Russell A. Poldrack

Sayash Kapoor, Emily Cantrell, Kenny Peng et al. · princeton

Machine learning (ML) methods are proliferating in scientific research. However, the adoption of these methods has been accompanied by failures of validity, reproducibility, and generalizability. These failures can hinder scientific progress, lead to false consensus around invalid claims, and undermine the credibility of ML-based science. ML methods are often applied and fail in similar ways across disciplines. Motivated by this observation, our goal is to provide clear reporting standards for ML-based science. Drawing from an extensive review of past literature, we present the REFORMS checklist ($\textbf{Re}$porting Standards $\textbf{For}$ $\textbf{M}$achine Learning Based $\textbf{S}$cience). It consists of 32 questions and a paired set of guidelines. REFORMS was developed based on a consensus of 19 researchers across computer science, data science, mathematics, social sciences, and biomedical sciences. REFORMS can serve as a resource for researchers when designing and implementing a study, for referees when reviewing papers, and for journals when enforcing standards for transparency and reproducibility.

Anish Khazane, Julien Hoachuck, Krzysztof J. Gorgolewski et al.

Recent advancements in the field of magnetic resonance imaging (MRI) have enabled large-scale collaboration among clinicians and researchers for neuroimaging tasks. However, researchers are often forced to use outdated and slow software to anonymize MRI images for publication. These programs specifically perform expensive mathematical operations over 3D images that rapidly slow down anonymization speed as an image's volume increases in size. In this paper, we introduce DeepDefacer, an application of deep learning to MRI anonymization that uses a streamlined 3D U-Net network to mask facial regions in MRI images with a significant increase in speed over traditional de-identification software. We train DeepDefacer on MRI images from the Brain Development Organization (IXI) and International Consortium for Brain Mapping (ICBM) and quantitatively evaluate our model against a baseline 3D U-Net model with regards to Dice, recall, and precision scores. We also evaluate DeepDefacer against Pydeface, a traditional defacing application, with regards to speed on a range of CPU and GPU devices and qualitatively evaluate our model's defaced output versus the ground truth images produced by Pydeface. We provide a link to a PyPi program at the end of this manuscript to encourage further research into the application of deep learning to MRI anonymization.

Armin W. Thomas, Christopher Ré, Russell A. Poldrack

Deep learning (DL) models find increasing application in mental state decoding, where researchers seek to understand the mapping between mental states (e.g., perceiving fear or joy) and brain activity by identifying those brain regions (and networks) whose activity allows to accurately identify (i.e., decode) these states. Once a DL model has been trained to accurately decode a set of mental states, neuroimaging researchers often make use of interpretation methods from explainable artificial intelligence research to understand the model's learned mappings between mental states and brain activity. Here, we compare the explanation performance of prominent interpretation methods in a mental state decoding analysis of three functional Magnetic Resonance Imaging (fMRI) datasets. Our findings demonstrate a gradient between two key characteristics of an explanation in mental state decoding, namely, its biological plausibility and faithfulness: interpretation methods with high explanation faithfulness, which capture the model's decision process well, generally provide explanations that are biologically less plausible than the explanations of interpretation methods with less explanation faithfulness. Based on this finding, we provide specific recommendations for the application of interpretation methods in mental state decoding.

Russell A Poldrack, Thomas Lu, Gašper Beguš

Artificial intelligence (AI) tools based on large language models have acheived human-level performance on some computer programming tasks. We report several experiments using GPT-4 to generate computer code. These experiments demonstrate that AI code generation using the current generation of tools, while powerful, requires substantial human validation to ensure accurate performance. We also demonstrate that GPT-4 refactoring of existing code can significantly improve that code along several established metrics for code quality, and we show that GPT-4 can generate tests with substantial coverage, but that many of the tests fail when applied to the associated code. These findings suggest that while AI coding tools are very powerful, they still require humans in the loop to ensure validity and accuracy of the results.

Rastko Ciric, Armin W. Thomas, Oscar Esteban et al.

Mapping the functional connectome has the potential to uncover key insights into brain organisation. However, existing workflows for functional connectomics are limited in their adaptability to new data, and principled workflow design is a challenging combinatorial problem. We introduce a new analytic paradigm and software toolbox that implements common operations used in functional connectomics as fully differentiable processing blocks. Under this paradigm, workflow configurations exist as reparameterisations of a differentiable functional that interpolates them. The differentiable program that we envision occupies a niche midway between traditional pipelines and end-to-end neural networks, combining the glass-box tractability and domain knowledge of the former with the amenability to optimisation of the latter. In this preliminary work, we provide a proof of concept for differentiable connectomics, demonstrating the capacity of our processing blocks both to recapitulate canonical knowledge in neuroscience and to make new discoveries in an unsupervised setting. Our differentiable modules are competitive with state-of-the-art methods in problem domains including functional parcellation, denoising, and covariance modelling. Taken together, our results and software demonstrate the promise of differentiable programming for functional connectomics.

Russell A. Poldrack, Krzysztof J. Gorgolewski, Gael Varoquaux

The reproducibility of scientific research has become a point of critical concern. We argue that openness and transparency are critical for reproducibility, and we outline an ecosystem for open and transparent science that has emerged within the human neuroimaging community. We discuss the range of open data sharing resources that have been developed for neuroimaging data, and the role of data standards (particularly the Brain Imaging Data Structure) in enabling the automated sharing, processing, and reuse of large neuroimaging datasets. We outline how the open-source Python language has provided the basis for a data science platform that enables reproducible data analysis and visualization. We also discuss how new advances in software engineering, such as containerization, provide the basis for greater reproducibility in data analysis. The emergence of this new ecosystem provides an example for many areas of science that are currently struggling with reproducibility.

Armin W. Thomas, Christopher Ré, Russell A. Poldrack

In cognitive decoding, researchers aim to characterize a brain region's representations by identifying the cognitive states (e.g., accepting/rejecting a gamble) that can be identified from the region's activity. Deep learning (DL) methods are highly promising for cognitive decoding, with their unmatched ability to learn versatile representations of complex data. Yet, their widespread application in cognitive decoding is hindered by their general lack of interpretability as well as difficulties in applying them to small datasets and in ensuring their reproducibility and robustness. We propose to approach these challenges by leveraging recent advances in explainable artificial intelligence and transfer learning, while also providing specific recommendations on how to improve the reproducibility and robustness of DL modeling results.

Jérôme Dockès, Russell Poldrack, Romain Primet et al.

Reaching a global view of brain organization requires assembling evidence on widely different mental processes and mechanisms. The variety of human neuroscience concepts and terminology poses a fundamental challenge to relating brain imaging results across the scientific literature. Existing meta-analysis methods perform statistical tests on sets of publications associated with a particular concept. Thus, large-scale meta-analyses only tackle single terms that occur frequently. We propose a new paradigm, focusing on prediction rather than inference. Our multivariate model predicts the spatial distribution of neurological observations, given text describing an experiment, cognitive process, or disease. This approach handles text of arbitrary length and terms that are too rare for standard meta-analysis. We capture the relationships and neural correlates of 7 547 neuroscience terms across 13 459 neuroimaging publications. The resulting meta-analytic tool, neuroquery.org, can ground hypothesis generation and data-analysis priors on a comprehensive view of published findings on the brain.

Jérôme Dockès, Demian Wassermann, Russell Poldrack et al.

Despite the digital nature of magnetic resonance imaging, the resulting observations are most frequently reported and stored in text documents. There is a trove of information untapped in medical health records, case reports, and medical publications. In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms. The problem is formulated in terms of minimization of a risk on distributions which leads to a least-deviation cost function. An efficient algorithm in the dual then learns the mapping from documents to brain structures. Empirical results using coordinates extracted from the brain-imaging literature show that i) models must adapt to semantic variation in the terms used to describe a given anatomical structure, ii) voxel-wise parameterization leads to higher likelihood of locations reported in unseen documents, iii) least-deviation cost outperforms least-square. As a proof of concept for our method, we use our model of spatial distributions to predict the distribution of specific neurological conditions from text-only reports.

Rajiv Khanna, Joydeep Ghosh, Russell Poldrack et al.

Approximate inference via information projection has been recently introduced as a general-purpose approach for efficient probabilistic inference given sparse variables. This manuscript goes beyond classical sparsity by proposing efficient algorithms for approximate inference via information projection that are applicable to any structure on the set of variables that admits enumeration using a \emph{matroid}. We show that the resulting information projection can be reduced to combinatorial submodular optimization subject to matroid constraints. Further, leveraging recent advances in submodular optimization, we provide an efficient greedy algorithm with strong optimization-theoretic guarantees. The class of probabilistic models that can be expressed in this way is quite broad and, as we show, includes group sparse regression, group sparse principal components analysis and sparse canonical correlation analysis, among others. Moreover, empirical results on simulated data and high dimensional neuroimaging data highlight the superior performance of the information projection approach as compared to established baselines for a range of probabilistic models.

Megasthenis Asteris, Anastasios Kyrillidis, Oluwasanmi Koyejo et al.

Given two sets of variables, derived from a common set of samples, sparse Canonical Correlation Analysis (CCA) seeks linear combinations of a small number of variables in each set, such that the induced canonical variables are maximally correlated. Sparse CCA is NP-hard. We propose a novel combinatorial algorithm for sparse diagonal CCA, i.e., sparse CCA under the additional assumption that variables within each set are standardized and uncorrelated. Our algorithm operates on a low rank approximation of the input data and its computational complexity scales linearly with the number of input variables. It is simple to implement, and parallelizable. In contrast to most existing approaches, our algorithm administers precise control on the sparsity of the extracted canonical vectors, and comes with theoretical data-dependent global approximation guarantees, that hinge on the spectrum of the input data. Finally, it can be straightforwardly adapted to other constrained variants of CCA enforcing structure beyond sparsity. We empirically evaluate the proposed scheme and apply it on a real neuroimaging dataset to investigate associations between brain activity and behavior measurements.