Riddhish Bhalodia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Riddhish Bhalodia has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Shireen Elhabian
University of Utah
6 shared publications Ladislav Kavan
School of Computing, 50 Central Campus Dr, University of Utah, Salt Lake City, UT 84112, USA
3 shared publications- Jadie Adams
University of Utah
2 shared publications Ross Whitaker
Scientific Computing and Imaging Institute, 72 Central Campus Dr, University of Utah, Salt Lake City, UT 84112, USA; School of Computing, 50 Central Campus Dr, University of Utah, Salt Lake City, UT 84112, USA
2 shared publicationsAlan Morris
Division of Cardiovascular Medicine, School of Medicine, University of Utah, Salt Lake City, Utah, USA
1 shared publicationArchanasri Subramanian
Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah, USA
1 shared publication
Latest Publications
- 17 November 2023
- Published by Elsevier in Medical Image Analysis
- Vol. 91, 103034
DeepSSM: A blueprint for image-to-shape deep learning models
- 17 November 2023
- Published by Elsevier in Medical Image Analysis
- Vol. 91, 103034
DeepSSM: A blueprint for image-to-shape deep learning models
- 1 October 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 73, 102157
Leveraging unsupervised image registration for discovery of landmark shape descriptor
- 1 October 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 73, 102157
Leveraging unsupervised image registration for discovery of landmark shape descriptor
- 25 February 2021
- Published by Springer Nature
- Vol. 12625, 643-660
dpVAEs: Fixing Sample Generation for Regularized VAEs
Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objective, VAEs fail to learn useful representations amenable for downstream tasks. Regularization-based methods that attempt to improve the representation learning aspect of VAEs come at a price: poor sample generation. In this paper, we explore this representation-generation trade-off for regularized VAEs and introduce a new family of priors, namely decoupled priors, or dpVAEs, that decouple the representation space from the generation space. This decoupling enables the use of VAE regularizers on the representation space without impacting the distribution used for sample generation, and thereby reaping the representation learning benefits of the regularizations without sacrificing the sample generation. dpVAE leverages invertible networks to learn a bijective mapping from an arbitrarily complex representation distribution to a simple, tractable, generative distribution. Decoupled priors can be adapted to the state-of-the-art VAE regularizers without additional hyperparameter tuning. We showcase the use of dpVAEs with different regularizers. Experiments on MNIST, SVHN, and CelebA demonstrate, quantitatively and qualitatively, that dpVAE fixes sample generation and improves representation for regularized VAEs.
- 25 February 2021
- Published by Springer Nature
- Vol. 12625, 643-660
dpVAEs: Fixing Sample Generation for Regularized VAEs
Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objective, VAEs fail to learn useful representations amenable for downstream tasks. Regularization-based methods that attempt to improve the representation learning aspect of VAEs come at a price: poor sample generation. In this paper, we explore this representation-generation trade-off for regularized VAEs and introduce a new family of priors, namely decoupled priors, or dpVAEs, that decouple the representation space from the generation space. This decoupling enables the use of VAE regularizers on the representation space without impacting the distribution used for sample generation, and thereby reaping the representation learning benefits of the regularizations without sacrificing the sample generation. dpVAE leverages invertible networks to learn a bijective mapping from an arbitrarily complex representation distribution to a simple, tractable, generative distribution. Decoupled priors can be adapted to the state-of-the-art VAE regularizers without additional hyperparameter tuning. We showcase the use of dpVAEs with different regularizers. Experiments on MNIST, SVHN, and CelebA demonstrate, quantitatively and qualitatively, that dpVAE fixes sample generation and improves representation for regularized VAEs.
- 3 October 2020
- Published by Springer Nature
- Vol. 12474, 57-72
Uncertain-DeepSSM: From Images to Probabilistic Shape Models
Statistical shape modeling (SSM) has recently taken advantage of advances in deep learning to alleviate the need for a time-consuming and expert-driven workflow of anatomy segmentation, shape registration, and the optimization of population-level shape representations. DeepSSM is an end-to-end deep learning approach that extracts statistical shape representation directly from unsegmented images with little manual overhead. It performs comparably with state-of-the-art shape modeling methods for estimating morphologies that are viable for subsequent downstream tasks. Nonetheless, DeepSSM produces an overconfident estimate of shape that cannot be blindly assumed to be accurate. Hence, conveying what DeepSSM does not know, via quantifying granular estimates of uncertainty, is critical for its direct clinical application as an on-demand diagnostic tool to determine how trustworthy the model output is. Here, 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.
- 3 October 2020
- Published by Springer Nature
- Vol. 12474, 57-72
Uncertain-DeepSSM: From Images to Probabilistic Shape Models
Statistical shape modeling (SSM) has recently taken advantage of advances in deep learning to alleviate the need for a time-consuming and expert-driven workflow of anatomy segmentation, shape registration, and the optimization of population-level shape representations. DeepSSM is an end-to-end deep learning approach that extracts statistical shape representation directly from unsegmented images with little manual overhead. It performs comparably with state-of-the-art shape modeling methods for estimating morphologies that are viable for subsequent downstream tasks. Nonetheless, DeepSSM produces an overconfident estimate of shape that cannot be blindly assumed to be accurate. Hence, conveying what DeepSSM does not know, via quantifying granular estimates of uncertainty, is critical for its direct clinical application as an on-demand diagnostic tool to determine how trustworthy the model output is. Here, 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.
- Open Access
dpVAEs: Fixing Sample Generation for Regularized VAEs
Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objective, VAEs fail to learn useful representations amenable for downstream tasks. Regularization-based methods that attempt to improve the representation learning aspect of VAEs come at a price: poor sample generation. In this paper, we explore this representation-generation trade-off for regularized VAEs and introduce a new family of priors, namely decoupled priors, or dpVAEs, that decouple the representation space from the generation space. This decoupling enables the use of VAE regularizers on the representation space without impacting the distribution used for sample generation, and thereby reaping the representation learning benefits of the regularizations without sacrificing the sample generation. dpVAE leverages invertible networks to learn a bijective mapping from an arbitrarily complex representation distribution to a simple, tractable, generative distribution. Decoupled priors can be adapted to the state-of-the-art VAE regularizers without additional hyperparameter tuning. We showcase the use of dpVAEs with different regularizers. Experiments on MNIST, SVHN, and CelebA demonstrate, quantitatively and qualitatively, that dpVAE fixes sample generation for regularized VAEs.
Open AccessdpVAEs: Fixing Sample Generation for Regularized VAEs
Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objective, VAEs fail to learn useful representations amenable for downstream tasks. Regularization-based methods that attempt to improve the representation learning aspect of VAEs come at a price: poor sample generation. In this paper, we explore this representation-generation trade-off for regularized VAEs and introduce a new family of priors, namely decoupled priors, or dpVAEs, that decouple the representation space from the generation space. This decoupling enables the use of VAE regularizers on the representation space without impacting the distribution used for sample generation, and thereby reaping the representation learning benefits of the regularizations without sacrificing the sample generation. dpVAE leverages invertible networks to learn a bijective mapping from an arbitrarily complex representation distribution to a simple, tractable, generative distribution. Decoupled priors can be adapted to the state-of-the-art VAE regularizers without additional hyperparameter tuning. We showcase the use of dpVAEs with different regularizers. Experiments on MNIST, SVHN, and CelebA demonstrate, quantitatively and qualitatively, that dpVAE fixes sample generation for regularized VAEs.
- 30 December 2019
- Published by Computing in Cardiology in Computing in cardiology
- Vol. 46
Does Alignment in Statistical Shape Modeling of Left Atrium Appendage Impact Stroke Prediction?
Evidence suggests that the shape of left atrium appendages (LAA) is a primary indicator in predicting stroke for patients diagnosed with atrial fibrillation (AF). Statistical shape modeling tools used to represent (i.e., parameterize) the underlying LAA variability are of crucial importance to learn shape-based predictors of stroke. Most shape modeling techniques use some form of alignment either as a data pre-processing step or during the modeling step. However, the LAA is a joint anatomy along with left atrium (LA), and the relative position and alignment plays a crucial part in determining risk of stroke. In this paper, we explore different alignment strategies for statistical shape modeling and how each strategy affects the stroke prediction capability. This allows for identifying a unified approach of alignment while analyzing the LAA anatomy for stroke. Here, we study three different alignment strategies, (i) global alignment, (ii) global translational alignment and (iii) cluster based alignment. Our results show that alignment strategies that take into account LAA orientation, i.e., (ii), or the inherent natural clustering of the population under study, i.e., (iii), provide significant improvement over global alignment in both qualitative as well as quantitative measures.
- 30 December 2019
- Published by Computing in Cardiology in Computing in cardiology
- Vol. 46
Does Alignment in Statistical Shape Modeling of Left Atrium Appendage Impact Stroke Prediction?
Evidence suggests that the shape of left atrium appendages (LAA) is a primary indicator in predicting stroke for patients diagnosed with atrial fibrillation (AF). Statistical shape modeling tools used to represent (i.e., parameterize) the underlying LAA variability are of crucial importance to learn shape-based predictors of stroke. Most shape modeling techniques use some form of alignment either as a data pre-processing step or during the modeling step. However, the LAA is a joint anatomy along with left atrium (LA), and the relative position and alignment plays a crucial part in determining risk of stroke. In this paper, we explore different alignment strategies for statistical shape modeling and how each strategy affects the stroke prediction capability. This allows for identifying a unified approach of alignment while analyzing the LAA anatomy for stroke. Here, we study three different alignment strategies, (i) global alignment, (ii) global translational alignment and (iii) cluster based alignment. Our results show that alignment strategies that take into account LAA orientation, i.e., (ii), or the inherent natural clustering of the population under study, i.e., (iii), provide significant improvement over global alignment in both qualitative as well as quantitative measures.
- 10 October 2019
- Published by Springer Nature
- Vol. 11765, 391-400
A Cooperative Autoencoder for Population-Based Regularization of CNN Image Registration
Spatial transformations are enablers in a variety of medical image analysis applications that entail aligning images to a common coordinate systems. Population analysis of such transformations is expected to capture the underlying image and shape variations, and hence these transformations are required to produce anatomically feasible correspondences. This is usually enforced through some smoothness-based generic metric or regularization of the deformation field. Alternatively, population-based regularization has been shown to produce anatomically accurate correspondences in cases where anatomically unaware (i.e., data independent) regularization fail. Recently, deep networks have been used to generate spatial transformations in an unsupervised manner, and, once trained, these networks are computationally faster and as accurate as conventional, optimization-based registration methods. However, the deformation fields produced by these networks require smoothness penalties, just as the conventional registration methods, and ignores population-level statistics of the transformations. Here, we propose a novel neural network architecture that simultaneously learns and uses the population-level statistics of the spatial transformations to regularize the neural networks for unsupervised image registration. This regularization is in the form of a bottleneck autoencoder, which learns and adapts to the population of transformations required to align input images by encoding the transformations to a low dimensional manifold. The proposed architecture produces deformation fields that describe the population-level features and associated correspondences in an anatomically relevant manner and are statistically compact relative to the state-of-the-art approaches while maintaining computational efficiency. We demonstrate the efficacy of the proposed architecture on synthetic data sets, as well as 2D and 3D medical data.
- 10 October 2019
- Published by Springer Nature
- Vol. 11765, 391-400
A Cooperative Autoencoder for Population-Based Regularization of CNN Image Registration
Spatial transformations are enablers in a variety of medical image analysis applications that entail aligning images to a common coordinate systems. Population analysis of such transformations is expected to capture the underlying image and shape variations, and hence these transformations are required to produce anatomically feasible correspondences. This is usually enforced through some smoothness-based generic metric or regularization of the deformation field. Alternatively, population-based regularization has been shown to produce anatomically accurate correspondences in cases where anatomically unaware (i.e., data independent) regularization fail. Recently, deep networks have been used to generate spatial transformations in an unsupervised manner, and, once trained, these networks are computationally faster and as accurate as conventional, optimization-based registration methods. However, the deformation fields produced by these networks require smoothness penalties, just as the conventional registration methods, and ignores population-level statistics of the transformations. Here, we propose a novel neural network architecture that simultaneously learns and uses the population-level statistics of the spatial transformations to regularize the neural networks for unsupervised image registration. This regularization is in the form of a bottleneck autoencoder, which learns and adapts to the population of transformations required to align input images by encoding the transformations to a low dimensional manifold. The proposed architecture produces deformation fields that describe the population-level features and associated correspondences in an anatomically relevant manner and are statistically compact relative to the state-of-the-art approaches while maintaining computational efficiency. We demonstrate the efficacy of the proposed architecture on synthetic data sets, as well as 2D and 3D medical data.