Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

• URL: http://arxiv.org/abs/2301.08525v1
• Date: Fri, 20 Jan 2023 12:05:59 GMT
• Title: Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• Authors: Fabian Eitel, Marc-Andr\'e Schulz, Moritz Seiler, Henrik Walter, Kerstin Ritter
• Abstract summary: Deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises. After reviewing recent applications within neuroimaging-based psychiatric research, we discuss current challenges.
• Score: 0.9449650062296824
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.

Related papers

• NeuroBind: Towards Unified Multimodal Representations for Neural Signals [20.02503060795981]
  We present NeuroBind, a representation that unifies multiple brain signal types, including EEG, fMRI, calcium imaging, and spiking data. This approach holds significant potential for advancing neuroscience research, improving AI systems, and developing neuroprosthetics and brain-computer interfaces.
  arXiv  Detail & Related papers  (2024-07-19T04:42:52Z)
• Dimensional Neuroimaging Endophenotypes: Neurobiological Representations of Disease Heterogeneity Through Machine Learning [11.653182438505558]
  We first present a systematic literature overview of studies using machine learning and multimodal MRI to unravel disease heterogeneity in various neuropsychiatric and neurodegenerative disorders. We then summarize relevant machine learning methodologies and discuss an emerging paradigm which we call dimensional neuroimaging endophenotype (DNE) DNE dissects the neurobiological heterogeneity of neuropsychiatric and neurodegenerative disorders into a low dimensional yet informative, quantitative brain phenotypic representation.
  arXiv  Detail & Related papers  (2024-01-17T16:31:48Z)
• Constraints on the design of neuromorphic circuits set by the properties of neural population codes [61.15277741147157]
  In the brain, information is encoded, transmitted and used to inform behaviour. Neuromorphic circuits need to encode information in a way compatible to that used by populations of neuron in the brain.
  arXiv  Detail & Related papers  (2022-12-08T15:16:04Z)
• Applications of Generative Adversarial Networks in Neuroimaging and Clinical Neuroscience [4.394368629380544]
  Generative adversarial networks (GANs) are one powerful type of deep learning models that have been successfully utilized in numerous fields. GANs have shown enhanced capabilities in capturing spatially complex, nonlinear, and potentially subtle disease effects. This review appraises the existing literature on the applications of GANs in imaging studies of various neurological conditions.
  arXiv  Detail & Related papers  (2022-06-14T18:10:00Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations [60.47807856873544]
  A fundamental goal in neuroscience is to understand the relationship between neural activity and behavior. We generated a new multimodal dataset consisting of the spontaneous behaviors generated by fruit flies. This dataset and our new set of augmentations promise to accelerate the application of self-supervised learning methods in neuroscience.
  arXiv  Detail & Related papers  (2021-11-29T15:27:51Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• Machine Learning Applications on Neuroimaging for Diagnosis and Prognosis of Epilepsy: A Review [6.185653026582807]
  We highlight the interactions between neuroimaging and machine learning in the context of the epilepsy diagnosis and prognosis. We introduce two approaches to apply machine learning methods to neuroimaging data: the two-step compositional approach and the end-to-end approach. A detailed review on the machine learning tasks on epileptic images is presented, such as segmentation, localization and lateralization tasks.
  arXiv  Detail & Related papers  (2021-02-05T18:39:12Z)
• Neuro-symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernels [93.58854458951431]
  We present a probabilistic programmed deep kernel learning approach to personalized, predictive modeling of neurodegenerative diseases. Our analysis considers a spectrum of neural and symbolic machine learning approaches. We run evaluations on the problem of Alzheimer's disease prediction, yielding results that surpass deep learning.
  arXiv  Detail & Related papers  (2020-09-16T15:16:03Z)
• A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis [38.213459556446765]
  Deep learning has been recently used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET) This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis.
  arXiv  Detail & Related papers  (2020-05-10T04:20:50Z)
• A Graph Gaussian Embedding Method for Predicting Alzheimer's Disease Progression with MEG Brain Networks [59.15734147867412]
  Characterizing the subtle changes of functional brain networks associated with Alzheimer's disease (AD) is important for early diagnosis and prediction of disease progression. We developed a new deep learning method, termed multiple graph Gaussian embedding model (MG2G) We used MG2G to detect the intrinsic latent dimensionality of MEG brain networks, predict the progression of patients with mild cognitive impairment (MCI) to AD, and identify brain regions with network alterations related to MCI.
  arXiv  Detail & Related papers  (2020-05-08T02:29:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.