| Autor: |
Richie-Halford, A., Cieslak, M., Ai, L., Caffarra, S., Covitz, S., Franco, A., Karipidis, I., Kruper, J., Milham, M., Avelar-Pereira, B., Roy, E., Sydnor, V., Yeatman, J., Abbott, N., Anderson, J., Gagana, B., Bleile, M., Bloomfield, P., Bottom, V., Bourque, J., Boyle, R., Brynildsen, J., Calarco, N., Castrellon, J., Chaku, N., Chen, B., Chopra, S., Coffey, E., Colenbier, N., Cox, D., Crippen, J., Crouse, J., David, S., Leener, B., Delap, G., Deng, Z., Dugre, J., Eklund, A., Ellis, K., Ered, A., Farmer, H., Faskowitz, J., Finch, J., Flandin, G., Flounders, M., Fonville, L., Frandsen, S., Garic, D., Garrido-Vásquez, P., Gonzalez-Escamilla, G., Grogans, S., Grotheer, M., Gruskin, D., Guberman, G., Haggerty, E., Hahn, Y., Hall, E., Hanson, J., Harel, Y., Vieira, B., Hettwer, M., Hobday, H., Horien, C., Huang, F., Huque, Z., James, A., Kahhale, I., Kamhout, S., Keller, A., Khera, H., Kiar, G., Kirk, P., Kohl, S., Korenic, S., Korponay, C., Kozlowski, A., Kraljevic, N., Lazari, A., Leavitt, M., Li, Z., Liberati, G., Lorenc, E., Lossin, A., Lotter, L., Lydon-Staley, D., Madan, C., Magielse, N., Marusak, H., Mayor, J., McGowan, A., Mehta, K., Meisler, S., Michael, C., Mitchell, M., Morand-Beaulieu, S., Newman, B., Nielsen, J., O’Mara, S., Ojha, A., Omary, A., Özarslan, E., Parkes, L., Peterson, M., Pines, A., Pisanu, C., Rich, R., Sahoo, A., Samara, A., Sayed, F., Schneider, J., Shaffer, L., Shatalina, E., Sims, S., Sinclair, S., Song, J., Hogrogian, G., Tooley, U., Tripathi, V., Turker, H., Valk, S., https://orcid.org/0000-0003-2998-6849, Wall, M., Walther, C., Wang, Y., Wegmann, B., Welton, T., Wiesman, A., Wiesman, M., Winters, D., Yuan, R., Zacharek, S., Zajner, C., Zakharov, I., Zammarchi, G., Zhou, D., Zimmerman, B., Zoner, K., Satterthwaite, T., Rokem, A. |
| Přispěvatelé: |
Fibr Community Science Consortium |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
Scientific Data
Scientific Data, 9 (1) |
| ISSN: |
2052-4463 |
| Popis: |
We created a set of resources to enable research based on openly-available diffusion MRI (dMRI) data from the Healthy Brain Network (HBN) study. First, we curated the HBN dMRI data (N = 2747) into the Brain Imaging Data Structure and preprocessed it according to best-practices, including denoising and correcting for motion effects, susceptibility-related distortions, and eddy currents. Preprocessed, analysis-ready data was made openly available. Data quality plays a key role in the analysis of dMRI. To optimize QC and scale it to this large dataset, we trained a neural network through the combination of a small data subset scored by experts and a larger set scored by community scientists. The network performs QC highly concordant with that of experts on a held out set (ROC-AUC = 0.947). A further analysis of the neural network demonstrates that it relies on image features with relevance to QC. Altogether, this work both delivers resources to advance transdiagnostic research in brain connectivity and pediatric mental health, and establishes a novel paradigm for automated QC of large datasets.
Scientific Data, 9 (1)
ISSN:2052-4463 |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink 