1
|
Liu M, Zhang H, Liu M, Chen D, Zhuang Z, Wang X, Zhang L, Peng D, Wang Q. Randomizing Human Brain Function Representation for Brain Disease Diagnosis. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:2537-2546. [PMID: 38376975 DOI: 10.1109/tmi.2024.3368064] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/22/2024]
Abstract
Resting-state fMRI (rs-fMRI) is an effective tool for quantifying functional connectivity (FC), which plays a crucial role in exploring various brain diseases. Due to the high dimensionality of fMRI data, FC is typically computed based on the region of interest (ROI), whose parcellation relies on a pre-defined atlas. However, utilizing the brain atlas poses several challenges including 1) subjective selection bias in choosing from various brain atlases, 2) parcellation of each subject's brain with the same atlas yet disregarding individual specificity; 3) lack of interaction between brain region parcellation and downstream ROI-based FC analysis. To address these limitations, we propose a novel randomizing strategy for generating brain function representation to facilitate neural disease diagnosis. Specifically, we randomly sample brain patches, thus avoiding ROI parcellations of the brain atlas. Then, we introduce a new brain function representation framework for the sampled patches. Each patch has its function description by referring to anchor patches, as well as the position description. Furthermore, we design an adaptive-selection-assisted Transformer network to optimize and integrate the function representations of all sampled patches within each brain for neural disease diagnosis. To validate our framework, we conduct extensive evaluations on three datasets, and the experimental results establish the effectiveness and generality of our proposed method, offering a promising avenue for advancing neural disease diagnosis beyond the confines of traditional atlas-based methods. Our code is available at https://github.com/mjliu2020/RandomFR.
Collapse
|
2
|
Zhong T, Wang Y, Xu X, Wu X, Liang S, Ning Z, Wang L, Niu Y, Li G, Zhang Y. A brain subcortical segmentation tool based on anatomy attentional fusion network for developing macaques. Comput Med Imaging Graph 2024; 116:102404. [PMID: 38870599 DOI: 10.1016/j.compmedimag.2024.102404] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2024] [Revised: 05/21/2024] [Accepted: 05/22/2024] [Indexed: 06/15/2024]
Abstract
Magnetic Resonance Imaging (MRI) plays a pivotal role in the accurate measurement of brain subcortical structures in macaques, which is crucial for unraveling the complexities of brain structure and function, thereby enhancing our understanding of neurodegenerative diseases and brain development. However, due to significant differences in brain size, structure, and imaging characteristics between humans and macaques, computational tools developed for human neuroimaging studies often encounter obstacles when applied to macaques. In this context, we propose an Anatomy Attentional Fusion Network (AAF-Net), which integrates multimodal MRI data with anatomical constraints in a multi-scale framework to address the challenges posed by the dynamic development, regional heterogeneity, and age-related size variations of the juvenile macaque brain, thus achieving precise subcortical segmentation. Specifically, we generate a Signed Distance Map (SDM) based on the initial rough segmentation of the subcortical region by a network as an anatomical constraint, providing comprehensive information on positions, structures, and morphology. Then we construct AAF-Net to fully fuse the SDM anatomical constraints and multimodal images for refined segmentation. To thoroughly evaluate the performance of our proposed tool, over 700 macaque MRIs from 19 datasets were used in this study. Specifically, we employed two manually labeled longitudinal macaque datasets to develop the tool and complete four-fold cross-validations. Furthermore, we incorporated various external datasets to demonstrate the proposed tool's generalization capabilities and promise in brain development research. We have made this tool available as an open-source resource at https://github.com/TaoZhong11/Macaque_subcortical_segmentation for direct application.
Collapse
Affiliation(s)
- Tao Zhong
- School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing and Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, China
| | - Ya Wang
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, USA
| | - Xiaotong Xu
- School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing and Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, China
| | - Xueyang Wu
- School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing and Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, China
| | - Shujun Liang
- School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing and Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, China
| | - Zhenyuan Ning
- School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing and Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, China
| | - Li Wang
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, USA
| | - Yuyu Niu
- Yunnan Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, China
| | - Gang Li
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, USA.
| | - Yu Zhang
- School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing and Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, China.
| |
Collapse
|
3
|
Peralta-Malváez L, Turnbull A, Anthony M, Adeli E, Lin FV. CCA identifies a neurophysiological marker of adaptation capacity that is reliably linked to internal locus of control of cognition in amnestic MCI. GeroScience 2023:10.1007/s11357-023-00730-8. [PMID: 36697886 PMCID: PMC10400522 DOI: 10.1007/s11357-023-00730-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2022] [Accepted: 01/09/2023] [Indexed: 01/27/2023] Open
Abstract
Locus of control (LOC) describes whether an individual thinks that they themselves (internal LOC) or external factors (external LOC) have more influence on their lives. LOC varies by domain, and a person's LOC for their intellectual capacities (LOC-Cognition) may be a marker of resilience in older adults at risk for dementia, with internal LOC-Cognition relating to better outcomes and improved treatment adherence. Vagal control, a key component of parasympathetic autonomic nervous system (ANS) regulation, may reflect a neurophysiological biomarker of internal LOC-Cognition. We used canonical correlation analysis (CCA) to identify a shared neurophysiological marker of ANS regulation from electrocardiogram (during auditory working memory) and functional connectivity (FC) data. A canonical variable from root mean square of successive differences (RMSSD) time series and between-network FC was significantly related to internal LOC-Cognition (β = 0.266, SE = 0.971, CI = [0.190, 4.073], p = 0.031) in 65 participants (mean age = 74.7, 32 female) with amnestic mild cognitive impairment (aMCI). Follow-up data from 55 of these individuals (mean age = 73.6, 22 females) was used to show reliability of this relationship (β = 0.271, SE = 0.971, CI = [0.033, 2.630], p = 0.047), and a second sample (40 participants with aMCI/healthy cognition, mean age = 72.7, 24 females) showed that the canonical vector biomarker generalized to visual working memory (β = 0.36, SE = 0.136, CI = [0.023, 0.574], p = 0.037), but not inhibition task RMSSD data (β = 0.08, SE = 1.486, CI = [- 0.354, 0.657], p = 0.685). This canonical vector may represent a biomarker of autonomic regulation that explains how some older adults maintain internal LOC-Cognition as dementia progresses. Future work should further test the causality of this relationship and the modifiability of this biomarker.
Collapse
Affiliation(s)
- Lizbeth Peralta-Malváez
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, 94305, USA
| | - Adam Turnbull
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, 94305, USA. .,Department of Brain and Cognitive Sciences, University of Rochester, Rochester, NY, 14627, USA.
| | - Mia Anthony
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, 94305, USA.,Department of Brain and Cognitive Sciences, University of Rochester, Rochester, NY, 14627, USA
| | - Ehsan Adeli
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, 94305, USA
| | - F Vankee Lin
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, 94305, USA
| |
Collapse
|
4
|
Chen Q, Turnbull A, Cole M, Zhang Z, Lin FV. Enhancing Cortical Network-level Participation Coefficient as a Potential Mechanism for Transfer in Cognitive Training in aMCI. Neuroimage 2022; 254:119124. [PMID: 35331866 PMCID: PMC9199485 DOI: 10.1016/j.neuroimage.2022.119124] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Accepted: 03/19/2022] [Indexed: 02/06/2023] Open
Abstract
Effective cognitive training must improve cognition beyond the trained domain (show a transfer effect) and be applicable to dementia-risk populations, e.g., amnesic mild cognitive impairment (aMCI). Theories suggest training should target processes that 1) show robust engagement, 2) are domain-general, and 3) reflect long-lasting changes in brain organization. Brain regions that connect to many different networks (i.e., show high participation coefficient; PC) are known to support integration. This capacity is 1) relatively preserved in aMCI, 2) required across a wide range of cognitive domains, and 3) trait-like. In 49 individuals with aMCI that completed a 6-week visual speed of processing training (VSOP) and 28 active controls, enhancement in PC was significantly more related to transfer to working memory at global and network levels in VSOP compared to controls, particularly in networks with many high-PC nodes. This suggests that enhancing brain integration may provide a target for developing effective cognitive training.
Collapse
Affiliation(s)
- Quanjing Chen
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, United States
| | - Adam Turnbull
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, United States; School of Nursing, University of Rochester, United States.
| | - Martin Cole
- Department of Biostatics and Computational Biology, University of Rochester, United States
| | - Zhengwu Zhang
- Department of Statistics and Operations Research, UNC-Chapel Hill, United States
| | - Feng V Lin
- CogT Lab, Department of Psychiatry and Behavioral Sciences, Stanford University, United States; The Wu Tsai Neuroscience Institute, Stanford University, University of Rochester, United States
| |
Collapse
|
5
|
Mansour L S, Seguin C, Smith RE, Zalesky A. Connectome spatial smoothing (CSS): Concepts, methods, and evaluation. Neuroimage 2022; 250:118930. [PMID: 35077853 DOI: 10.1016/j.neuroimage.2022.118930] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2021] [Revised: 01/17/2022] [Accepted: 01/21/2022] [Indexed: 10/19/2022] Open
Abstract
Structural connectomes are increasingly mapped at high spatial resolutions comprising many hundreds-if not thousands-of network nodes. However, high-resolution connectomes are particularly susceptible to image registration misalignment, tractography artifacts, and noise, all of which can lead to reductions in connectome accuracy and test-retest reliability. We investigate a network analogue of image smoothing to address these key challenges. Connectome Spatial Smoothing (CSS) involves jointly applying a carefully chosen smoothing kernel to the two endpoints of each tractography streamline, yielding a spatially smoothed connectivity matrix. We develop computationally efficient methods to perform CSS using a matrix congruence transformation and evaluate a range of different smoothing kernel choices on CSS performance. We find that smoothing substantially improves the identifiability, sensitivity, and test-retest reliability of high-resolution connectivity maps, though at a cost of increasing storage burden. For atlas-based connectomes (i.e. low-resolution connectivity maps), we show that CSS marginally improves the statistical power to detect associations between connectivity and cognitive performance, particularly for connectomes mapped using probabilistic tractography. CSS was also found to enable more reliable statistical inference compared to connectomes without any smoothing. We provide recommendations for optimal smoothing kernel parameters for connectomes mapped using both deterministic and probabilistic tractography. We conclude that spatial smoothing is particularly important for the reliability of high-resolution connectomes, but can also provide benefits at lower parcellation resolutions. We hope that our work enables computationally efficient integration of spatial smoothing into established structural connectome mapping pipelines.
