Investigators
Dinggang Shen, Pew-Thian Yap
Contact info (email)
ptyap@med.unc.edu
1. Define context(s)
aid in clinical decision making
identify/explore new therapies
reveal new biological insights
Current Conformance Level / Target Conformance Level
Extensive
Primary goal of the model/tool/database
The Brain Network Construction and Classification (BrainNetClass v1.1) toolbox is designed for neuroscientists interested in using advanced brain functional connectomics, beyond simple Pearson’s correlation, for individualized disease diagnosis. The toolbox provides an easy-to-use automated pipeline that converts regional blood-oxygen-level-dependent (BOLD) resting-state functional MRI time series to high-order dynamic brain functional networks.
Biological domain of the model
blood-oxygen-level-dependent signal
Structure(s) of interest in the model
Brain
Spatial scales included in the model
Not Applicable
Time scales included in the model
Not Applicable
2. Data for building and validating the model
| Data for building the model | Published? | Private? | How is credibility checked? | Current Conformance Level / Target Conformance Level |
|---|---|---|---|---|
| in vitro (primary cells cell, lines, etc.) | ||||
| ex vivo (excised tissues) | ||||
| in vivo pre-clinical (lower-level organism or small animal) | ||||
| in vivo pre-clinical (large animal) | ||||
| Human subjects/clinical | Yes | Public | It's from the ADNI dataset. | Adequate |
| Other: ________________________ |
| Data for validating the model | Published? | Private? | How is credibility checked? | Current Conformance Level / Target Conformance Level |
|---|---|---|---|---|
| in vitro (primary cells cell, lines, etc.) | ||||
| ex vivo (excised tissues) | ||||
| in vivo pre-clinical (lower-level organism or small animal) | ||||
| in vivo pre-clinical (large animal) | ||||
| Human subjects/clinical | Yes | Public | Eyes open and closed fMRI data from the Beijing Eyes Open Eyes Closed Study (http://fcon_1000.projects.nitrc.org/indi/retro/BeijingEOEC.html). It has been used in many researches. | Adequate |
| Other: ________________________ |
3. Validate within context(s)
| Who does it? | When does it happen? | How is it done? | Current Conformance Level / Target Conformance Level | |
|---|---|---|---|---|
| Verification | ||||
| Validation | Developers and users have done independent validations | throughout development of the software with an independent review prior to release | Our toolbox was validated on various datasets. Machine learning techniques adopted in the toolbox were evaluated using cross-validation strategies. | Extensive |
| Uncertainty quantification | ||||
| Sensitivity analysis | Developers and users have performed sentivity analysis | throughout development of the software with an independent review prior to release | The test-retest reliability of high-order functional connectivity metrics has been verify. Parameter sensitivity and model robustness tests were perform in [2] for reproducibility and generalizability. | Extensive |
| Other:__________ | ||||
| Additional Comments |
4. Limitations
| Disclaimer statement (explain key limitations) | Who needs to know about this disclaimer? | How is this disclaimer shared with that audience? | Current Conformance Level / Target Conformance Level |
|---|---|---|---|
| Only two-class classification. | Toolbox users | In the published paper. | Extensive |
| Features limited to functional connectivity strengths and clustering coefficients. | Toolbox users | In the published paper. | Extensive |
| Only support vector machine (SVM) classification is supported. | Toolbox users | In the published paper. | Extensive |
| Feature selection methods limited LASSO and two-sample t-test. | Toolbox users | In the published paper. | Extensive |
| For SVM and LASSO hyperparameters, users need to use batch mode. | Toolbox users | In the published paper. | Extensive |
5. Version control
| Current Conformance Level / Target Conformance Level |
|---|
| Extensive |
| Naming Conventions? | Repository? | Code Review? | |
|---|---|---|---|
| individual modeler | Yes | Yes | Yes |
| within the lab | NA | Yes | Yes |
| collaborators | NA | Yes | Yes |
6. Documentation
| Current Conformance Level / Target Conformance Level | |
|---|---|
| Code commented? | Extensive |
| Scope and intended use described? | Extensive |
| User’s guide? | Extensive |
| Developer’s guide? | Extensive |
7. Dissemination
| Current Conformance Level / Target Conformance Level |
|---|
| Extensive |
| Target Audience(s): | “Inner circle” | Scientific community | Public |
|---|---|---|---|
| Simulations | |||
| Models | https://github.com/zzstefan/BrainNetClass | ||
| Software | https://github.com/zzstefan/BrainNetClass | ||
| Results | https://onlinelibrary.wiley.com/doi/full/10.1002/hbm.24979 | ||
| Implications of results | https://onlinelibrary.wiley.com/doi/full/10.1002/hbm.24979 |
8. Independent reviews
| Current Conformance Level / Target Conformance Level |
|---|
| Extensive |
| Reviewer(s) name & affiliation: | It has been published in Human Brain Mapping. So the reviewers are selected by the editors. |
|---|---|
| When was review performed? | 1/1/2020-2/9/2020 |
| How was review performed and outcomes of the review? | We have revised the paper based on the reviews and our paper got accepted. |
9. Test competing implementations
| Current Conformance Level / Target Conformance Level |
|---|
| Adequate |
| Yes or No (briefly summarize) | |
|---|---|
| Were competing implementations tested? | |
| Did this lead to model refinement or improvement? | Yes----Comparisons with competing methods were performed the results were published. |
10. Conform to standards
| Current Conformance Level / Target Conformance Level |
|---|
| Adequate |
| Yes or No (briefly summarize) | |
|---|---|
| Are there operating procedures, guidelines, or standards for this type of multiscale modeling? | Yes----Our toolbox conforms to rigorous guidelines for best practices in machine learning, including parameter optimization, cross validation, multiple performance metrics, generalization, and robustness. |
| How do your modeling efforts conform? |
11. (optional) Additional information to support items 1-10