1
|
Yin Z, Ding X, Zhang X, Wu Z, Wang L, Xu X, Li G. Early autism diagnosis based on path signature and Siamese unsupervised feature compressor. Cereb Cortex 2024; 34:72-83. [PMID: 38696605 DOI: 10.1093/cercor/bhae069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 01/07/2024] [Accepted: 02/07/2024] [Indexed: 05/04/2024] Open
Abstract
Autism spectrum disorder has been emerging as a growing public health threat. Early diagnosis of autism spectrum disorder is crucial for timely, effective intervention and treatment. However, conventional diagnosis methods based on communications and behavioral patterns are unreliable for children younger than 2 years of age. Given evidences of neurodevelopmental abnormalities in autism spectrum disorder infants, we resort to a novel deep learning-based method to extract key features from the inherently scarce, class-imbalanced, and heterogeneous structural MR images for early autism diagnosis. Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features. We also proposed weight constraints to cope with sample heterogeneity by giving different samples different voting weights during validation, and used Path Signature to unravel meaningful developmental features from the two-time point data longitudinally. We further extracted machine learning focused brain regions for autism diagnosis. Extensive experiments have shown that our method performed well under practical scenarios, transcending existing machine learning methods and providing anatomical insights for autism early diagnosis.
Collapse
Affiliation(s)
- Zhuowen Yin
- School of Electronics and Information Engineering, South China University of Technology, 510641 Guangzhou, Guangdong Province, China
- Department of Bioengineering, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA 19104, United States
| | - Xinyao Ding
- School of Electronics and Information Engineering, South China University of Technology, 510641 Guangzhou, Guangdong Province, China
- The Affiliated Shenzhen School of Guangdong Experimental High School, 518100 Shenzhen, Guangdong Province, China
| | - Xin Zhang
- School of Electronics and Information Engineering, South China University of Technology, 510641 Guangzhou, Guangdong Province, China
- Pazhou Lab, 510330 Guangzhou, Guangdong Province, China
| | - Zhengwang Wu
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Li Wang
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Xiangmin Xu
- Pazhou Lab, 510330 Guangzhou, Guangdong Province, China
- School of Future Technology, South China University of Technology, 510641 Guangzhou, Guangdong Province, China
| | - Gang Li
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| |
Collapse
|
2
|
Li X, Jiang M, Zhao L, Yang K, Lu T, Zhang D, Li J, Wang L. Relationship between autism and brain cortex surface area: genetic correlation and a two-sample Mendelian randomization study. BMC Psychiatry 2024; 24:69. [PMID: 38263034 PMCID: PMC10807092 DOI: 10.1186/s12888-024-05514-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Accepted: 01/10/2024] [Indexed: 01/25/2024] Open
Abstract
BACKGROUND Alterations in surface area (SA) in specific regions of the cortex have been reported in many individuals with autism spectrum disorder (ASD), however, the genetic background between ASD and SA is still unclear. This study estimated the genetic correlation and causal effect of ASD and cortical SA. METHODS Summarized data of genome-wide association studies (GWAS) were separately downloaded from the Psychiatric Genomics Consortium (18,381 cases of ASD, and 27,969 controls) and the Enhancing Neuroimaging Genetics through Meta-Analysis Consortium (33,992 participants of Europeans). We used Linkage disequilibrium score regression (LDSC) and Heritability Estimation from Summary Statistics (HESS) to calculate the heritability of each trait. As for the genetic correlation between ASD and SA, LDSC was used for global correlation and HESS was used to examine the local genetic covariance further. We used three Mendelian randomization (MR) methods, Inverse-variance weighted, MR-Egger, and weighted median to estimate the causal relationship. RESULTS LDSC observed a nominal significant genetic correlation (rg = 0.1229, P-value = 0.0346) between ASD and SA of the rostral anterior cingulate gyrus whereas analysis through HESS did not reveal any significant loci having genetic covariance. Based on MR results, statistically meaningful estimations were found in the following areas, postcentral cortex (β (SE) = 21.82 (7.84) mm, 95% CI: 6.46 to 37.19 mm, PIVW = 5.38 × 10- 3, PFDR = 3.09 × 10- 2), posterior cingulate gyrus (β (SE) = 6.23 (2.69) mm, 95% CI: 0.96 to 11.49 mm, PIVW = 2.05 × 10- 2, PFDR = 4.26 × 10- 2), supramarginal gyrus (β (SE) = 19.25 (8.43) mm, 95% CI: 29.29 to 35.77 mm, PIVW = 2.24 × 10- 2, PFDR = 4.31 × 10- 2). CONCLUSION Our results provided genetic evidence to support the opinion that individuals with ASD tend to develop differences in cortical SA of special areas. The findings contributed to understanding the genetic relationship between ASD and cortical SA.
Collapse
Grants
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 2019B030335001 Key-Area Research and Development Program of Guangdong Province
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
- 81971283, 82171537, 82071541, 81671363, and 81730037 National Natural Science Foundation of China
Collapse
Affiliation(s)
- Xianjing Li
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China
| | - Miaomiao Jiang
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China
| | - Liyang Zhao
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China
| | - Kang Yang
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China
| | - Tianlan Lu
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China
| | - Dai Zhang
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China
- Guangdong Key Laboratory of Mental Health and Cognitive Science, Institute for Brain Research and Rehabilitation (IBRR), South China Normal University, Guangzhou, China
| | - Jun Li
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China.
| | - Lifang Wang
- NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital, Peking University Sixth Hospital, Peking University Institute of Mental Health, Beijing, China.
| |
Collapse
|
3
|
Xu H, Li J, Huang H, Yin B, Li DD. Abnormal developmental of structural covariance networks in young adults with heavy cannabis use: a 3-year follow-up study. Transl Psychiatry 2024; 14:45. [PMID: 38245512 PMCID: PMC10799944 DOI: 10.1038/s41398-024-02764-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Revised: 01/05/2024] [Accepted: 01/10/2024] [Indexed: 01/22/2024] Open
Abstract
Heavy cannabis use (HCU) exerts adverse effects on the brain. Structural covariance networks (SCNs) that illustrate coordinated regional maturation patterns are extensively employed to examine abnormalities in brain structure. Nevertheless, the unexplored aspect remains the developmental alterations of SCNs in young adults with HCU for three years, from the baseline (BL) to the 3-year follow-up (FU). These changes demonstrate dynamic development and hold potential as biomarkers. A total of 20 young adults with HCU and 22 matched controls were recruited. All participants underwent magnetic resonance imaging (MRI) scans at both the BL and FU and were evaluated using clinical measures. Both groups used cortical thickness (CT) and cortical surface area (CSA) to construct structural covariance matrices. Subsequently, global and nodal network measures of SCNs were computed based on these matrices. Regarding global network measures, the BL assessment revealed significant deviations in small-worldness and local efficiency of CT and CSA in young adults with HCU compared to controls. However, no significant differences between the two groups were observed at the FU evaluation. Young adults with HCU displayed changes in nodal network measures across various brain regions during the transition from BL to FU. These alterations included abnormal nodal degree, nodal efficiency, and nodal betweenness in widespread areas such as the entorhinal cortex, superior frontal gyrus, and parahippocampal cortex. These findings suggest that the topography of CT and CSA plays a role in the typical structural covariance topology of the brain. Furthermore, these results indicate the effect of HCU on the developmental changes of SCNs in young adults.
Collapse
Affiliation(s)
- Hui Xu
- School of Mental Health, Wenzhou Medical University, Wenzhou, 325035, China.
- The Affiliated Kangning Hospital of Wenzhou Medical University, Zhejiang Provincial Clinical Research Center for Mental Disorder, Wenzhou, 325007, China.
| | - Jiahao Li
- Department of Neurosurgery, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China
- Department of Neurology, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, 710061, China
| | - Huan Huang
- Department of Radiology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China
| | - Bo Yin
- Department of Neurosurgery, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China
| | - Dan-Dong Li
- Department of Neurosurgery, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China.
| |
Collapse
|
4
|
Coskunpinar EM, Tur S, Cevher Binici N, Yazan Songür C. Association of GABRG3, GABRB3, HTR2A Gene Variants with Autism Spectrum Disorder. Gene 2023; 870:147399. [PMID: 37019319 DOI: 10.1016/j.gene.2023.147399] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2022] [Revised: 03/18/2023] [Accepted: 03/22/2023] [Indexed: 04/05/2023]
Abstract
Autism spectrum disorder (ASD) is a neurodevelopmental and neurobehavioral disorder characterized by impaired social communication, repetitive and restricted patterns of behavior, activity, or interest, and altered emotional processing. Reported prevalence is 4 times higher in men and it has increased in recent years. Immunological, environmental, epigenetic, and genetic factors play a role in the pathophysiology of autism. Many neurochemical pathways and neuroanatomical events are effective in determining the disease. It is still unclear how the main symptoms of autism occur because of this complex and heterogeneous situation. In this study, we focused on gamma amino butyric acid (GABA) and serotonin, which are thought to contribute to the etiology of autism; it is aimed to elucidate the mechanism of the disease by investigating variant changes in the GABA receptor subunit genes GABRB3, GABRG3 and the HTR2A gene, which encodes one of the serotonin receptors. 200 patients with ASD between the ages of 3-9 and 100 healthy volunteers were included in the study. Genomic DNA isolation was performed from peripheral blood samples taken from volunteers. Genotyping was performed using the RFLP method with PCR specific for specific variants. Data were analyzed with SPSS v25.0 program. According to the data obtained in our study; In terms of HTR2A (rs6313 T102C) genotypes, the homozygous C genotype carrying frequency in the patient group and the homozygous T genotype carrying frequency in the GABRG3 (rs140679 C/T) genotypes were found to be significantly higher in the patient group compared to the control group (*p: 0.0001, p: 0.0001). It was determined that the frequency of individuals with homozygous genotype was significantly higher in the patient group compared to the control group and having homozygous genotypes increased the disease risk approximately 1.8 times. In terms of GABRB3 (rs2081648 T/C) genotypes, it was determined that there was no statistically significant difference in the frequency of carrying homozygous C genotype in the patient group compared to the control group (p: 0.36). According to the results of our study, we think that the HTR2A (rs6313 T102C) polymorphism is effective in modulating the empathic and autistic characteristics of individuals, and that the HTR2A (rs6313 T102C) polymorphism is more distributed in the post-synaptic membranes in individuals with a higher number of C alleles. We believe that this situation can be attributed to the spontaneous stimulatory distribution of the HTR2A gene in the postsynaptic membranes because of T102C transformation. In genetically based autism cases, carrying the point mutation in the rs6313 variant of the HTR2A gene and the C allele and the point mutation in the rs140679 variant of the GABRG3 gene and accordingly carrying the T allele provide a predisposition to the disease.
Collapse
Affiliation(s)
- Ender M Coskunpinar
- Department of Medical Biology, School of Medicine, University of Health Sciences, Turkey.
| | - Seymanur Tur
- Department of Medical Biology, School of Medicine, University of Health Sciences, Turkey.
| | - Nagihan Cevher Binici
- Department of Child and Adolescent Psychiatry, University of Health Sciences Dr. Behcet Uz Child Disease and Pediatric Surgery Training and Research Hospital, Izmir, Turkey.
| | - Cisel Yazan Songür
- Department of Child and Adolescent Psychiatry, University of Health Sciences Dr. Behcet Uz Child Disease and Pediatric Surgery Training and Research Hospital, Izmir, Turkey.
| |
Collapse
|
5
|
Wang L, Wu Z, Chen L, Sun Y, Lin W, Li G. iBEAT V2.0: a multisite-applicable, deep learning-based pipeline for infant cerebral cortical surface reconstruction. Nat Protoc 2023; 18:1488-1509. [PMID: 36869216 DOI: 10.1038/s41596-023-00806-x] [Citation(s) in RCA: 24] [Impact Index Per Article: 24.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2021] [Accepted: 11/03/2022] [Indexed: 03/05/2023]
Abstract
The human cerebral cortex undergoes dramatic and critical development during early postnatal stages. Benefiting from advances in neuroimaging, many infant brain magnetic resonance imaging (MRI) datasets have been collected from multiple imaging sites with different scanners and imaging protocols for the investigation of normal and abnormal early brain development. However, it is extremely challenging to precisely process and quantify infant brain development with these multisite imaging data because infant brain MRI scans exhibit (a) extremely low and dynamic tissue contrast caused by ongoing myelination and maturation and (b) inter-site data heterogeneity resulting from the use of diverse imaging protocols/scanners. Consequently, existing computational tools and pipelines typically perform poorly on infant MRI data. To address these challenges, we propose a robust, multisite-applicable, infant-tailored computational pipeline that leverages powerful deep learning techniques. The main functionality of the proposed pipeline includes preprocessing, brain skull stripping, tissue segmentation, topology correction, cortical surface reconstruction and measurement. Our pipeline can handle both T1w and T2w structural infant brain MR images well in a wide age range (from birth to 6 years of age) and is effective for different imaging protocols/scanners, despite being trained only on the data from the Baby Connectome Project. Extensive comparisons with existing methods on multisite, multimodal and multi-age datasets demonstrate superior effectiveness, accuracy and robustness of our pipeline. We have maintained a website, iBEAT Cloud, for users to process their images with our pipeline ( http://www.ibeat.cloud ), which has successfully processed over 16,000 infant MRI scans from more than 100 institutions with various imaging protocols/scanners.
Collapse
Affiliation(s)
- Li Wang
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
| | - Zhengwang Wu
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
| | - Liangjun Chen
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Yue Sun
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Weili Lin
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Gang Li
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
| |
Collapse
|