Collapse
Affiliation(s)
- Sina Mansour L
- Department of Biomedical Engineering, The University of Melbourne, Parkville, Victoria, Australia.
| | - Caio Seguin
- Melbourne Neuropsychiatry Centre, Department of Psychiatry, The University of Melbourne and Melbourne Health, Parkville, Victoria, Australia; The University of Sydney, School of Biomedical Engineering, Sydney, Australia
| | - Robert E Smith
- The Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria, Australia; Florey Department of Neuroscience and Mental Health, The University of Melbourne, Parkville, Victoria, Australia
| | - Andrew Zalesky
- Department of Biomedical Engineering, The University of Melbourne, Parkville, Victoria, Australia; Melbourne Neuropsychiatry Centre, Department of Psychiatry, The University of Melbourne and Melbourne Health, Parkville, Victoria, Australia
| |
Collapse
|
6
|
Cole M, Murray K, St‐Onge E, Risk B, Zhong J, Schifitto G, Descoteaux M, Zhang Z. Surface-Based Connectivity Integration: An atlas-free approach to jointly study functional and structural connectivity. Hum Brain Mapp 2021; 42:3481-3499. [PMID: 33956380 PMCID: PMC8249904 DOI: 10.1002/hbm.25447] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2020] [Revised: 03/03/2021] [Accepted: 04/06/2021] [Indexed: 01/29/2023] Open
Abstract
There has been increasing interest in jointly studying structural connectivity (SC) and functional connectivity (FC) derived from diffusion and functional MRI. Previous connectome integration studies almost exclusively required predefined atlases. However, there are many potential atlases to choose from and this choice heavily affects all subsequent analyses. To avoid such an arbitrary choice, we propose a novel atlas-free approach, named Surface-Based Connectivity Integration (SBCI), to more accurately study the relationships between SC and FC throughout the intra-cortical gray matter. SBCI represents both SC and FC in a continuous manner on the white surface, avoiding the need for prespecified atlases. The continuous SC is represented as a probability density function and is smoothed for better facilitation of its integration with FC. To infer the relationship between SC and FC, three novel sets of SC-FC coupling (SFC) measures are derived. Using data from the Human Connectome Project, we introduce the high-quality SFC measures produced by SBCI and demonstrate the use of these measures to study sex differences in a cohort of young adults. Compared with atlas-based methods, this atlas-free framework produces more reproducible SFC features and shows greater predictive power in distinguishing biological sex. This opens promising new directions for all connectomics studies.
Collapse
Affiliation(s)
- Martin Cole
- Department of Biostatistics and Computational BiologyUniversity of RochesterRochesterNew YorkUSA
| | - Kyle Murray
- Department of Physics and AstronomyUniversity of RochesterRochesterNew YorkUSA
| | - Etienne St‐Onge
- Sherbrooke Connectivity Imaging Laboratory (SCIL)Université de SherbrookeQuébecCanada
| | - Benjamin Risk
- Department of Biostatistics and BioinformaticsEmory UniversityAtlantaGeorgiaUSA
| | - Jianhui Zhong
- Department of Physics and AstronomyUniversity of RochesterRochesterNew YorkUSA
- Department of Imaging SciencesUniversity of RochesterRochesterNew YorkUSA
| | - Giovanni Schifitto
- Department of Imaging SciencesUniversity of RochesterRochesterNew YorkUSA
- Department of NeurologyUniversity of RochesterRochesterNew YorkUSA
| | - Maxime Descoteaux
- Sherbrooke Connectivity Imaging Laboratory (SCIL)Université de SherbrookeQuébecCanada
| | - Zhengwu Zhang
- Department of Statistics and Operations ResearchUniversity of North Carolina at Chapel HillNorth CarolinaUSA
| |
Collapse
|