Normative Modeling with the Predictive Clinical Neuroscience Toolkit (PCNtoolkit)

Rutherford, Saige; Marquand, André F.

doi:10.31219/osf.io/2c8s9

Cited by 1 publication

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Section 1: Accessing and computing at scale The Predictive Clinical Neuroscience (PCN) Toolkit is described in Chapter 14 (Rutherford & Marquand, 2023), and offers an easy way to apply the powerful tool that is Normative Modeling.…”

Section: Overview Of Chapters In This Bookmentioning

confidence: 99%

Introduction to Methods for Analyzing Large Neuroimaging Datasets

Whelan,

Lemaitre

2023

Preprint

View full text Add to dashboard Cite

In this chapter, we provide an overview of this book on methods for analyzing large neuroimaging datasets. There is a recognition in the field of neuroimaging that sample size must drastically increase to achieve adequate statistical power and reproducibility. Several large neuroimaging studies and databases, such as OpenNeuro and the Adolescent Brain and Cognitive Development project have emerged, offering open access to vast amounts of data. However, there is a dearth of practical guidance for working with large neuroimaging datasets, a deficit that this book seeks to address. With the emphasis on providing hands-on instruction, chapters contain worked examples using open-access data. The book is organized as follows. In Section 1, the reader is shown how to access and download large datasets, and how to compute at scale. In Section 2, chapters cover best practices for working with large data, including how to build reproducible pipelines, the use of Git for collaboration and how to make EEG and fMRI data sharable and standardized. In Section 3, chapters describe how to do structural and functional preprocessing data at scale, incorporating practical advice on potential trade-offs of standardization. In Section 4, chapters describe various toolboxes for interrogating large neuroimaging datasets, including those based on machine learning and deep learning approaches. These methods can be applied to connectomic and region-of-interest data. Finally, the book contains a glossary of useful terms.

show abstract

Section: Overview Of Chapters In This Bookmentioning

confidence: 99%