AUTHOR=Ali Muhaddisa Barat , Gu Irene Yu-Hua , Berger Mitchel S. , Jakola Asgeir Store 

TITLE=A novel federated deep learning scheme for glioma and its subtype classification

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1181703

DOI=10.3389/fnins.2023.1181703

ISSN=1662-453X

ABSTRACT=Background: Deep learning (DL) requires a large number of training data for achieving
good generalization performance. Since brain tumor datasets are usually small in size,
combination of such datasets from different hospitals are needed. Data privacy issue from
hospitals often poses a constraint on such a practice. 
Method: We propose a novel 3D FL scheme for glioma and its molecular subtype classification. A slice-based DL classifier, EtFedDyn, is exploited which is an extension of FedDyn
(1), with the key differences on using focal loss function to tackle severe class imbalances in
the datasets, and on multi-stream network to exploit MRIs in different modalities. By combining
EtFedDyn with domain mapping as the pre-processing and 3D scan-based post-processing, it examines whether the FL scheme could replace the central learning (CL) one, we
then compare the classification performance between the proposed FL and the corresponding
CL schemes. 
Results: : Experiments were done on 2 case studies: classification of glioma subtypes (IDH
mutation and wild-type on TCGA and US datasets in case A) and glioma grades (high/low grade
glioma HGG and LGG on MICCAI dataset in case B). The proposed FL scheme has obtained good performance on the test sets (85.46%, 75.56% for IDH subtypes and 89.28%, 90.72% for
glioma LGG/HGG all averaged on 5 runs). Comparing with the corresponding CL scheme, the
drop in test accuracy from the proposed FL scheme is small (-1.17%, -0.83%), indicating its
good potential to replace the CL scheme. Furthermore, the empirically tests have shown that
an increased classification test accuracy by applying: domain mapping (0.4%, 1.85% in case A),
focal loss function (1.66%, 3.25% in case A, 1.19%, 1.85% in case B), 3D post-processing (2.11%,
2.23% in case A and 1.81%, 2.39% in case B) and EtFedDyn over FedAvg classifier (1.05%,
1.55% in case A and 1.23%, 1.81% in case B) with fast convergence, which all contributed to the
improvement of overall performance in the proposed FL scheme.
Conclusion: The proposed FL scheme is shown to be effective in predicting glioma  and its subtype, with great potential of replacing the conventional CL approaches for training deep networks.