no code implementations • 13 Apr 2023 • Peiyu Duan, Yuan Xue, Shuo Han, Lianrui Zuo, Aaron Carass, Caitlyn Bernhard, Savannah Hays, Peter A. Calabresi, Susan M. Resnick, James S. Duncan, Jerry L. Prince
The meninges, located between the skull and brain, are composed of three membrane layers: the pia, the arachnoid, and the dura.
no code implementations • 6 Apr 2023 • Chenyu You, Weicheng Dai, Yifei Min, Lawrence Staib, James S. Duncan
Integrating high-level semantically correlated contents and low-level anatomical features is of central importance in medical image segmentation.
1 code implementation • 5 Apr 2023 • Chenyu You, Weicheng Dai, Yifei Min, Lawrence Staib, Jasjeet S. Sekhon, James S. Duncan
In this work, we present ACTION++, an improved contrastive learning framework with adaptive anatomical contrast for semi-supervised medical segmentation.
1 code implementation • 2 Apr 2023 • Bo Zhou, Huidong Xie, Qiong Liu, Xiongchao Chen, Xueqi Guo, Zhicheng Feng, S. Kevin Zhou, Biao Li, Axel Rominger, Kuangyu Shi, James S. Duncan, Chi Liu
While previous federated learning (FL) algorithms enable multi-institution collaborative training without the need of aggregating local data, addressing the large domain shift in the application of multi-institutional low-count PET denoising remains a challenge and is still highly under-explored.
no code implementations • 2 Mar 2023 • Bo Zhou, Yingda Xia, Jiawen Yao, Le Lu, Jingren Zhou, Chi Liu, James S. Duncan, Ling Zhang
Accurate detection, segmentation, and differential diagnosis of the full taxonomy of pancreatic lesions, i. e., normal, seven major types of lesions, and other lesions, is critical to aid the clinical decision-making of patient management and treatment.
no code implementations • 18 Feb 2023 • Bo Zhou, Jo Schlemper, Neel Dey, Seyed Sadegh Mohseni Salehi, Kevin Sheth, Chi Liu, James S. Duncan, Michal Sofka
To this end, we present a fully self-supervised approach for accelerated non-Cartesian MRI reconstruction which leverages self-supervision in both k-space and image domains.
no code implementations • 14 Feb 2023 • Bo Zhou, Yu-Jung Tsai, Jiazhen Zhang, Xueqi Guo, Huidong Xie, Xiongchao Chen, Tianshun Miao, Yihuan Lu, James S. Duncan, Chi Liu
To this end, modeling-free universal motion correction reconstruction for accelerated PET is still highly under-explored.
no code implementations • 27 Sep 2022 • Chenyu You, Weicheng Dai, Fenglin Liu, Yifei Min, Haoran Su, Xiaoran Zhang, Xiaoxiao Li, David A. Clifton, Lawrence Staib, James S. Duncan
Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent anatomical features due to the intra-class variations between different anatomical features; and (3) diversity: the intra-slice correlations within the entire dataset have received significantly less attention.
1 code implementation • 20 Jul 2022 • Siyuan Dong, Gilbert Hangel, Eric Z. Chen, Shanhui Sun, Wolfgang Bogner, Georg Widhalm, Chenyu You, John A. Onofrey, Robin de Graaf, James S. Duncan
Specifically, we propose a flow-based enhancer network to improve the visual quality of super-resolution MRSI.
no code implementations • 6 Jun 2022 • Chenyu You, Weicheng Dai, Yifei Min, Lawrence Staib, James S. Duncan
In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation.
no code implementations • 3 Jun 2022 • Chenyu You, Jinlin Xiang, Kun Su, Xiaoran Zhang, Siyuan Dong, John Onofrey, Lawrence Staib, James S. Duncan
Many medical datasets have recently been created for medical image segmentation tasks, and it is natural to question whether we can use them to sequentially train a single model that (1) performs better on all these datasets, and (2) generalizes well and transfers better to the unknown target site domain.
no code implementations • 26 Jan 2022 • Bo Zhou, Neel Dey, Jo Schlemper, Seyed Sadegh Mohseni Salehi, Chi Liu, James S. Duncan, Michal Sofka
To these ends, we present a dual-domain self-supervised transformer (DSFormer) for accelerated MC-MRI reconstruction.
no code implementations • 26 Jan 2022 • Chenyu You, Ruihan Zhao, Fenglin Liu, Siyuan Dong, Sandeep Chinchali, Ufuk Topcu, Lawrence Staib, James S. Duncan
In this work, we present CASTformer, a novel type of adversarial transformers, for 2D medical image segmentation.
2 code implementations • NeurIPS 2021 • Juntang Zhuang, Yifan Ding, Tommy Tang, Nicha Dvornek, Sekhar Tatikonda, James S. Duncan
We demonstrate that ACProp has a convergence rate of $O(\frac{1}{\sqrt{T}})$ for the stochastic non-convex case, which matches the oracle rate and outperforms the $O(\frac{logT}{\sqrt{T}})$ rate of RMSProp and Adam.
no code implementations • 13 Aug 2021 • Chenyu You, Yuan Zhou, Ruihan Zhao, Lawrence Staib, James S. Duncan
However, most existing learning-based approaches usually suffer from limited manually annotated medical data, which poses a major practical problem for accurate and robust medical image segmentation.
1 code implementation • 12 Jul 2021 • Bo Zhou, Chi Liu, James S. Duncan
The manual efforts can be alleviated if the manual segmentation in one imaging modality (e. g., CT) can be utilized to train a segmentation network in another imaging modality (e. g., CBCT/MRI/PET).
1 code implementation • 12 Jul 2021 • Bo Zhou, Rui Wang, Ming-Kai Chen, Adam P. Mecca, Ryan S. O'Dell, Christopher H. Van Dyck, Richard E. Carson, James S. Duncan, Chi Liu
Thus, it is desirable to develop an efficient multi-tracer PET synthesis model that can generate multi-tracer PET from single-tracer PET.
no code implementations • 14 May 2021 • Chenyu You, Ruihan Zhao, Lawrence Staib, James S. Duncan
In this work, we present a novel Contrastive Voxel-wise Representation Learning (CVRL) method to effectively learn low-level and high-level features by capturing 3D spatial context and rich anatomical information along both the feature and the batch dimensions.
no code implementations • 6 May 2021 • Nicha C. Dvornek, Pamela Ventola, James S. Duncan
We demonstrate that the functional networks learned by the LSTM model are more strongly associated with the task activity and dynamics compared to other approaches.
no code implementations • 15 Apr 2021 • Nicha C. Dvornek, Xiaoxiao Li, Juntang Zhuang, Pamela Ventola, James S. Duncan
Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain.
1 code implementation • 14 Apr 2021 • Bo Zhou, Zachary Augenfeld, Julius Chapiro, S. Kevin Zhou, Chi Liu, James S. Duncan
Our experimental results on in-house TACE patient data demonstrated that our APA2Seg-Net can generate robust CBCT and MR liver segmentation, and the anatomy-guided registration framework with these segmenters can provide high-quality multimodal registrations.
1 code implementation • ICLR 2021 • Juntang Zhuang, Nicha C. Dvornek, Sekhar Tatikonda, James S. Duncan
Neural ordinary differential equations (Neural ODEs) are a new family of deep-learning models with continuous depth.
Ranked #19 on
Image Generation
on ImageNet 64x64
(Bits per dim metric)
8 code implementations • NeurIPS 2020 • Juntang Zhuang, Tommy Tang, Yifan Ding, Sekhar Tatikonda, Nicha Dvornek, Xenophon Papademetris, James S. Duncan
Viewing the exponential moving average (EMA) of the noisy gradient as the prediction of the gradient at the next time step, if the observed gradient greatly deviates from the prediction, we distrust the current observation and take a small step; if the observed gradient is close to the prediction, we trust it and take a large step.
no code implementations • 6 Sep 2020 • Chenyu You, Junlin Yang, Julius Chapiro, James S. Duncan
However, the well-trained models often fail in the target domain due to the domain shift.
no code implementations • 3 Sep 2020 • Bo Zhou, S. Kevin Zhou, James S. Duncan, Chi Liu
To derive quality reconstruction, previous state-of-the-art methods use UNet-like neural architectures to directly predict the full view reconstruction from limited view data; but these methods leave the deep network architecture issue largely intact and cannot guarantee the consistency between the sinogram of the reconstructed image and the acquired sinogram, leading to a non-ideal reconstruction.
no code implementations • 2 Aug 2020 • S. Kevin Zhou, Hayit Greenspan, Christos Davatzikos, James S. Duncan, Bram van Ginneken, Anant Madabhushi, Jerry L. Prince, Daniel Rueckert, Ronald M. Summers
In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues.
no code implementations • 29 Jul 2020 • Xiaoxiao Li, Yuan Zhou, Nicha C. Dvornek, Muhan Zhang, Juntang Zhuang, Pamela Ventola, James S. Duncan
We propose an interpretable GNN framework with a novel salient region selection mechanism to determine neurological brain biomarkers associated with disorders.
