.pdf

accesso aperto

Descrizione: articolo internazionale
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso: Creative commons
Dimensione 3.64 MB
Formato Adobe PDF
3.64 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/345299
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact