no code implementations • 19 Feb 2024 • Florian van Daalen, Lianne Ippel, Andre Dekker, Inigo Bermejo
In this article, we explore the use of federated ensembles of Bayesian networks (FBNE) in a range of experiments and compare their performance with locally trained models and models trained with VertiBayes, a federated learning algorithm to train Bayesian networks from decentralized data.
1 code implementation • 31 Oct 2022 • Florian van Daalen, Lianne Ippel, Andre Dekker, Inigo Bermejo
For structure learning we adapted the widely used K2 algorithm with a privacy-preserving scalar product protocol.
no code implementations • 17 Dec 2021 • Florian van Daalen, Inigo Bermejo, Lianne Ippel, Andre Dekker
Privacy-preserving machine learning enables the training of models on decentralized datasets without the need to reveal the data, both on horizontal and vertically partitioned data.
no code implementations • 16 Sep 2021 • Junhua Chen, Leonard Wee, Andre Dekker, Inigo Bermejo
The trained GANs were applied to three scenarios: 1) improving radiomics reproducibility in simulated low dose CT images and 2) same-day repeat low dose CTs (RIDER dataset) and 3) improving radiomics performance in survival prediction.
no code implementations • 6 Sep 2021 • Junhua Chen, Inigo Bermejo, Andre Dekker, Leonard Wee
Generative models can improve the performance of low dose CT-based radiomics in different tasks.
1 code implementation • 30 Apr 2021 • Junhua Chen, Chong Zhang, Alberto Traverso, Ivan Zhovannik, Andre Dekker, Leonard Wee, Inigo Bermejo
Moreover, images with different noise levels can be denoised to improve the reproducibility using these models without re-training, as long as the noise intensity is equal or lower than that in high-noise CTs.
no code implementations • 29 Apr 2021 • Junhua Chen, Haiyan Zeng, Chong Zhang, Zhenwei Shi, Andre Dekker, Leonard Wee, Inigo Bermejo
In this article, we treat lung cancer diagnosis as a multiple instance learning (MIL) problem in order to better reflect the diagnosis process in the clinical setting and for the higher interpretability of the output.