FEDMix

Fusible evolutionary deep neural network mixture learning from distributed data for robust medical...

Automated Medical Image Analysis (MIA) has the potential to truly innovate clinical practice by offering solutions to routine, yet key tasks, such as segmentation (i.e., delineating organs). Especially with recent advances in machine learning (ML), in particular in Deep Neural Networks (DNNs) that have led to an explosive growth of successful MIA studies reported in academic literature, the time appears right for such innovations to find widespread real-world uptake.

Yet, labor-intensive manual performance of these tasks is still often daily clinical practice. In this proposal, we integrate DNNs with other state-of-the-art computational intelligence techniques, in particular evolutionary algorithms (EAs), to overcome 2 key obstacles in moving toward widespread clinical uptake of computationally intelligent MIA techniques: 1) observer variation in the definition of a ground truth, and 2) image quality variation due to different acquisition protocols and scanners at different institutes.

In particular, we design and develop efficient-computing-compatible implementations of mixtures of DNNs, the results of which can be fused with results learned from other  data sets (i.e., from different institutes).

To maintain sufficient focus while doing so, we consider an elementary, but key MIA task: segmentation. Moreover, by means of an application in radiotherapy treatment planning, in collaboration with the Academic Medical Center in Amsterdam, we validate the newly developed technology on real-world patient data within the runtime of the proposed project.

Participating organisations

CWI
Life Sciences
Life Sciences
Netherlands eScience Center

Impact

Output

Team

Contact person

Christiaan Meijer

Christiaan Meijer

eScience Research Engineer
Netherlands eScience Center
Mail Christiaan
AM
Adriënne Mendrik
eScience Coordinator
Netherlands eScience Center
Christiaan Meijer
Christiaan Meijer
eScience Research Engineer
Netherlands eScience Center
Jesus G. Gonzalez
eScience Research Engineer
Netherlands eScience Center
PB
Peter Bosman
Principal investigator
CWI

Related projects

Perfect Fit

Targeting key risk factors for cardiovascular disease in at-risk individuals using a personalized and adaptive approach

Updated 14 months ago
In progress

MyDigiTwin

Using big data to put a cardiovascular digital twin into the hands of people

Updated 8 months ago
In progress

Integrated omics analysis for small molecule-mediated host-microbiome interactions

Advancing our understanding of molecular mechanisms of health and disease

Updated 24 months ago
Finished

DeepRank

Scoring 3D protein-protein interaction models using deep learning

Updated 20 months ago
Finished

Data quality in a distributed learning environment

Vast amounts of data to improve cancer treatment decisions

Updated 24 months ago
Finished

Enhancing Protein-Drug Binding Prediction

Combining molecular simulation and eScience technologies

Updated 2 weeks ago
Finished

ANDI

Advanced neuropsychological diagnostics infrastructure

Updated 20 months ago
Finished

3D-e-Chem

Efficient exploitation of the massive amount of modern-day life science data

Updated 21 months ago
Finished

Chemical Informatics for Metabolite Identification and Biochemical Network Reconstruction

Chemical informatics for metabolite identification and biochemical network reconstruction

Updated 20 months ago
Finished