Merge pull request #3 from MedVIC-Lab/test_KI

Added publications and profile

pages/people/iyerkrithika.md

@@ -0,0 +1,22 @@
+---
+layout: person
+name: "Krithika Iyer"
+role: "PhD Student" 
+title: "PhD Candidate" # e.g., "PhD Student", "MS Student", "Staff", "Researcher", "Alumni"
+org: "University of Utah, SCI Institute"
+avatar: "iyerkrithika.jpg" # Replace with the URL to your avatar image
+links:
+  - icon: "github"
+    link: "https://github.com/iyerkrithika21" # Replace with your GitHub profile link
+  - icon: "twitter"
+    link: "https://twitter.com/iyerkrithika21" # Replace with your Twitter profile link
+  - icon: "website"
+    link: "https://www.sci.utah.edu/~iyerkrithika/" # Replace with your personal website link
+---
+
+# About Krithika Iyer
+
+I'm currently a Ph.D. candidate at the Scientific Computing and Imaging Institute, University of Utah, working under the guidance of Dr. Shireen Elhabian. Prior to this, I earned my Bachelor of Engineering from Maharashtra Institute of Technology, University of Pune. After completing my undergraduate studies, I gained valuable experience as an Associate System Engineer at IBM Global Business Services. 
+
+My research focuses on machine learning, probabilistic modeling, deep learning, and statistical shape modeling. I am particularly passionate about exploring the applications of these areas in healthcare, aiming to contribute to advancements in diagnosis and treatment. 
+

pages/publications/adassm.md

@@ -0,0 +1,19 @@
+---
+title: "ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images"
+authors: "Mokshagna Sai Teja Karanam, Tushar Kataria, , Krithika Iyer, Shireen Elhabian. "
+conference: "Shape in Medical Imaging (ShapeMI) at MICCAI"
+year: "2023"
+link: "https://arxiv.org/abs/2307.03273"
+image:
+  src: "adassm.png"
+  alt: Results Highlight
+---
+
+# ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images
+This paper introduces a novel strategy for on-
+the-fly data augmentation for the Image-to-SSM framework by leveraging
+data-dependent noise generation or texture augmentation. The proposed
+framework is trained as an adversary to the Image-to-SSM network, aug-
+menting diverse and challenging noisy samples. Our approach achieves
+improved accuracy by encouraging the model to focus on the underlying
+geometry rather than relying solely on pixel values.

pages/publications/benchmarking.md

@@ -0,0 +1,14 @@
+---
+title: "Benchmarking Off-the-shelf Statistical Shape Modeling Tools in Clinical Applications"
+authors: "Anupama Goparaju, Krithika Iyer, Alexandre Bône, Nan Hu, Heath B. Henninger, Andrew E. Anderson, Stanley Durrleman, Matthijs Jacxsens, Alan Morris, Ibolya Csecs, Nassir Marrouche, Shireen Y. Elhabian"
+conference: "Medical Image Analysis"
+year: "2021"
+link: "https://www.sciencedirect.com/science/article/pii/S1361841521003169"
+image:
+  src: "benchmarking.jpg"
+  alt: Benchmarking FrameWork
+---
+
+# Benchmarking Off-the-shelf Statistical Shape Modeling Tools in Clinical Applications
+
+Current evaluations predominantly focus on non-clinical domains, leaving a gap in understanding the applicability of SSM techniques in real-world clinical scenarios. We aim to conduct comprehensive evaluation and validation studies to assess the precision and reliability of SSM tools for clinical tasks such as landmark/measurement estimation and lesion screening across multiple datasets.

pages/publications/benchmarking_segmentation.md

@@ -0,0 +1,13 @@
+---
+title: "Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation"
+authors: "Jadie Adams, Shireen Elhabian"
+conference: "Unsure Workshop at MICCAI"
+year: "2023"
+link: "https://arxiv.org/abs/2308.07506"
+image:
+  src: "benchmarking_segmentation.png"
+  alt: Results Highlight
+---
+
+# Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation
+VIB is only half-Bayesian and lacks epistemic uncertainty inference. We derive a fully Bayesian VIB formulation and demonstrate the efficacy of two scalable implementation approaches: concrete dropout and batch ensemble. Additionally, we introduce a novel combination of the two that further enhances uncertainty calibration via multimodal marginalization. Experiments on synthetic shapes and left atrium data demonstrate that the fully Bayesian VIB network predicts SSM from images with improved uncertainty reasoning without sacrificing accuracy.

pages/publications/bvib_deepssm.md

@@ -0,0 +1,13 @@
+---
+title: "Fully Bayesian VIB DeepSSM"
+authors: "Jadie Adams, Shireen Elhabian"
+conference: "MICCAI"
+year: "2023"
+link: "https://arxiv.org/pdf/2305.05797.pdf"
+image:
+  src: "bvib_deepssm.png"
+  alt: Results Highlight
+---
+
+# Fully Bayesian VIB DeepSSM
+VIB is only half-Bayesian and lacks epistemic uncertainty inference. We derive a fully Bayesian VIB formulation and demonstrate the efficacy of two scalable implementation approaches: concrete dropout and batch ensemble. Additionally, we introduce a novel combination of the two that further enhances uncertainty calibration via multimodal marginalization. Experiments on synthetic shapes and left atrium data demonstrate that the fully Bayesian VIB network predicts SSM from images with improved uncertainty reasoning without sacrificing accuracy.

pages/publications/can_pointclouds.md

@@ -0,0 +1,13 @@
+---
+title: "Can point cloud networks learn statistical shape models of anatomies?"
+authors: "Jadie Adams, Shireen Elhabian"
+conference: "MICCAI"
+year: "2023"
+link: "https://arxiv.org/abs/2305.05610"
+image:
+  src: "can_pointclouds.png"
+  alt: Results Highlight
+---
+
+# Can point cloud networks learn statistical shape models of anatomies?
+Point cloud deep networks have recently achieved remarkable success in learning permutation-invariant features for different point cloud tasks (e.g., completion, semantic segmentation, classification). However, their application to learning SSM from point clouds is to-date unexplored. In this work, we demonstrate that existing point cloud encoder-decoder-based completion networks can provide an untapped potential for SSM, capturing population-level statistical representations of shapes while reducing the inference burden and relaxing the input requirement. We discuss the limitations of these techniques to the SSM application and suggest future improvements. Our work paves the way for further exploration of point cloud deep learning for SSM, a promising avenue for advancing shape analysis literature and broadening SSM to diverse use cases. 

pages/publications/frontiers_sharedboundary.md

@@ -0,0 +1,16 @@
+---
+title: "Statistical Shape Modeling of Multi-Organ Anatomies with Shared Boundaries: A Data-Driven Approach"
+authors: "Krithika Iyer, Alan Morris, Brian Zenger, Karthik Karnath, Nawazish Khan, Benjamin A. Orkild, Oleksandre Korshak, Shireen Elhabian"
+conference: "Frontiers in Bioengineering and Biotechnology"
+year: "2023"
+link: "https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.1078800/full"
+image:
+  src: "frontiers_shared.jpg"
+  alt: Results Highlight
+---
+
+# Statistical Shape Modeling of Multi-Organ Anatomies with Shared Boundaries: A Data-Driven Approach
+
+This work focuses on particle-based shape modeling (PSM), a state-of-art SSM approach for building shape models by optimizing the position of correspondence particles. The proposed PSM strategy for handling shared boundaries entails (a) detecting and extracting the shared boundary surface and contour (outline of the surface mesh/isoline) of the meshes of the two organs, (b) followed by a formulation for a correspondence-based optimization algorithm to build a multi-organ anatomy statistical shape model that captures morphological and alignment changes of individual organs and their shared boundary surfaces throughout the population.
+
+We demonstrate the shared boundary pipeline using a toy dataset of parameterized shapes and a clinical dataset of the biventricular heart models. The shared boundary model for the cardiac biventricular data achieves consistent parameterization of the shared surface (interventricular septum) and identifies the curvature of the interventricular septum as pathological shape differences.

pages/publications/frontiers_spatiotemporal_ssm.md

@@ -0,0 +1,14 @@
+---
+title: "Learning Spatiotemporal Statistical Shape Models for Non-Linear Dynamic Anatomies"
+authors: "Jadie Adams, Nawazish Khan, Alan Morris, Shireen Elhabian"
+conference: "Frontiers in Bioengineering and Biotechnology"
+year: "2023"
+link: "https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2023.1086234/full"
+image:
+  src: "frontiers_spatiotemporal_ssm.jpg"
+  alt: Results Highlight
+---
+
+# Learning Spatiotemporal Statistical Shape Models for Non-Linear Dynamic Anatomies
+
+We present a principled approach to spatiotemporal SSM that relaxes these assumptions to correctly capture population-level shape variation over time. We propose to incorporate modeling the underlying time dependency into correspondence optimization via a regularized principal component polynomial regression. This approach is flexible enough to capture non-linear temporal dynamics while encoding population-specific spatial regularity. We demonstrate our method’s efficacy on synthetic data and left atrium segmented from cardiac MRI scans. Our approach better captures the population modes of variation and a statistically significant time dependency than existing methods.

pages/publications/mesh2ssm.md

@@ -0,0 +1,14 @@
+---
+title: "Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy"
+authors: "Krithika Iyer  and Shireen Elhabian"
+conference: "MICCAI 2023"
+year: "2023"
+link: "https://scholar.google.com/citations?view_op=view_citation&hl=en&user=MN0NWL0AAAAJ&citation_for_view=MN0NWL0AAAAJ:W7OEmFMy1HYC"
+image:
+  src: "mesh2ssm.png"
+  alt: Mesh2SSM Model
+---
+
+# Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy
+
+Substantial non-linear variability in human anatomy often makes the traditional shape modeling process challenging. Deep learning techniques have the potential to learn complex nonlinear representations of shapes and generate statistical shape models more faithful to the underlying population-level variability. This work aims to predict correspondences from meshes in an unsupervised manner. This approach seeks to overcome the limitations associated with linearity assumption and computationally intensive inference pipelines.

pages/publications/point2ssm.md

@@ -0,0 +1,14 @@
+---
+title: "Point2SSM: Learning Morphological Variations of Anatomies from Point Cloud"
+authors: "Jadie Adams, Shireen Elhabian"
+conference: "ICLR"
+year: "2024"
+link: "https://arxiv.org/abs/2305.14486"
+image:
+  src: "point2ssm.png"
+  alt: Results Highlight
+---
+
+# Point2SSM: Learning Morphological Variations of Anatomies from Point Cloud
+Traditional methods of SSM construction have limitations, including the requirement of noise-free surface meshes or binary volumes, reliance on assumptions or templates, and prolonged inference times due to simultaneous optimization of the entire cohort. Point2SSM overcomes these barriers by providing a data-driven solution that infers SSMs directly from raw point clouds, reducing inference burdens and increasing applicability as point clouds are more easily acquired. While deep learning on 3D point clouds has seen success in unsupervised representation learning and shape correspondence, its application to anatomical SSM construction is largely unexplored. We conduct a benchmark of state-of-the-art point cloud deep networks on the SSM task, revealing their limited robustness to clinical challenges such as noisy, sparse, or incomplete input and limited training data. Point2SSM addresses these issues through an attention-based module, providing effective correspondence mappings from learned point features. Our results demonstrate that the proposed method significantly outperforms existing networks in terms of accurate surface sampling and correspondence, better capturing population-level statistics. 
+

pages/publications/rvtr.md

@@ -0,0 +1,15 @@
+---
+title: "All Roads Lead to Rome: Diverse Etiologies of Tricuspid Regurgitation Create a Predictable Constellation of Right Ventricular Shape Changes"
+authors: "Benjamin A. Orkild, Brian Zenger*, Krithika Iyer*,
+Lindsay C. Rupp, Masjid M. Ibrahim, Atefeh G. Khashani, Maura D. Perez, Markus D. Foote, Jake A. Bergquist, Alan K. Morris, Shireen Elhabian and others"
+conference: "Frontiers in Physiology"
+year: "2022"
+link: "https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.908552/full"
+image:
+  src: "rvtr.jpg"
+  alt: Results Highlight
+---
+
+# All Roads Lead to Rome: Diverse Etiologies of Tricuspid Regurgitation Create a Predictable Constellation of Right Ventricular Shape Changes
+
+We demonstrate the effectiveness of SSM in identifying and quantifying morphological changes indicative of pathology. 

pages/publications/scorp.md

@@ -0,0 +1,13 @@
+---
+title: "SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images"
+authors: "Krithika Iyer, Jadie Adams, Shireen Elhabian. "
+conference: "Medical Image Understanding and Analysis (MIUA)"
+year: "2024"
+link: "https://arxiv.org/abs/2404.17967"
+image:
+  src: "scorp.jpg"
+  alt: Results Highlight
+---
+
+# SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images
+Existing deep learning methods for estimating correspondences from CT/MRI images rely heavily on established PDMs for training, limiting their applicability and generalization. Moreover, volumetric images could contain misleading information, effectively regularizing the correspondence estimation process becomes critical for precise feature extraction. This work proposes an approach to predict correspondences directly from raw images without relying on pre-optimized PDMs, leveraging shape prior built from surface representations like meshes, point clouds, or segmentations to guide the image-driven SSM task to learn predictive features.

pages/publications/sharedboundary.md

@@ -0,0 +1,15 @@
+---
+title: "Statistical Shape Modeling of Biventricular Anatomy with Shared Boundaries"
+authors: "Krithika Iyer, Alan Morris, Brian Zenger, Karthik Karnath, Benjamin A. Orkild, Oleksandre Korshak, Shireen Elhabian. "
+conference: "Statistical Atlases and Computational Models of the Heart (STACOM) at MICCAI"
+year: "2022"
+link: "https://pmc.ncbi.nlm.nih.gov/articles/PMC10103081/"
+image:
+  src: "stacom_shared.jpg"
+  alt: Results Highlight
+---
+
+# Statistical Shape Modeling of Biventricular Anatomy with Shared Boundaries
+
+
+The unique shape changes of the complex anatomical structures consisting of multiple organs with a shared boundary are not captured when the organs are modeled individually. Therefore, this work aims to develop (a) simple and effective shape modeling tools for extracting shared boundary surfaces and (b) a correspondence-based optimization scheme to parameterize multi-organ anatomies and their shared surfaces consistently.

pages/publications/spatiotemporal_ssm.md

@@ -0,0 +1,14 @@
+---
+title: "Spatiotemporal Cardiac Statistical Shape Modeling: A Data-Driven Approach"
+authors: "Jadie Adams, Nawazish Khan, Alan Morris, Shireen Elhabian"
+conference: "Statistical Atlases and Computational Models of the Heart (STACOM) at MICCAI"
+year: "2022"
+link: "https://arxiv.org/abs/2209.02736"
+image:
+  src: "spatiotemporal_ssm.png"
+  alt: Results Highlight
+---
+
+# Spatiotemporal Cardiac Statistical Shape Modeling: A Data-Driven Approach
+
+Existing methods for modeling spatiotemporal or longitudinal shape changes require predefined shape atlases and pre-built shape models that are typically constructed cross-sectionally. This paper proposes a data-driven approach inspired by the PSM method to learn population-level spatiotemporal shape changes directly from shape data. We introduce a novel SSM optimization scheme that produces landmarks that are in correspondence both across the population (inter-subject) and across time-series (intra-subject). We apply the proposed method to 4D cardiac data from atrial-fibrillation patients and demonstrate its efficacy in representing the dynamic change of the left atrium. Furthermore, we show that our method outperforms an image-based approach for spatiotemporal SSM with respect to a generative time-series model, the Linear Dynamical System (LDS). LDS fit using a spatiotemporal shape model optimized via our approach provides better generalization and specificity, indicating it accurately captures the underlying time-dependency. 

