1
|
Liu S, Liang B, Wang S, Li B, Pan L, Wang SH. NF-GAT: A Node Feature-Based Graph Attention Network for ASD Classification. IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY 2023; 5:428-433. [PMID: 38899023 PMCID: PMC11186657 DOI: 10.1109/ojemb.2023.3267612] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2023] [Revised: 03/21/2023] [Accepted: 04/12/2023] [Indexed: 06/21/2024] Open
Abstract
Goal: The purpose of this paper is to recognize autism spectrum disorders (ASD) using graph attention network. Methods: we propose a node features graph attention network (NF-GAT) for learning functional connectivity (FC) features to achieve ASD diagnosis. Firstly, node features are modelled based on functional magnetic resonance imaging (fMRI) data, with each subject modelled as a graph. Next, we use the graph attention layer to learn the node features and gets the node information of different nodes for ASD classification. Results: Compared with other models, the NF-GAT has significant advantages in terms of classification results. Conclusions: NF-GAT can be effectively used for ASD classification.
Collapse
Affiliation(s)
- Shuaiqi Liu
- College of Electronic and Information Engineering, Machine Vision Engineering Research Center of Hebei ProvinceHebei UniversityBaoding071002China
- National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijing100190China
| | - Beibei Liang
- Key Laboratory of Digital Medical Engineering of Hebei Province, College of Electronic and Information EngineeringHebei UniversityBaoding071002China
| | - Siqi Wang
- Key Laboratory of Digital Medical Engineering of Hebei Province, College of Electronic and Information EngineeringHebei UniversityBaoding071002China
| | - Bing Li
- National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijing100190China
| | - Lidong Pan
- Key Laboratory of Digital Medical Engineering of Hebei Province, College of Electronic and Information EngineeringHebei UniversityBaoding071002China
| | - Shui-Hua Wang
- School of Computer Science and TechnologyHenan Polytechnic UniversityJiaozuo454000China
| |
Collapse
|
2
|
Koller S, Müller N, Kauschke C. The Elephant in the Room: A Systematic Review of Stimulus Control in Neuro-Measurement Studies on Figurative Language Processing. Front Hum Neurosci 2022; 15:791374. [PMID: 35126074 PMCID: PMC8814624 DOI: 10.3389/fnhum.2021.791374] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2021] [Accepted: 12/23/2021] [Indexed: 11/22/2022] Open
Abstract
The processing of metaphors and idioms has been the subject of neuroscientific research for several decades. However, results are often contradictory, which can be traced back to inconsistent terminology and stimulus control. In this systematic review of research methods, we analyse linguistic aspects of 116 research papers which used EEG, fMRI, PET, MEG, or NIRS to investigate the neural processing of the two figurative subtypes metaphor and idiom. We critically examine the theoretical foundations as well as stimulus control by performing a systematic literature synthesis according to the PRISMA guidelines. We explicitly do not analyse the findings of the studies but instead focus on four primary aspects: definitions of figurative language and its subtypes, linguistic theory behind the studies, control for factors influencing figurative language processing, and the relationship between theoretical and operational definitions. We found both a lack and a broad variety in existing definitions and operationalisation, especially in regard to familiarity and conventionality. We identify severe obstacles in the comparability and validation potential of the results of the papers in our review corpus. We propose the development of a consensus in fundamental terminology and more transparency in the reporting of stimulus design in the research on figurative language processing.
Collapse
Affiliation(s)
| | - Nadine Müller
- Department of German Studies and Arts, Institute of German Linguistics, Philipps University of Marburg, Marburg, Germany
| | | |
Collapse
|
3
|
Koo SJ, Kim YJ, Han JH, Seo E, Park HY, Bang M, Park JY, Lee E, An SK. "Reading the Mind in the Eyes Test": Translated and Korean Versions. Psychiatry Investig 2021; 18:295-303. [PMID: 33849244 PMCID: PMC8103020 DOI: 10.30773/pi.2020.0289] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/28/2020] [Accepted: 12/28/2020] [Indexed: 12/19/2022] Open
Abstract
OBJECTIVE The Reading the Mind in the Eyes Test (RMET) was developed by using Caucasian eyes, which may not be appropriate to be used in Korean. The aims of the present study were 1) to develop a Korean version of the RMET (K-RMET) by using Korean eye stimuli and 2) to examine the psychometric properties of the Korean-translated version of the RMET and the K-RMET. METHODS Thirty-six photographs of Korean eyes were selected. A total of 196 (101 females) healthy subjects were asked to take the Korean-translated version of the RMET and K-RMET. To assess internal consistency reliability, Cronbach's alpha coefficients were computed, and test-retest reliability was assessed by the intraclass correlation coefficient (ICC) and Bland-Altman plots. Confirmatory factor analysis (CFA) and item analysis were also conducted. RESULTS Internal consistency, measured by Cronbach's alpha, was 0.542 for the Korean-translated version of the RMET, and 0.540 for the K-RMET. Test-retest reliability (n=25), measured by the ICC, was 0.787 for the Korean-translated version of the RMET, and 0.758 for the K-RMET. In CFA, the assumed single and 3-factor model fit indices were not good in the both types of RMETs. There was difficulty in discrimination in nine items of the Korean-translated version of the RMET and 10 items of the K-RMET. CONCLUSION The psychometric properties of both the Korean-translated version of the RMET and the K-RMET are acceptable. Both tests are applicable to the clinical population, as well as the general population in Korea.
Collapse
Affiliation(s)
- Se Jun Koo
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.,Graduate Program in Cognitive Science, Yonsei University, Seoul, Republic of Korea
| | - Ye Jin Kim
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Jung Hwa Han
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.,Department of Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Eunchong Seo
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.,Department of Psychiatry, Yonsei University College of Medicine, Severance Hospital, Seoul, Republic of Korea
| | - Hye Yoon Park
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.,Department of Psychiatry, Yonsei University College of Medicine, Severance Hospital, Seoul, Republic of Korea
| | - Minji Bang
- Department of Psychiatry, CHA Bundang Medical Center, CHA University, Seongnam, Republic of Korea
| | - Jin Young Park
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.,Department of Psychiatry, Yonsei University College of Medicine, Yongin Severance Hospital, Yongin, Republic of Korea
| | - Eun Lee
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.,Department of Psychiatry, Yonsei University College of Medicine, Severance Hospital, Seoul, Republic of Korea
| | - Suk Kyoon An
- Section of Self, Affect and Neuroscience, Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.,Graduate Program in Cognitive Science, Yonsei University, Seoul, Republic of Korea.,Department of Psychiatry, Yonsei University College of Medicine, Severance Hospital, Seoul, Republic of Korea
| |
Collapse
|
4
|
Hodge SM, Haselgrove C, Honor L, Kennedy DN, Frazier JA. An assessment of the autism neuroimaging literature for the prospects of re-executability. F1000Res 2020; 9:1031. [PMID: 33796274 PMCID: PMC7968525 DOI: 10.12688/f1000research.25306.2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 02/22/2021] [Indexed: 11/20/2022] Open
Abstract
Background: The degree of reproducibility of the neuroimaging literature in psychiatric application areas has been called into question and the issues that relate to this reproducibility are extremely complex. Some of these complexities have to do with the underlying biology of the disorders that we study and others arise due to the technology we apply to the analysis of the data we collect. Ultimately, the observations we make get communicated to the rest of the community through publications in the scientific literature. Methods: We sought to perform a 're-executability survey' to evaluate the recent neuroimaging literature with an eye toward seeing if the technical aspects of our publication practices are helping or hindering the overall quest for a more reproducible understanding of brain development and aging. The topic areas examined include availability of the data, the precision of the imaging method description and the reporting of the statistical analytic approach, and the availability of the complete results. We applied the survey to 50 publications in the autism neuroimaging literature that were published between September 16, 2017 to October 1, 2018. Results: The results of the survey indicate that for the literature examined, data that is not already part of a public repository is rarely available, software tools are usually named but versions and operating system are not, it is expected that reasonably skilled analysts could approximately perform the analyses described, and the complete results of the studies are rarely available. Conclusions: We have identified that there is ample room for improvement in research publication practices. We hope exposing these issues in the retrospective literature can provide guidance and motivation for improving this aspect of our reporting practices in the future.
Collapse
Affiliation(s)
- Steven M. Hodge
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - Christian Haselgrove
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - Leah Honor
- Lamar Soutter Library, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - David N. Kennedy
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - Jean A. Frazier
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| |
Collapse
|
5
|
Hodge SM, Haselgrove C, Honor L, Kennedy DN, Frazier JA. An assessment of the autism neuroimaging literature for the prospects of re-executability. F1000Res 2020; 9:1031. [PMID: 33796274 PMCID: PMC7968525 DOI: 10.12688/f1000research.25306.1] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 08/04/2020] [Indexed: 05/04/2024] Open
Abstract
Background: The degree of reproducibility of the neuroimaging literature in psychiatric application areas has been called into question and the issues that relate to this reproducibility are extremely complex. Some of these complexities have to do with the underlying biology of the disorders that we study and others arise due to the technology we apply to the analysis of the data we collect. Ultimately, the observations we make get communicated to the rest of the community through publications in the scientific literature. Methods: We sought to perform a 're-executability survey' to evaluate the recent neuroimaging literature with an eye toward seeing if our publication practices are helping or hindering the overall quest for a more reproducible understanding of brain development and aging. The topic areas examined include availability of the data, the precision of the imaging method description and the reporting of the statistical analytic approach, and the availability of the complete results. We applied the survey to 50 publications in the autism neuroimaging literature that were published between September 16, 2017 to October 1, 2018. Results: The results of the survey indicate that for the literature examined, data that is not already part of a public repository is rarely available, software tools are usually named but versions and operating system are not, it is expected that reasonably skilled analysts could approximately perform the analyses described, and the complete results of the studies are rarely available. Conclusions: We have identified that there is ample room for improvement in research publication practices. We hope exposing these issues in the retrospective literature can provide guidance and motivation for improving this aspect of our reporting practices in the future.
Collapse
Affiliation(s)
- Steven M. Hodge
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - Christian Haselgrove
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - Leah Honor
- Lamar Soutter Library, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - David N. Kennedy
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| | - Jean A. Frazier
- Eunice Kennedy Shriver Center, Department of Psychiatry, University of Massachusetts Medical School, Worcester, Massachusetts, 01655, USA
| |
Collapse
|