Noah Schweitzer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Noah Schweitzer has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Akiko Mizuno
Department of Psychiatry, University of Pittsburgh, Pittsburgh, PA, USA
1 shared publication Bistra Iordanova
University of Pittsburgh Pittsburgh PA USA
1 shared publicationEduardo Diniz
Department of Bioengineering University of Pittsburgh Pittsburgh Pennsylvania United States of America
1 shared publication- George Stetten
University of Pittsburgh, Pittsburgh, PA USA
1 shared publication Hecheng Jin
1 shared publicationHoward J Aizenstein
University of Pittsburgh Pittsburgh PA USA
1 shared publication
Latest Publications
- Open Access
Leveraging The Finite States of Emotion Processing to Study Late-Life Mental Health
Traditional approaches in mental health research apply General Linear Models (GLM) to describe the longitudinal dynamics of observed psycho-behavioral measurements (questionnaire summary scores). Similarly, GLMs are also applied to characterize relationships between neurobiological measurements (regional fMRI signals) and perceptual stimuli or other regional signals. While these methods are useful for exploring linear correlations among the isolated signals of those constructs (i.e., summary scores or fMRI signals), these classical frameworks fall short in providing insights into the comprehensive system-level dynamics underlying observable changes. Hidden Markov Models (HMM) are a statistical model that enable us to describe the sequential relations among multiple observable constructs, and when applied through the lens of Finite State Automata (FSA), can provide a more integrated and intuitive framework for modeling and understanding the underlying controller (the prescription for how to respond to inputs) that fundamentally defines any system, as opposed to linearly correlating output signals produced by the controller. We present a simple and intuitive HMM processing pipeline vcHMM (See Preliminary Data) that highlights FSA theory and is applicable for both behavioral analysis of questionnaire data and fMRI data. HMMs offer theoretic promise as they are computationally equivalent to the FSA, the control processor of a Turing Machine (TM) The dynamic programming Viterbi algorithm is used to leverage the HMM model. It efficiently identifies the most likely sequence of hidden states. The vcHMM pipeline leverages this grammar to understand how behavior and neural activity relate to depression.
Open AccessLeveraging The Finite States of Emotion Processing to Study Late-Life Mental Health
Traditional approaches in mental health research apply General Linear Models (GLM) to describe the longitudinal dynamics of observed psycho-behavioral measurements (questionnaire summary scores). Similarly, GLMs are also applied to characterize relationships between neurobiological measurements (regional fMRI signals) and perceptual stimuli or other regional signals. While these methods are useful for exploring linear correlations among the isolated signals of those constructs (i.e., summary scores or fMRI signals), these classical frameworks fall short in providing insights into the comprehensive system-level dynamics underlying observable changes. Hidden Markov Models (HMM) are a statistical model that enable us to describe the sequential relations among multiple observable constructs, and when applied through the lens of Finite State Automata (FSA), can provide a more integrated and intuitive framework for modeling and understanding the underlying controller (the prescription for how to respond to inputs) that fundamentally defines any system, as opposed to linearly correlating output signals produced by the controller. We present a simple and intuitive HMM processing pipeline vcHMM (See Preliminary Data) that highlights FSA theory and is applicable for both behavioral analysis of questionnaire data and fMRI data. HMMs offer theoretic promise as they are computationally equivalent to the FSA, the control processor of a Turing Machine (TM) The dynamic programming Viterbi algorithm is used to leverage the HMM model. It efficiently identifies the most likely sequence of hidden states. The vcHMM pipeline leverages this grammar to understand how behavior and neural activity relate to depression.
- 31 December 2021
- Published by Wiley in Alzheimer's & Dementia
- Vol. 17 (S1) , e053167
A novel method for tracking the progression of WMHs through the alignment of premortem in‐vivo to postmortem ex‐vivo MRI and histopathology
Background: White matter hyperintensities (WMHs) are neuroimaging features associated with Alzheimer’s disease (AD). Ex‐vivo studies may enable better characterization of WMHs pathological substrates. In this work, we present a novel method that leverages in‐vivo and ex‐vivo MRIs and histopathology to analyze the progression of WMHs in AD.Method: A single subject’s in‐vivo MRI scans at four different time points were analyzed. Ex‐vivo scans of the brain left hemisphere were done using 16‐Tx and 32‐Rx TicTacToe coil3 and a 3‐D printed enclosure with integrated cutting guides1 (Fig. 1). The WMHs were segmented on the T2‐weighted FLAIR in‐vivo MRI 2, and registered onto the final time point via SPM’s normalized mutual information‐based algorithm. All four WMH segmentations were warped to the ex‐vivo MRI’s space by applying the deformation field from the ITK in‐vivo to ex‐vivo registration.Result: The 3D printed enclosure achieved an accurate alignment between gross pathology, ex‐vivo and in‐vivo MRI (Fig. 1). Then, we computed the WMHs’ growth over time warped onto the ex‐vivo MRI (Fig. 2). This growth was quantified as the total number of voxels in each segmentation longitudinally with a quadratic fit with an R2 =0.99 (Fig. 2). Lastly, we found a significant change in the distribution of WMH segmentations over time as evident by their normalized histograms (Fig. 3).Conclusion: We present a novel method to track the progression of WMHs in‐vivo to ex‐vivo MRI and gross pathology. Future studies will perform a voxel‐wise analysis on the WMHs in MRI scans, both in‐vivo and ex‐vivo, along with its histological correlates to gain insight into the underlying cellular mechanisms during the biomarker’s development. References: 1. Nadim Farhat et al. “Reusable 3D printed enclosure with integrated cutting guides for the alignment of high resolution ex‐vivo MRI with ex‐vivo gross brain photographs.” 2021 ISMRM Meeting (Under revision). 2. Wu, M. et al (2006). “A fully automated method for quantifying and localizing white matter hyperintensities on MR images.” Psychiatry Research: Neuroimaging, 148(2‐3), 133‐142. 3. T. Santini et al., “In‐vivo and numerical analysis of the eigenmodes produced by a multi‐level Tic‐Tac‐Toe head transmit array for 7 Tesla MRI,” PLoS One, vol. 13, no. 11, p. e0206127, Nov. 2018.
- 31 December 2021
- Published by Wiley in Alzheimer's & Dementia
- Vol. 17 (S1) , e053167
A novel method for tracking the progression of WMHs through the alignment of premortem in‐vivo to postmortem ex‐vivo MRI and histopathology
Background: White matter hyperintensities (WMHs) are neuroimaging features associated with Alzheimer’s disease (AD). Ex‐vivo studies may enable better characterization of WMHs pathological substrates. In this work, we present a novel method that leverages in‐vivo and ex‐vivo MRIs and histopathology to analyze the progression of WMHs in AD.Method: A single subject’s in‐vivo MRI scans at four different time points were analyzed. Ex‐vivo scans of the brain left hemisphere were done using 16‐Tx and 32‐Rx TicTacToe coil3 and a 3‐D printed enclosure with integrated cutting guides1 (Fig. 1). The WMHs were segmented on the T2‐weighted FLAIR in‐vivo MRI 2, and registered onto the final time point via SPM’s normalized mutual information‐based algorithm. All four WMH segmentations were warped to the ex‐vivo MRI’s space by applying the deformation field from the ITK in‐vivo to ex‐vivo registration.Result: The 3D printed enclosure achieved an accurate alignment between gross pathology, ex‐vivo and in‐vivo MRI (Fig. 1). Then, we computed the WMHs’ growth over time warped onto the ex‐vivo MRI (Fig. 2). This growth was quantified as the total number of voxels in each segmentation longitudinally with a quadratic fit with an R2 =0.99 (Fig. 2). Lastly, we found a significant change in the distribution of WMH segmentations over time as evident by their normalized histograms (Fig. 3).Conclusion: We present a novel method to track the progression of WMHs in‐vivo to ex‐vivo MRI and gross pathology. Future studies will perform a voxel‐wise analysis on the WMHs in MRI scans, both in‐vivo and ex‐vivo, along with its histological correlates to gain insight into the underlying cellular mechanisms during the biomarker’s development. References: 1. Nadim Farhat et al. “Reusable 3D printed enclosure with integrated cutting guides for the alignment of high resolution ex‐vivo MRI with ex‐vivo gross brain photographs.” 2021 ISMRM Meeting (Under revision). 2. Wu, M. et al (2006). “A fully automated method for quantifying and localizing white matter hyperintensities on MR images.” Psychiatry Research: Neuroimaging, 148(2‐3), 133‐142. 3. T. Santini et al., “In‐vivo and numerical analysis of the eigenmodes produced by a multi‐level Tic‐Tac‐Toe head transmit array for 7 Tesla MRI,” PLoS One, vol. 13, no. 11, p. e0206127, Nov. 2018.