pages/publications/spicorrnet.md

@@ -0,0 +1,13 @@
+---
+title: "Probabilistic 3D Correspondence Prediction from Sparse Unsegmented Images"
+authors: "Krithika Iyer, Shireen Elhabian. "
+conference: "Machine Learning in Medical Imaging Workshop (MLMI) at MICCAI"
+year: "2024"
+link: "https://arxiv.org/abs/2407.01931"
+image:
+  src: "spicorrnet.jpg"
+  alt: Results Highlight
+---
+
+# Probabilistic 3D Correspondence Prediction from Sparse Unsegmented Images
+Despite its utility, the conventional SSM construction pipeline is often complex and time-consuming. Additionally, reliance on linearity assumptions further limits the model from capturing clinically relevant variations. Recent advancements in deep learning solutions enable the direct inference of SSM from unsegmented medical images, streamlining the process and improving accessibility. However, the new methods of SSM from images do not adequately account for situations where the imaging data quality is poor or where only sparse information is available. Moreover, quantifying aleatoric uncertainty, which represents inherent data variability, is crucial in deploying deep learning for clinical tasks to ensure reliable model predictions and robust decision-making, especially in challenging imaging conditions. Therefore, we propose SPI-CorrNet, a unified model that predicts 3D correspondences from sparse imaging data. It leverages a teacher network to regularize feature learning and quantifies data-dependent aleatoric uncertainty by adapting the network to predict intrinsic input variances. Experiments on the LGE MRI left atrium dataset and Abdomen CT-1K liver datasets demonstrate that our technique enhances the accuracy and robustness of sparse image-driven SSM. 

pages/publications/uncertain_deepssm.md

@@ -0,0 +1,13 @@
+---
+title: "Uncertain-DeepSSM: From Images to Probabilistic Shape Models"
+authors: "Jadie Adams, Riddhish Bhalodia, Shireen Elhabian. "
+conference: "Shape in Medical Imaging (ShapeMI) at MICCAI"
+year: "2020"
+link: "https://arxiv.org/abs/2007.06516"
+image:
+  src: "uncertain_deepssm.png"
+  alt: Results Highlight
+---
+
+# Uncertain-DeepSSM: From Images to Probabilistic Shape Models
+We propose Uncertain-DeepSSM as a unified model that quantifies both, data-dependent aleatoric uncertainty by adapting the network to predict intrinsic input variance, and model-dependent epistemic uncertainty via a Monte Carlo dropout sampling to approximate a variational distribution over the network parameters. Experiments show an accuracy improvement over DeepSSM while maintaining the same benefits of being end-to-end with little pre-processing. 

pages/publications/vib_deepssm.md

@@ -0,0 +1,13 @@
+---
+title: "From Images to Probabilistic Anatomical Shapes: A Deep Variational Bottleneck Approach"
+authors: "Jadie Adams, Shireen Elhabian"
+conference: "MICCAI"
+year: "2022"
+link: "https://arxiv.org/abs/2205.06862"
+image:
+  src: "vib_deepssm.png"
+  alt: Results Highlight
+---
+
+# From Images to Probabilistic Anatomical Shapes: A Deep Variational Bottleneck Approach
+In this paper, we propose a principled framework based on the variational information bottleneck theory to relax these assumptions while predicting probabilistic shapes of anatomy directly from images without supervised encoding of shape descriptors. Here, the latent representation is learned in the context of the learning task, resulting in a more scalable, flexible model that better captures data non-linearity. Additionally, this model is self-regularized and generalizes better given limited training data. Our experiments demonstrate that the proposed method provides improved accuracy and better calibrated aleatoric uncertainty estimates than state-of-the-art methods.