Wednesday, Aug 7: 8:30 AM - 10:20 AM
5143
Contributed Papers
Oregon Convention Center
Room: CC-E142
Main Sponsor
Section on Statistics in Imaging
Presentations
FMRI has been a powerful and safe medical imaging tool to study the function of the brain by demonstrating the spatial and temporal changes in brain metabolism in recent decades. To capture brain functionality more efficiently, efforts have been made to accelerate the number of images acquired per unit of time that create each volume image without losing full anatomical structure. The Simultaneous Multi-Slice (SMS) technique provides an alternative reconstruction method where multiple slices are acquired and aliased concurrently. Traditional imaging techniques such as SENSE and GRAPPA can reconstruct an image from less measured data but have their drawbacks. Controlled Aliasing in Parallel Imaging (CAIPI) shifts is a technique where the field-of-view is shifted during image acquisition. We present a novel SMS technique called mSPECS-CAIPI with Through-Plane and In-Plane Acceleration. It combines the image shift method of CAIPI, the CAIPI with view angle tilting technique, and Hadamard phase-encoding. Our proposed approach was applied to a simulation study with preliminary results showing a decrease in the influence of the geometry factor while increasing brain activation detection.
Keywords
fMRI
SMS
Through-Plane
In-Plane
CAIPI
In tumor immunology, clinical regimes corresponding to different stages of disease or responses to treatment may manifest as different spatial arrangements of tumor and immune cells. Spatial point pattern (SPP) modeling can be used to segment tissue images according to these regimes. To this end, we propose a two-stage approach: first, local intensities and pair correlation functions (PCF) are estimated from the SPP of cells within each image, and the PCFs are reduced in dimension via spectral decomposition of the covariance function. Second, the estimates are clustered in a Bayesian hierarchical model with spatially-dependent cluster labels. The clusters correspond to regimes of interest that are present across subjects; the cluster labels segment the images according to those regimes. Through Markov Chain Monte Carlo (MCMC) sampling, we jointly estimate and quantify uncertainty in the cluster assignment and spatial characteristics of each cluster. The number of clusters is found through cross-validation. Simulations demonstrate the performance of the method, and it is applied to a set of multiplex immunofluorescence images of pancreatic tissue.
Keywords
Bayesian mixture model
Biomedical imaging
Functional data analysis
Tumor immunology
MCMC
Spatial point pattern
This paper uses sample data to study the problem of comparing populations on finite-dimensional parallelizable Riemannian manifolds and more general trivial vector bundles. Utilizing triviality, our framework represents populations as mixtures of Gaussians on vector bundles and estimates the population parameters using a mode-based clustering algorithm. We derive a Wasserstein-type metric between Gaussian mixtures, adapted to the manifold geometry, in order to compare estimated distributions. Our contributions include an identifiability result for Gaussian mixtures on manifold domains and a convenient characterization of optimal couplings of Gaussian mixtures under the derived metric. We demonstrate these tools on some example domains, including the pre-shape space of planar closed curves, with applications to the shape space of triangles and populations of nanoparticles. In the nanoparticle application, we consider a sequence of populations of particle shapes arising from a manufacturing process, and utilize the Wasserstein-type distance to perform change-point detection.
Keywords
Optimal Transport
Differential Geometry
Statistical Shape Analysis
Abstracts
A deep learning algorithm is implemented to identify building footprints in satellite or arial imagery. A Mask Region-Based Convolutional Neural Network (Mask R-CNN) was trained and tested for detection of residential buildings. Annotated dataset for training was generated by sketching bounding boxes across the buildings. Resnet50 was used as the backbone for transfer learning in the model for detection of building footprints. The dataset for re-training and fine-tuning of the transfer network was the 2024 Bay County building footprints for annotation of the 2022 NAIP images taken over Panama City, Florida. The training data was created by making 2851 image chips of size 256 x 256 from the original image using the Bay County footprints as the labels. The learning rate for the model was 1.0000e-04 with an Average Precision Score of 0.72. It was then tested on images in Mexico Beach and other areas of Panama City for a final test and the results were promising. The unregularized footprints show good agreement with the current image used for inference. Looking at the confidence in the predictions, the lowest level recorded in the attribute table was 0.93.
Keywords
GIS
Artificial Intelligence
Satellite Imagery
Building Footprint
Object Detection
Georeferencing
Digital pathology is a fast-growing field where leveraging machine learning methods uncovers meaningful imaging features, but it faces the hurdles of sparse annotations, particularly for small pathology image segments. We propose a novel approach that employs spatially resolved transcriptomic data for annotations, though it faces challenges like annotation uncertainty from transcriptomic data and inconsistent image resolutions. We established the viability of this approach and developed a novel transfer-learning neural network model, STpath (Spatial Transcriptomics and pathology images), designed to predict cell type proportions or classify tumor microenvironments. Our findings revealed the intrinsic link between pre-trained deep learning features and cell identities in pathology image segments. Tested on two breast cancer datasets, STpath demonstrated robust performance, effectively handling samples with diverse cell type proportions and high-resolution images despite limited training data. As the influx of spatially resolved transcriptomic data continues, we foresee ongoing updates to STpath, shaping it into an invaluable AI tool for pathologists, enhancing diagnostic accuracy.
Keywords
Digital and computational pathology
Whole slide imaging
Spatially resolved transcriptomics
Artificial Intelligence
Transfer learning
Cell type proportion and tumor microenvironment
We present improved extrinsic energy tests for projective shape analyses. Our methods make use of novel embeddings for projective shape space and their tangential components data in place of the embedded sample data such as was previously considered in Guo, et al. (2023). We compare our novel methodologies with those based on embedded sample data via simulation studies and consider a real-life application of our methodology.
Keywords
extrinsic energy tests
projective shape analysis
tangential components
Microstructural lung damage is the pivotal cause of morbidity and mortality in patients with Cystic fibrosis (CF), a life-shortening genetic disorder. Detection of such lung abnormalities by examining the microstructural changes from Hyperpolarized Xe-129 MRI, are often done by calculating parameters such as apparent diffusion coefficient (ADC). We examined the spatial distribution of ADC parameter to explain the microstructural differences between healthy controls and CF patients.
Using DW-MRI images from 38 healthy controls (age: 17.2 ±9.5 year) and 39 CF patients (age: 15.28±7.62 year), we compared the spatial characteristics of 129Xe ADC in CF patients to healthy controls. Upon doing this, two random effects for the spatial and nonspatial variations in ADC maps were introduced. The prior distribution for the spatial random effect was specified using the conditional autoregressive model. This helps in understanding the microstructural changes in the lungs of CF patients by looking at the ADC map and the voxel level spatial map along with patient level spatial autocorrelation in comparison to healthy controls. The findings will be presented in the meeting.
Keywords
Conditional autoregressive model
Cystic Fibrosis
apparent diffusion coefficient
MRI images
Co-Author(s)
A. Bdaiwi, CPIR, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States
Marepalli Rao, University of Cincinnati
Z.I. Cleveland, CPIR, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States
Md. M. Hossain, Cincinnati Children Hospital medical center
First Author
Neelakshi Chatterjee
Presenting Author
Neelakshi Chatterjee