Domain Adaptation Using a Three-Way Decision Improves the Identification of Autism Patients from Multisite fMRI Data

Shi, Changwei; Xin, Xianwei; Zhang, Jiacai

doi:10.3390/brainsci11050603

Cited by 22 publications

(20 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nearly half of the models (48.3% [268 of 555]) were found in studies authored by those with academic training in computers and data science 27 , 32 , 33 , 34 , 35 , 36 , 37 , 39 , 40 , 41 , 42 , 44 , 45 , 46 , 47 , 48 , 50 , 52 , 58 , 70 , 71 , 72 , 73 , 75 , 76 , 79 , 82 , 85 , 87 , 89 , 90 , 92 , 93 , 95 , 96 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , 112 , 113 , 114 , 115 , 116 , 117 , 118 , 121 , 123 , 128 , 129 , 130 , ...…”

Section: Resultsmentioning

confidence: 99%

“…The study protocol was registered at PROSPERO (CRD42022340624) and followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guideline (Figure 1…”

Section: Methodsmentioning

confidence: 99%

“… a Of the 555 artificial intelligence (AI) models, 469 were tested at the internal sample and 86 at the independent external sample, including intellectual disability, autism spectrum disorder, attention-deficit/hyperactivity disorder,…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

et al. 2023

View full text Add to dashboard Cite

ImportanceNeuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.ObjectiveTo systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.Evidence ReviewPubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.FindingsA total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).Conclusions and RelevanceThis systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The study protocol was registered at PROSPERO (CRD42022340624) and followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guideline (Figure 1…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

et al. 2023

View full text Add to dashboard Cite

show abstract

“…As shown in Table V, in the case that the number of subjects we used is larger than that of other methods, the results of our LRCDR method are better than those of ComBat-ANN that adopts data harmonization to reduce the heterogeneity among multiple sites, and the methods using DA that include Three-Way Decision [17] and MCDA [15], suggesting the efficacy of the proposed LRCDR method in domain adaptation. The proposed LRCDR unsupervised multi-source DA method synchronously reduces the marginal and conditional distribution differences to make the data distributions of multiple sites be as similar as possible while ensuring the data to have good class separability, thus achieving the best results on more data compared to all other methods in Table V.…”

Section: Discussionmentioning

confidence: 90%

“…Therefore, the absence of class discriminative information can lead to the degradation of ASD identification performance. To align the conditional distributions between domains, Shi et al [17] proposed a single-source domain adaptation method via three-way decision. However, this method focused on the optimization of pseudo labels in the target domain that is a process separated from domain invariant feature learning, and cannot perform the joint optimization to obtain better results.…”

mentioning

confidence: 99%

Domain Adaptation via Low Rank and Class Discriminative Representation for Autism Spectrum Disorder Identification: A Multi-Site fMRI Study

Liu

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

To construct a more effective model with good generalization performance for inter-site autism spectrum disorder (ASD) diagnosis, domain adaptation based ASD diagnostic models are proposed to alleviate the inter-site heterogeneity. However, most existing methods only reduce the marginal distribution difference without considering class discriminative information, and are difficult to achieve satisfactory results. In this paper, we propose a low rank and class discriminative representation (LRCDR) based multi-source unsupervised domain adaptation method to reduce the marginal and conditional distribution differences synchronously for improving ASD identification. Specifically, LRCDR adopts low rank representation to alleviate the marginal distribution difference between domains by aligning the global structure of the projected multi-site data. To reduce the conditional distribution difference of data from all sites, LRCDR learns the class discriminative representation of data from multiple source domains and the target domain to enhance the intra-class compactness and inter-class separability of the projected data. For inter-site prediction on all ABIDE I data (1102 subjects from 17 sites), LRCDR obtains the mean accuracy of 73.1%, superior to the results of the compared state-of-the-art domain adaptation methods and multi-site ASD identification methods. In addition, we locate some meaningful biomarkers: Most of the top important biomarkers are inter-network resting-state functional connectivities (RSFCs). The proposed LRCDR method can effectively improve the identification of ASD, and has great potential as a clinical diagnostic tool.

show abstract

Addressing multi‐site functional MRI heterogeneity through dual‐expert collaborative learning for brain disease identification

Fang

Potter

et al. 2023

Human Brain Mapping

View full text Add to dashboard Cite

Several studies employ multi‐site rs‐fMRI data for major depressive disorder (MDD) identification, with a specific site as the to‐be‐analyzed target domain and other site(s) as the source domain. But they usually suffer from significant inter‐site heterogeneity caused by the use of different scanners and/or scanning protocols and fail to build generalizable models that can well adapt to multiple target domains. In this article, we propose a dual‐expert fMRI harmonization (DFH) framework for automated MDD diagnosis. Our DFH is designed to simultaneously exploit data from a single labeled source domain/site and two unlabeled target domains for mitigating data distribution differences across domains. Specifically, the DFH consists of a domain‐generic student model and two domain‐specific teacher/expert models that are jointly trained to perform knowledge distillation through a deep collaborative learning module. A student model with strong generalizability is finally derived, which can be well adapted to unseen target domains and analysis of other brain diseases. To the best of our knowledge, this is among the first attempts to investigate multi‐target fMRI harmonization for MDD diagnosis. Comprehensive experiments on 836 subjects with rs‐fMRI data from 3 different sites show the superiority of our method. The discriminative brain functional connectivities identified by our method could be regarded as potential biomarkers for fMRI‐related MDD diagnosis.

show abstract

Domain Adaptation Using a Three-Way Decision Improves the Identification of Autism Patients from Multisite fMRI Data

Cited by 22 publications

References 76 publications

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

Domain Adaptation via Low Rank and Class Discriminative Representation for Autism Spectrum Disorder Identification: A Multi-Site fMRI Study

Addressing multi‐site functional MRI heterogeneity through dual‐expert collaborative learning for brain disease identification

Contact Info

Product

Resources

About