Dataset Information

Limits of decoding mental states with fMRI.

ABSTRACT: A growing number of studies claim to decode mental states using multi-voxel decoders of brain activity. It has been proposed that the fixed, fine-grained, multi-voxel patterns in these decoders are necessary for discriminating between and identifying mental states. Here, we present evidence that the efficacy of these decoders might be overstated. Across various tasks, decoder patterns were spatially imprecise, as decoder performance was unaffected by spatial smoothing; 90% redundant, as selecting a random 10% of a decoder's constituent voxels recovered full decoder performance; and performed similarly to brain activity maps used as decoders. We distinguish decoder performance in discriminating between mental states from performance in identifying a given mental state, and show that even when discrimination performance is adequate, identification can be poor. Finally, we demonstrate that simple and intuitive similarity metrics explain 91% and 62% of discrimination performance within- and across-subjects, respectively. These findings indicate that currently used across-subject decoders of mental states are superfluous and inappropriate for decision-making.

SUBMITTER: Jabakhanji R

PROVIDER: S-EPMC9238276 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Limits of decoding mental states with fMRI.

Jabakhanji Rami R Vigotsky Andrew D AD Bielefeld Jannis J Huang Lejian L Baliki Marwan N MN Iannetti Giandomenico G Apkarian A Vania AV

Cortex; a journal devoted to the study of the nervous system and behavior 20220131

A growing number of studies claim to decode mental states using multi-voxel decoders of brain activity. It has been proposed that the fixed, fine-grained, multi-voxel patterns in these decoders are necessary for discriminating between and identifying mental states. Here, we present evidence that the efficacy of these decoders might be overstated. Across various tasks, decoder patterns were spatially imprecise, as decoder performance was unaffected by spatial smoothing; 90% redundant, as selectin ...[more]

PMID: 35219121

Similar Datasets

Project description:This paper describes a general kernel regression approach to predict experimental conditions from activity patterns acquired with functional magnetic resonance image (fMRI). The standard approach is to use classifiers that predict conditions from activity patterns. Our approach involves training different regression machines for each experimental condition, so that a predicted temporal profile is computed for each condition. A decision function is then used to classify the responses from the testing volumes into the corresponding category, by comparing the predicted temporal profile elicited by each event, against a canonical hemodynamic response function. This approach utilizes the temporal information in the fMRI signal and maintains more training samples in order to improve the classification accuracy over an existing strategy. This paper also introduces efficient techniques of temporal compaction, which operate directly on kernel matrices for kernel classification algorithms such as the support vector machine (SVM). Temporal compacting can convert the kernel computed from each fMRI volume directly into the kernel computed from beta-maps, average of volumes or spatial-temporal kernel. The proposed method was applied to three different datasets. The first one is a block-design experiment with three conditions of image stimuli. The method outperformed the SVM classifiers of three different types of temporal compaction in single-subject leave-one-block-out cross-validation. Our method achieved 100% classification accuracy for six of the subjects and an average of 94% accuracy across all 16 subjects, exceeding the best SVM classification result, which was 83% accuracy (p=0.008). The second dataset is also a block-design experiment with two conditions of visual attention (left or right). Our method yielded 96% accuracy and SVM yielded 92% (p=0.005). The third dataset is from a fast event-related experiment with two categories of visual objects. Our method achieved 77% accuracy, compared with 72% using SVM (p=0.0006).

Dataset Information

Limits of decoding mental states with fMRI.

Publications

Limits of decoding mental states with fMRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets