Improved Prediction of MGMT Methylation Status in Glioblastoma using a Deep Attention Network

Iranmehr, Azadeh; Gutta, Sreedevi; Hadaegh, Ahmad

doi:10.1109/iceccme55909.2022.9988694

Cited by 1 publication

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 In one-third GB cases, MGMT is epigenetically silenced by promoter hypermethylation, 4 improving survival and favorable response to TMZ. 5 Several prior studies [6][7][8] demonstrate that deep learning (DL) models can predict MGMT methylation status from pre-operative magnetic resonance imaging (MRI), but centralized data aggregation for DL model training raises privacy concerns. Federated learning (FL) offers a promising approach, where participating institutions train local models on their own data without forwarding it to a server or central node.…”

Section: Description Of Purposementioning

confidence: 99%

Domain adaptive federated learning for multi-institution molecular mutation prediction and bias identification

Farzana,

Witherow,

Longoria

et al. 2024

Medical Imaging 2024: Computer-Aided Diagnosis

View full text Add to dashboard Cite

Deep learning models have shown potential in medical image analysis tasks. However, training a generalized deep learning model requires huge amounts of patient data that is usually gathered from multiple institutions which may raise privacy concerns. Federated learning (FL) provides an alternative to sharing data across institutions. Nonetheless, FL is susceptible to a few challenges including inversion attacks on model weights, heterogenous data distributions, and bias. This study addresses heterogeneity and bias issues for multi-institution patient data by proposing domain adaptive FL modeling using several radiomics (volume, fractal, texture) features for O6-methylguanine-DNA methyltransferase (MGMT) classification across multiple institutions. The proposed domain adaptive FL MGMT classification inherently offers differential privacy (DP) for the patient data. For domain adaptation two techniques e.g., mixture of experts (ME) with a gating network and adversarial alignment are used for comparison. The proposed method is evaluated using publicly available multi-institution (UPENN-GBM, UCSF-PDGM, RSNA-ASNR-MICCAI BraTS-2021) data set with a total of 1007 patients. Our experiments with 5-fold cross validation suggest that domain adaptive FL offers improved performance with a mean accuracy of 69.93% ± 4.8 % and area under curve of 0.655 ± 0.055 across multiple institutions. In addition, further analysis of probability density of gating network for domain adaptive FL identifies the institution that may bias the global model prediction due to increased heterogeneity for a given input. Our comparison analysis shows that the proposed method with bias identification offers the best predictive performance when compared to different commonly employed FL and baseline methods in the literature.

show abstract