1 code implementation • 16 Jan 2020 • Xiaoxiao Li, Yufeng Gu, Nicha Dvornek, Lawrence Staib, Pamela Ventola, James S. Duncan
However, to effectively train a high-quality deep learning model, the aggregation of a significant amount of patient information is required.
no code implementations • 1 Dec 2019 • Junlin Yang, Nicha C. Dvornek, Fan Zhang, Julius Chapiro, MingDe Lin, Aaron Abajian, James S. Duncan
This work proposes a pipeline to predict treatment response to intra-arterial therapy of patients with Hepatocellular Carcinoma (HCC) for improved therapeutic decision-making.
no code implementations • 15 Oct 2019 • Nicha C. Dvornek, Xiaoxiao Li, Juntang Zhuang, James S. Duncan
The addition of the generative model constrains the network to learn functional communities represented by the LSTM nodes that are both consistent with the data generation as well as useful for the classification task.
1 code implementation • 30 Sep 2019 • Juntang Zhuang, Nicha C. Dvornek, Xiaoxiao Li, Junlin Yang, James S. Duncan
We can determine the decision boundary of a linear classifier in the feature space; since the transform is invertible, we can invert the decision boundary from the feature space to the input space.
no code implementations • 25 Sep 2019 • Juntang Zhuang, Nicha Dvornek, Xiaoxiao Li, James S. Duncan
Inspired by neural ordinary differential equation (NODE) for data in the Euclidean domain, we extend the idea of continuous-depth models to graph data, and propose graph ordinary differential equation (GODE).
no code implementations • 27 Aug 2019 • Junlin Yang, Nicha C. Dvornek, Fan Zhang, Juntang Zhuang, Julius Chapiro, MingDe Lin, James S. Duncan
For the DA task, our DALACE model outperformed CycleGAN, TD-GAN , and DADR with DSC of 0. 847 compared to 0. 721, 0. 793 and 0. 806.
no code implementations • 31 Jul 2019 • Junlin Yang, Nicha C. Dvornek, Fan Zhang, Julius Chapiro, MingDe Lin, James S. Duncan
First, images from each domain are embedded into two spaces, a shared domain-invariant content space and a domain-specific style space.
1 code implementation • 23 Jul 2019 • Juntang Zhuang, Nicha C. Dvornek, Xiaoxiao Li, Pamela Ventola, James S. Duncan
Recently deep learning methods have achieved success in the classification task of ASD using fMRI data.
no code implementations • 2 Jul 2019 • Xiaoxiao Li, Nicha C. Dvornek, Yuan Zhou, Juntang Zhuang, Pamela Ventola, James S. Duncan
Our pipeline can be generalized to other graph feature importance interpretation problems.
no code implementations • 14 Dec 2018 • Xiaoxiao Li, Nicha C. Dvornek, Yuan Zhou, Juntang Zhuang, Pamela Ventola, James S. Duncan
Cooperative game theory is advantageous here because it directly considers the interaction between features and can be applied to any machine learning method, making it a novel, more accurate way of determining instance-wise biomarker importance from deep learning models.
no code implementations • 23 Aug 2018 • Xiaoxiao Li, Nicha C. Dvornek, Juntang Zhuang, Pamela Ventola, James S. Duncan
Therefore, in this work, we address the problem of interpreting reliable biomarkers associated with identifying ASD; specifically, we propose a 2-stage method that classifies ASD and control subjects using fMRI images and interprets the saliency features activated by the classifier.
no code implementations • 12 Jul 2018 • Allen Lu, Nripesh Parajuli, Maria Zontak, John Stendahl, Kevinminh Ta, Zhao Liu, Nabil Boutagy, Geng-Shi Jeng, Imran Alkhalil, Lawrence H. Staib, Matthew O'Donnell, Albert J. Sinusas, James S. Duncan
We extended this framework to include a supervised loss term on synthetic data and showed the effects of biomechanical constraints on the network's ability for domain adaptation.
no code implementations • 9 Jul 2018 • Nripesh Parajuli, Allen Lu, Kevinminh Ta, John C. Stendahl, Nabil Boutagy, Imran Alkhalil, Melissa Eberle, Geng-Shi Jeng, Maria Zontak, Matthew ODonnell, Albert J. Sinusas, James S. Duncan
In this work, we propose a point matching scheme where correspondences are modeled as flow through a graphical network.
no code implementations • 24 May 2018 • Nicha C. Dvornek, Daniel Yang, Archana Venkataraman, Pamela Ventola, Lawrence H. Staib, Kevin A. Pelphrey, James S. Duncan
We propose predicting patient response to PRT from baseline task-based fMRI by the novel application of a random forest and tree bagging strategy.
no code implementations • CVPR 2013 • Xiaowei Zhou, Xiaojie Huang, James S. Duncan, Weichuan Yu
In this paper, we propose to use the group similarity of object shapes in multiple images as a prior to aid segmentation, which can be interpreted as an unsupervised approach of shape prior modeling.