Gradient Matching Federated Domain Adaptation for Brain Image Classification

Zeng, Ling‐Li; Fan, Zhipeng; Su, Jianpo; Gan, Min; Peng, Limin; Shen, Hui; Hu, Dewen

doi:10.1109/tnnls.2022.3223144

Cited by 17 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taking the precuneus as an example, the preprocessed time series of 3010 vertices within the DK mask (left: 1476 vertices; right: 1534 vertices) was first extracted. To obtain the global spectrum connection features, the brain functional atlas BA512 was selected to provide target ROIs since its superiority in characterizing the patterns of brain functional connectome (Su et al, 2021 ; Zeng et al, 2022 ). The time series from 512 target ROIs covering the whole brain were extracted.…”

Section: Methodsmentioning

confidence: 99%

“…Therefore, FC is usually regarded as a biomarker to effectively distinguish mental disorders or predict individual phenotypes in the multivariate pattern analysis of fMRI, since differences in physiology or pathology are often accompanied by differences in FC. For example, our previous studies utilized whole‐brain FC as a classification feature and achieved objective diagnosis of multiple mental disorders using supervised machine learning algorithms (Shen et al, 2010 ; Zeng et al, 2012 , 2022 ). Moreover, with the development of deep learning methods, temporal, and spatial information of FC could be simultaneously utilized, and high accuracy was obtained in sex classification and intelligence prediction tasks (Fan et al, 2020 ; Sen & Parhi, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Measuring functional connectivity in frequency‐domain helps to better characterize brain function

Peng,

Su,

et al. 2024

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

Resting‐state functional connectivity (FC) is widely used in multivariate pattern analysis of functional magnetic resonance imaging (fMRI), including identifying the locations of putative brain functional borders, predicting individual phenotypes, and diagnosing clinical mental diseases. However, limited attention has been paid to the analysis of functional interactions from a frequency perspective. In this study, by contrasting coherence‐based and correlation‐based FC with two machine learning tasks, we observed that measuring FC in the frequency domain helped to identify finer functional subregions and achieve better pattern discrimination capability relative to the temporal correlation. This study has proven the feasibility of coherence in the analysis of fMRI, and the results indicate that modeling functional interactions in the frequency domain may provide richer information than that in the time domain, which may provide a new perspective on the analysis of functional neuroimaging.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Measuring functional connectivity in frequency‐domain helps to better characterize brain function

Peng,

Su,

et al. 2024

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although our study regresses out the effect of sites from the structural MRI data and then performs subtyping analysis, other methods such as z-standardisation [78] and federated learning [79] may also be explored. Z-standardization [78] may be used to normalize the correlation coefficients in the association matrices of each subtypes before analysing network metrics.…”

Section: Limitations and Future Scopementioning

confidence: 99%

“…Z-standardization [78] may be used to normalize the correlation coefficients in the association matrices of each subtypes before analysing network metrics. Also, the federated learning approach [79] may be a potential way to preserve the privacy of the raw medical image data from multiple sites.…”

Section: Limitations and Future Scopementioning

confidence: 99%

Brain connectivity for subtypes of parkinson’s disease using structural MRI

Samantaray,

Saini,

Pal

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Objective: Delineating Parkinson’s disease (PD) into distinct subtypes is a major challenge. Most studies use clinical symptoms to label PD subtypes while our work uses an imaging-based data-mining approach to subtype PD. Our study comprises of two major objectives - firstly, subtyping Parkinson’s patients based on grey matter information from structural magnetic resonance imaging scans of human brains; secondly, comparative structural brain connectivity analysis of PD subtypes derived from the former step. Approach: Source-based-morphometry decomposition was performed on 131 Parkinson’s patients and 78 healthy controls from PPMI dataset, to derive at components (regions) with significance in disease and high effect size. The loading coefficients of significant components were thresholded for arriving at subtypes. Further, regional grey matter maps of subtype-specific subjects were separately parcellated and employed for construction of subtype-specific association matrices using Pearson correlation. These association matrices were binarized using sparsity threshold and leveraged for structural brain connectivity analysis using network metrics. Main results: Two distinct Parkinson’s subtypes (namely A and B) were detected employing loadings of two component satisfying the selection criteria, and a third subtype (AB) was detected, common to these two components. Subtype A subjects were highly weighted in inferior, middle and superior frontal gyri while subtype B subjects in inferior, middle and superior temporal gyri. Network metrics analyses through permutation test revealed significant inter-subtype differences (p<0.05) in clustering coefficient, local efficiency, participation coefficient and betweenness centrality. Moreover, hubs were obtained using betweenness centrality and mean network degree. Significance: MRI-based data-driven subtypes show frontal and temporal lobe playing key role in PD. Graph theory-driven brain network analyses could untangle subtype-specific differences in structural brain connections showing differential network architecture. Replication of these initial results in other Parkinson’s datasets may be explored in future. Clinical Relevance- Investigating structural brain connections in Parkinson's disease may provide subtype-specific treatment.

show abstract

“…Another disease state susceptible to domain shift issues is using fMRIs to diagnose Schizophrenia and major depressive disorders. Zeng et al set out to create a method known as GM-FedDA, where a two-stage method can be implemented to increase performance [62]. The group showed that better performance can be achieved by using one common source adversarial domain adaptation strategy and fine-tuning the model using a gradient matching method.…”

Section: Schizophrenia and Depressive Disordersmentioning

confidence: 99%

Medical Imaging Applications of Federated Learning

Sandhu,

Gorji,

Tavakolian

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Since its introduction in 2016, researchers have applied the idea of Federated Learning (FL) to several domains ranging from edge computing to banking. The technique’s inherent security benefits, privacy-preserving capabilities, ease of scalability, and ability to transcend data biases have motivated researchers to use this tool on healthcare datasets. While several reviews exist detailing FL and its applications, this review focuses solely on the different applications of FL to medical imaging datasets, grouping applications by diseases, modality, and/or part of the body. This Systematic Literature review was conducted by querying and consolidating results from ArXiv, IEEE Xplorer, and PubMed. Furthermore, we provide a detailed description of FL architecture, models, descriptions of the performance achieved by FL models, and how results compare with traditional Machine Learning (ML) models. Additionally, we discuss the security benefits, highlighting two primary forms of privacy-preserving techniques, including homomorphic encryption and differential privacy. Finally, we provide some background information and context regarding where the contributions lie. The background information is organized into the following categories: architecture/setup type, data-related topics, security, and learning types. While progress has been made within the field of FL and medical imaging, much room for improvement and understanding remains, with an emphasis on security and data issues remaining the primary concerns for researchers. Therefore, improvements are constantly pushing the field forward. Finally, we highlighted the challenges in deploying FL in medical imaging applications and provided recommendations for future directions.

show abstract

Gradient Matching Federated Domain Adaptation for Brain Image Classification

Cited by 17 publications

References 51 publications

Measuring functional connectivity in frequency‐domain helps to better characterize brain function

Measuring functional connectivity in frequency‐domain helps to better characterize brain function

Brain connectivity for subtypes of parkinson’s disease using structural MRI

Medical Imaging Applications of Federated Learning

Contact Info

Product

Resources

About