FIVA: Federated Inverse Variance Averaging for Universal CT Segmentation with Uncertainty Estimation
Ukaye, Asim Saeed, Numan Nandakumar, Karthik
Ukaye, Asim
Saeed, Numan
Nandakumar, Karthik
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Different CT segmentation datasets are typically obtained from different scanners under different capture settings and often provide segmentation labels for a limited and often disjoint set of organs. Using these heterogeneous data effectively while preserving patient privacy can be challenging. This work presents a novel federated learning approach to achieve universal segmentation across diverse abdominal CT datasets by utilizing model uncertainty for aggregation and predictive uncertainty for inference. Our approach leverages the in herent noise in stochastic mini-batch gradient descent to estimate a distribution over the model weights to provide an on-the-go uncertainty over the model parameters at the client level. The parameters are then aggregated at the server using the additional uncertainty information using a Bayesian-inspired inverse-variance aggregation scheme. Furthermore, the proposed method quantifies prediction uncertainty by propagating the uncertainty from the model weights, providing confidence measures essential for clinical decision-making. In line with recent work shown, predictive uncertainty is utilized in the inference stage to improve predictive performance. Experimental evaluations demonstrate the effectiveness of this approach in improving both the quality of federated aggregation and uncertainty weighted inference compared to previously established baselines. The code for this work is made available at: https://github.com/asimukaye/fiva
Citation
A. Ukaye, N. Saeed, and K. Nandakumar, “FIVA: Federated Inverse Variance Averaging for Universal CT Segmentation with Uncertainty Estimation,” Oct. 07, 2025, PMLR. Accessed: Nov. 05, 2025. [Online]. Available: https://proceedings.mlr.press/v298/ukaye25a.html
Source
Proceedings of Machine Learning Research
Conference
Machine Learning for Healthcare Conference, MLHC 2025
Keywords
Subjects
Source
Machine Learning for Healthcare Conference, MLHC 2025
Publisher
ML Research Press