SOCR News AmStats SIM 2024

SOCR News & Events: 2024 American Statistical Association, Statistical Methods in Imaging Annual Meeting, Indianapolis

The 2024 American Statistical Association, Statistical Methods in Imaging (SMI) Annual Meeting will feature three SOCR activities:

• A Spacekime Analytics Tutorial,
• An Invited Special Session on Longitudinal Imaging and Biostatistical Methods, and
• A student paper titled Statistical Foundations of Invariance and Equivariance in Deep Artificial Neural Network Learning, by Yueyang Shen and Yupeng Zhang.

Spacekime Analytics Tutorial

Tutorial Logistics

• Title: Complex-Time Representation of Spatiotemporal Processes and Spacekime Analytics
• Organizer: Ivo Dinov (Michigan)
• Date/Time: Wednesday (May 29, 2024) 8:30am-10:00am US ET
• Venue: JW Marriott Indianapolis, Indianapolis, IN
• Registration: Registration
• Conference: 2024 Statistical Methods in Imaging Conference, Annual Meeting of the ASA Statistics in Imaging Section - Statistical Methods in Imaging (SMI)
• Format: A brief overview lecture followed by hands-on spacekime analytics tutorial and demonstrations.

Abstract

This time-comlexity and inferential uncertainty (TCIU) Spacekime Analytics tutorial will describe the novel complex-time (kime) representation of repeated measurement longitudinal processes, which underlies advanced space-kime statistical inference and space-kime artificial intelligence (AI) applications. By translating fundamental quantum mechanics principles into statistical inference models of time-varying processes, we generalize the classical 4D spatiotemporal sampling to a 5D space-kime manifold, where the phase of complex-time encodes repeated random drawings at fixed spatiotemporal locations. Many AI applications and statistical inference techniques involving temporal data can be formulated in a Bayesian space-kime analytics framework. We explore alternative strategies for translating time-series observations into kime-surfaces, which are richer, computationally tractable, objects amenable to tensor-based linear modeling and model-free inference. Simulated and observed neuroimaging and macroeconomics data will be used to demonstrate applications of space-kime analytics. As time permits, we may discuss the space-kime analytic duality between theoretical model inference, based on generalized functions (distributions), and experimental data inference, based on replicated finite samples as proxy measures of the underlying probability distributions. Several theoretical, experimental, computational, and data-analytic open problems will be presented.

Special Session

This session will include a blend of mathematical, statistical, and computational experts presenting on recent methodological advances to represent, model, predict, synthesize, and analyze large and heterogeneous spatiotemporal imaging data.

Session Logistics

• Title: Longitudinal Imaging and Biostatistical Methods
• Organizers: Ivo Dinov (Michigan), Sharmistha Guha (TAMU), Hossein Moradi (SD State), Ranjan Maitra (Iowa), and Dan Rowe (Marquette)
• Date/Time: Thursday, 5/30/24, 8:30 AM - 10:20 AM US ET
• Venue: JW Marriott Indianapolis, Indianapolis, IN
• Registration: Registration
• Conference: 2024 Statistical Methods in Imaging Conference, Annual Meeting of the ASA Statistics in Imaging Section.
• Session Format: 20+5 minute presentations (staggered).

Session Presenters

• Sharmistha Guha (TAMU)

Title: Supervised Modeling of Heterogeneous Networks: Investigating Functional Connectivity Across Various Cognitive Control Tasks

Abstract: We present a novel Bayesian approach to address limitations in current methods for studying the relationship between functional connectivity across cognitive control domains and cognitive phenotypes. Our integrated framework jointly learns heterogeneous networks with vector-valued predictors, overcoming the constraints of treating each network independently in regression analysis. By assuming shared nodes across networks with varying interconnections, our method captures complex relationships while offering uncertainty quantification. Theoretical analysis demonstrates convergence to the true data-generating density, supported by empirical studies showcasing superior performance over existing approaches.

• Hossein Moradi (SDState)

Title: Tensor Regression for Brain Imaging Data

Abstract: Multidimensional array data, also called tensors, are used in neuroimaging and other big data applications. In this paper, we propose a parsimonious Bayesian Tensor linear model for neuroimaging study with brain image as a response and a vector of predictors. Our method provides estimates for the parameters of interest by using an Envelope method. The proposed method characterizes different sources of uncertainty and the inference is performed using Markov Chain Monte Carlo (MCMC). We demonstrate posterior consistency and develop a computationally efficient MCMC algorithm for posterior computation using Gibbs sampling. The effectiveness of our approach is illustrated through simulation studies and analysis of alcohol addiction's effect on brain connectivity.

• Ranjan Maitra (Iowa State)

Title: ToTTR: Tensor-on-Tensor Times Series Regression for Integrated One-step functional MR Imaging analysis

Abstract: : A functional Magnetic Resonance Imaging (fMRI) activation detection experiment yields a massively structured array- or tensor-variate dataset that is to be analyzed with respect to a set of time-varying stimuli and/or other covariates. The conventional approach employs a two-stage analysis, first fitting a regression time series on the time series data individually at each voxel, thereby reducing each voxel’s time series data to a single statistic, and then following it with a second-stage analysis that incorporates spatial context in detecting the activation regions. We propose a holistic but practical one-step tensor-variate regression modeling of the entire time series dataset that uses low-rank-tensor decompositions on the regression parameters and Kronecker separable formats for the covariance matrices of the error arrays. Our approach obtains maximum likelihood estimators via block relaxation and derives asymptotic distributions for inference. Performance on simulation studies and a Flanker task dataset demonstrate that our approach can reliably identify cerebral regions that are significantly activated, more than the current two-stage setup.

• Dan Rowe (Marquette)

Title: Bayesian k-Space Estimation for fMRI

Abstract: In fMRI, as voxel sizes decrease, there is less tissue to produce a signal, resulting in a decrease in the signal-to-noise ratio and contrast-to-noise ratio. In fMRI, there have been many attempts to decrease the noise in an image in order to increase activation, but most lead to blurrier images. An alternative is to develop methods in spatial frequency space, which have unique benefits. This work proposes a Bayesian approach that quantifies available a priori information about measured complex-valued frequency coefficients. This prior information is incorporated with observed spatial frequency coefficients, and the spatial frequency coefficients estimated a posteriori. The posterior estimated spatial frequency coefficient are inverse Fourier transform reconstructed into images with reduced noise and increased detection power.

Best Student Paper Award

Congratulations to Yueyang Shen and Yupeng Zhang on Co-Winning (along with another student, James Buenfil/Washington) the annual “Theory and Methods Track” Best Student Paper Award of the 2024 American Statistical Association (AmStat) - Statistical Methods in Imaging (SMI) Conference.

This paper Statistical foundations of invariance and equivariance in deep artificial neural network learning was recognized as being of remarkable quality by the AmStat/SMI review committee.

Conference Program

Date	Start	End	Duration (minutes)	Session 1	Session 2
Wednesday 5/29/24	8:30	10:00	90	Tutorial: Complex-time representation of spatiotemporal processes and spacekime analyhtics; Instructor(s): Ivo Dinov; Location: Room 101	Tutorial: Tutorial on Deep learning and generative AI; Instructor(s): Haoda Fu; Location: Room 102
	10:00	10:10	10	Break
	10:10	11:40	90	Tutorial: NiChart: a software tool for building machine learning oriented neuroimaging brain chart; Instructor(s): Haochang Shou Ren Zheng; Location: Room 101	Tutorial: Tutorial on Deep learning and generative AI; Instructor(s): Haoda Fu; Location: Room 102
	11:40	13:10	90	Lunch break
	13:10	14:40	90	Student Paper Competition Winners; Location: Room 101/102
	14:40	14:50	10	Break
	14:50	15:50	60	Keynote - Bin Yu (Chair: Tingting Zhang); Location: Room 101/102
	15:50	18:00	130	Poster Presentations/Mixer (food and drinks offered); Location: Room 103/104
Thursday 5/30/24	8:00	8:30	30	Breakfast
	8:30	10:10	100	Longitudinal imaging and biostatistical methods; Session Organizer: Ivo Dinov; Speakers: Sharmistha Guha Hossein Moradi Ranjan Maitra Dan Rowe; Location: Room 103/104	Expanding neuroimaging research: integrating insights from biomedical sciences, Session Organizer: Jun Young Park; Speakers: Sarah M. Weinstein Andrew An Chen Bingxin Zhao Jun Young Park; Location: Room 102
	10:10	10:20	10	Break
	10:20	11:20	60	Keynote - Andrew J. Saykin (Chair: Sujuan Gao); Location: Room 103/104
	11:20	13:00	100	Lunch break
	13:00	14:15	75	Statistical learning methods for neuroscience; Session Organizer: Shuheng Zhou; Speakers: Jian Kang Chunming Zhang Shuheng Zhou; Location: Room 103/104	Recent developments in statistical methodology for neuroimaging data analysis; Session Organizer: Dayu Sun; Speakers: Xin Ma Shuo Chen Joshua Lukemire; Location: Room 102
	14:15	14:25	10	Break
	14:25	16:05	100	Statistical inference in neuroimaging; Session Organizer: Eardi Lila; Speakers: Benjamin Risk Raphiel Murden Daniel Kessler Simon Vandekar; Location: Room 103/104	New developments for harmonization processing and modeling for imaging data; Session Organizer: Yize Zhao; Speakers: Dana Tudorascu Selena Wang Zhengwu Zhang Tsung-Hung Yao; Location: Room 102
	16:05	16:15	10	Break
	16:15	17:30	75	Invariance and distribution/density objects in neuroimaging studies; Session Organizer: Yi Zhao; Speakers: Bonnie Smith Changbo Zhu Yi Zhao; Location: Room 103/104	Advances in statistical method for neuroimaging data; Session Organizer: Selena Wang; Speakers: Naomi Ding Dayu Sun Selena Wang ; Location: Room 102
Friday 5/31/24	8:00	8:30	30	Breakfast
	8:30	10:10	100	Graph-based network connectomes analysis; Session Organizer: Simon Vandekar; Speakers: Eardi Lila Sean L. Simpson Panpan Zhang Tingting Zhang; Location: Room 103/104	Statistical methods for dissecting tumor microenvironment based on spatial proteomics datasets; Session Organizer: Souvik Seal; Speakers: Thao Vu Jiangmei Xiong Julia Wrobel Junsouk Choi; Location: Room 102
	10:10	10:20	10	Break
	10:20	11:20	60	Keynote - Robert E. Kass (Chair: Daniel Rowe); Location: Room 103/104
	11:20	13:00	100	Lunch break
	13:00	14:40	100	When machine learning and generative models meet imaging network and point cloud data; Session Organizer: Zhengwu Zhang; Speakers: Mingxia Liu Maoran Xu Yuexuan Wu Xinyi Li; Location: Room 103/104	Novel statistical inference methods with applications; Session Organizer: Julia Fisher; Speakers: Fatma Parlak Daniel Adrian Yueyang Shen Jose Rodriguez-Acosta; Location: Room 102
	14:40	14:50	10	Break
	14:50	16:30	100	Frontiers in medical imaging: harnessing artificial intelligence and statistical analysis for breakthrough insights; Session Organizer: Lei Liu; Speakers: Yize Zhao Yifan Peng Lei Liu Haoda Fu; Location: Room 103/104
	16:30	16:40	10	Closing remarks; Location: Room 103/104

---

---

---

Translate this page:

(default)	Deutsch	Español	Français	Italiano	Português	日本語	България	الامارات العربية المتحدة	Suomi	इस भाषा में	Norge
한국어	中文	繁体中文	Русский	Nederlands	Ελληνικά	Hrvatska	Česká republika	Danmark	Polska	România	Sverige