Dataset Information

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets.

ABSTRACT: Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that may otherwise be too weak to detect. When there is only a single source of variability (e.g., different scanners), domain adaptation and matching the distributions of representations may suffice in many scenarios. But in the presence of more than one nuisance variable which concurrently influence the measurements, pooling datasets poses unique challenges, e.g., variations in the data can come from both the acquisition method as well as the demographics of participants (gender, age). Invariant representation learning, by itself, is ill-suited to fully model the data generation process. In this paper, we show how bringing recent results on equivariant representation learning (for studying symmetries in neural networks) instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution. In particular, we demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples. Our code is available on https://github.com/vsingh-group/DatasetPooling.

SUBMITTER: Lokhande VS

PROVIDER: S-EPMC9581465 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets.

Lokhande Vishnu Suresh VS Ravi Sathya N SN Chakraborty Rudrasis R Singh Vikas V

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 20220601

Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that may otherwise be too weak to detect. When there is only a single source of variability (e.g., different scanners), domain adaptation and matching the distributions of representations may suffice in many scenarios. But in the presence of more than one nuisance variable which concurrently influence the measure ...[more]

PMID: 36268536

Similar Datasets

Project description:Arterial Spin Labeling (ASL) perfusion image series have recently been utilized for functional connectivity (FC) analysis in healthy volunteers and children with autism spectrum disorders (ASD). Noise reduction by using nuisance variables has been shown to be necessary to minimize potential confounding effects of head motion and physiological signals on BOLD based FC analysis. The purpose of the present study is to systematically evaluate the effectiveness of different noise reduction strategies (NRS) using nuisance variables to improve perfusion based FC analysis in two cohorts of healthy adults using state of the art 3D background-suppressed (BS) GRASE pseudo-continuous ASL (pCASL) and dual-echo 2D-EPI pCASL sequences. Five different NRS were performed in healthy volunteers to compare their performance. We then compared seed-based FC analysis using 3D BS GRASE pCASL in a cohort of 12 children with ASD (3f/9m, age 12.8 ± 1.3 years) and 13 typically developing (TD) children (1f/12m; age 13.9 ± 3 years) in conjunction with NRS. Regression of different combinations of nuisance variables affected FC analysis from a seed in the posterior cingulate cortex (PCC) to other areas of the default mode network (DMN) in both BOLD and pCASL data sets. Consistent with existing literature on BOLD-FC, we observed improved spatial specificity after physiological noise reduction and improved long-range connectivity using head movement related regressors. Furthermore, 3D BS GRASE pCASL shows much higher temporal SNR compared to dual-echo 2D-EPI pCASL and similar effects of noise reduction as those observed for BOLD. Seed-based FC analysis using 3D BS GRASE pCASL in children with ASD and TD children showed that noise reduction including physiological and motion related signals as nuisance variables is crucial for identifying altered long-range connectivity from PCC to frontal brain areas associated with ASD. This is the first study that systematically evaluated the effects of different NRS on ASL based FC analysis. 3D BS GRASE pCASL is the preferred ASL sequence for FC analysis due to its superior temporal SNR. Removing physiological noise and motion parameters is critical for detecting altered FC in neurodevelopmental disorders such as ASD.

Project description:BackgroundData requirements by governments, donors and the international community to measure health and development achievements have increased in the last decade. Datasets produced in surveys conducted in several countries and years are often combined to analyse time trends and geographical patterns of demographic and health related indicators. However, since not all datasets have the same structure, variables definitions and codes, they have to be harmonised prior to submitting them to the statistical analyses. Manually searching, renaming and recoding variables are extremely tedious and prone to errors tasks, overall when the number of datasets and variables are large. This article presents an automated approach to harmonise variables names across several datasets, which optimises the search of variables, minimises manual inputs and reduces the risk of error.ResultsThree consecutive algorithms are applied iteratively to search for each variable of interest for the analyses in all datasets. The first search (A) captures particular cases that could not be solved in an automated way in the search iterations; the second search (B) is run if search A produced no hits and identifies variables the labels of which contain certain key terms defined by the user. If this search produces no hits, a third one (C) is run to retrieve variables which have been identified in other surveys, as an illustration. For each variable of interest, the outputs of these engines can be (O1) a single best matching variable is found, (O2) more than one matching variable is found or (O3) not matching variables are found. Output O2 is solved by user judgement. Examples using four variables are presented showing that the searches have a 100% sensitivity and specificity after a second iteration.ConclusionEfficient and tested automated algorithms should be used to support the harmonisation process needed to analyse multiple datasets. This is especially relevant when the numbers of datasets or variables to be included are large.

Dataset Information

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets.

Publications

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets