Search Results for author: Yuankai Huo

Found 58 papers, 17 papers with code

Random Multi-Channel Image Synthesis for Multiplexed Immunofluorescence Imaging

no code implementations18 Sep 2021 Shunxing Bao, Yucheng Tang, Ho Hin Lee, Riqiang Gao, Sophie Chiron, Ilwoo Lyu, Lori A. Coburn, Keith T. Wilson, Joseph T. Roland, Bennett A. Landman, Yuankai Huo

Our contribution is three-fold: (1) a single deep network framework is proposed to tackle missing stain in MxIF; (2) the proposed 'N-to-N' strategy reduces theoretical four years of computational time to 20 hours when covering all possible missing stains scenarios, with up to five missing stains (e. g., '(N-1)-to-1', '(N-2)-to-2'); and (3) this work is the first comprehensive experimental study of investigating cross-stain synthesis in MxIF.

Image Generation

Evaluating Transformer-based Semantic Segmentation Networks for Pathological Image Segmentation

no code implementations26 Aug 2021 Cam Nguyen, Zuhayr Asad, Yuankai Huo

For a more comprehensive analysis, we also compare the transformer-based models with six major traditional CNN-based models.

Tumor Segmentation whole slide images

Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective

no code implementations25 Jul 2021 Riqiang Gao, Yucheng Tang, Kaiwen Xu, Ho Hin Lee, Steve Deppen, Kim Sandler, Pierre Massion, Thomas A. Lasko, Yuankai Huo, Bennett A. Landman

To our knowledge, it is the first generative adversarial model that addresses multi-modal missing imputation by modeling the joint distribution of image and non-image data.


Compound Figure Separation of Biomedical Images with Side Loss

1 code implementation19 Jul 2021 Tianyuan Yao, Chang Qu, Quan Liu, Ruining Deng, Yuanhan Tian, Jiachen Xu, Aadarsh Jha, Shunxing Bao, Mengyang Zhao, Agnes B. Fogo, Bennett A. Landman, Catie Chang, Haichun Yang, Yuankai Huo

Our technical contribution is three-fold: (1) we introduce a new side loss that is designed for compound figure separation; (2) we introduce an intra-class image augmentation method to simulate hard cases; (3) the proposed framework enables an efficient deployment to new classes of images, without requiring resource extensive bounding box annotations.

Contrastive Learning Image Augmentation +1

VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning

no code implementations22 Jun 2021 Mengyang Zhao, Quan Liu, Aadarsh Jha, Ruining Deng, Tianyuan Yao, Anita Mahadevan-Jansen, Matthew J. Tyska, Bryan A. Millis, Yuankai Huo

Recently, pixel embedding-based cell instance segmentation and tracking provided a neat and generalizable computing paradigm for understanding cellular dynamics.

3D Instance Segmentation Semantic Segmentation

Attention-Guided Supervised Contrastive Learning for Semantic Segmentation

no code implementations3 Jun 2021 Ho Hin Lee, Yucheng Tang, Qi Yang, Xin Yu, Shunxing Bao, Bennett A. Landman, Yuankai Huo

In this paper, we propose an attention-guided supervised contrastive learning approach to highlight a single semantic object every time as the target.

Contrastive Learning Image Classification +1

SimTriplet: Simple Triplet Representation Learning with a Single GPU

1 code implementation9 Mar 2021 Quan Liu, Peter C. Louis, Yuzhe Lu, Aadarsh Jha, Mengyang Zhao, Ruining Deng, Tianyuan Yao, Joseph T. Roland, Haichun Yang, Shilin Zhao, Lee E. Wheless, Yuankai Huo

The contribution of the paper is three-fold: (1) The proposed SimTriplet method takes advantage of the multi-view nature of medical images beyond self-augmentation; (2) The method maximizes both intra-sample and inter-sample similarities via triplets from positive pairs, without using negative samples; and (3) The recent mix precision training is employed to advance the training by only using a single GPU with 16GB memory.

Contrastive Learning Representation Learning +1

Improve Global Glomerulosclerosis Classification with Imbalanced Data using CircleMix Augmentation

no code implementations16 Jan 2021 Yuzhe Lu, Haichun Yang, Zheyu Zhu, Ruining Deng, Agnes B. Fogo, Yuankai Huo

Different from the recently proposed CutMix method, the CircleMix augmentation is optimized for the ball-shaped biomedical objects, such as glomeruli.

Classification Data Augmentation +1

WearMask: Fast In-browser Face Mask Detection with Serverless Edge Computing for COVID-19

1 code implementation4 Jan 2021 Zekun Wang, Pengwei Wang, Peter C. Louis, Lee E. Wheless, Yuankai Huo

The serverless edge-computing design minimizes the extra hardware costs (e. g., specific devices or cloud computing servers).


ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations

no code implementations3 Jan 2021 Quan Liu, Isabella M. Gaeta, Mengyang Zhao, Ruining Deng, Aadarsh Jha, Bryan A. Millis, Anita Mahadevan-Jansen, Matthew J. Tyska, Yuankai Huo

Contribution: The contribution of this paper is three-fold: (1) the proposed method aggregates adversarial simulations and single-stage pixel-embedding based deep learning; (2) the method is assessed with both the cellular (i. e., HeLa cells) and subcellular (i. e., microvilli) objects; and (3) to the best of our knowledge, this is the first study to explore annotation-free instance segmentation and tracking study for microscope videos.

Instance Segmentation Semantic Segmentation

RAP-Net: Coarse-to-Fine Multi-Organ Segmentation with Single Random Anatomical Prior

1 code implementation23 Dec 2020 Ho Hin Lee, Yucheng Tang, Shunxing Bao, Richard G. Abramson, Yuankai Huo, Bennett A. Landman

We combine the anatomical prior with corresponding extracted patches to preserve the anatomical locations and boundary information for performing high-resolution segmentation across all organs in a single model.

Limitation of Acyclic Oriented Graphs Matching as Cell Tracking Accuracy Measure when Evaluating Mitosis

no code implementations22 Dec 2020 Ye Chen, Yuankai Huo

Multi-object tracking (MOT) in computer vision and cell tracking in biomedical image analysis are two similar research fields, whose common aim is to achieve instance level object detection/segmentation and associate such objects across different video frames.

Multi-Object Tracking Multiple Object Tracking +1

CaCL: Class-aware Codebook Learning for Weakly Supervised Segmentation on Diffuse Image Patterns

no code implementations2 Nov 2020 Ruining Deng, Quan Liu, Shunxing Bao, Aadarsh Jha, Catie Chang, Bryan A. Millis, Matthew J. Tyska, Yuankai Huo

This paper makes the following contributions: (1) we approach the weakly supervised segmentation from a novel codebook learning perspective; (2) the CaCL algorithm segments diffuse image patterns rather than focal objects; and (3) The proposed algorithm is implemented in a multi-task framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) to perform image reconstruction, classification, feature embedding, and segmentation.

Image Reconstruction Weakly supervised segmentation

GAN based Unsupervised Segmentation: Should We Match the Exact Number of Objects

no code implementations22 Oct 2020 Quan Liu, Isabella M. Gaeta, Bryan A. Millis, Matthew J. Tyska, Yuankai Huo

To match the number of objects at the micro-level, the novel fluorescence-based micro-level matching approach was presented.

Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking

1 code implementation28 Jul 2020 Mengyang Zhao, Aadarsh Jha, Quan Liu, Bryan A. Millis, Anita Mahadevan-Jansen, Le Lu, Bennett A. Landman, Matthew J. Tyskac, Yuankai Huo

With both embedding simulation and empirical validation via the four cohorts from the ISBI cell tracking challenge, the proposed Faster Mean-shift algorithm achieved 7-10 times speedup compared to the state-of-the-art embedding based cell instance segmentation and tracking algorithm.

Cell Segmentation Instance Segmentation +1

EasierPath: An Open-source Tool for Human-in-the-loop Deep Learning of Renal Pathology

1 code implementation28 Jul 2020 Zheyu Zhu, Yuzhe Lu, Ruining Deng, Haichun Yang, Agnes B. Fogo, Yuankai Huo

Inspired by the recent "human-in-the-loop" strategy, we developed EasierPath, an open-source tool to integrate human physicians and deep learning algorithms for efficient large-scale pathological image quantification as a loop.

Object Detection whole slide images

Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment

2 code implementations7 Jul 2020 Aadarsh Jha, Haichun Yang, Ruining Deng, Meghan E. Kapp, Agnes B. Fogo, Yuankai Huo

In this paper, we assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework.

Instance Segmentation Semantic Segmentation

Map3D: Registration Based Multi-Object Tracking on 3D Serial Whole Slide Images

no code implementations10 Jun 2020 Ruining Deng, Haichun Yang, Aadarsh Jha, Yuzhe Lu, Peng Chu, Agnes B. Fogo, Yuankai Huo

However, the 3D identification and association of large-scale glomeruli on renal pathology is challenging due to large tissue deformation, missing tissues, and artifacts from WSI.

Multi-Object Tracking whole slide images

CircleNet: Anchor-free Detection with Circle Representation

1 code implementation3 Jun 2020 Haichun Yang, Ruining Deng, Yuzhe Lu, Zheyu Zhu, Ye Chen, Joseph T. Roland, Le Lu, Bennett A. Landman, Agnes B. Fogo, Yuankai Huo

In this work, we propose CircleNet, a simple anchor-free detection method with circle representation for detection of the ball-shaped glomerulus.

Object Detection

JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans

no code implementations ECCV 2020 Fengze Liu, Jingzheng Cai, Yuankai Huo, Chi-Tung Cheng, Ashwin Raju, Dakai Jin, Jing Xiao, Alan Yuille, Le Lu, Chien-Hung Liao, Adam P. Harrison

We extensively evaluate our JSSR system on a large-scale medical image dataset containing 1, 485 patient CT imaging studies of four different phases (i. e., 5, 940 3D CT scans with pathological livers) on the registration, segmentation and synthesis tasks.

Image Registration Multi-Task Learning +1

The Value of Nullspace Tuning Using Partial Label Information

no code implementations17 Mar 2020 Colin B. Hansen, Vishwesh Nath, Diego A. Mesa, Yuankai Huo, Bennett A. Landman, Thomas A. Lasko

But in some learning problems, partial label information can be inferred from otherwise unlabeled examples and used to further improve the model.

Outlier Guided Optimization of Abdominal Segmentation

no code implementations10 Feb 2020 Yuchen Xu, Olivia Tang, Yucheng Tang, Ho Hin Lee, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael R. Savona, Richard G. Abramson, Yuankai Huo, Bennett A. Landman

We built on a pre-trained 3D U-Net model for abdominal multi-organ segmentation and augmented the dataset either with outlier data (e. g., exemplars for which the baseline algorithm failed) or inliers (e. g., exemplars for which the baseline algorithm worked).

Active Learning Computed Tomography (CT)

Lesion Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale

1 code implementation21 Jan 2020 Jinzheng Cai, Adam P. Harrison, Youjing Zheng, Ke Yan, Yuankai Huo, Jing Xiao, Lin Yang, Le Lu

This is the goal of our work, where we develop a powerful system to harvest missing lesions from the DeepLesion dataset at high precision.

Internal-transfer Weighting of Multi-task Learning for Lung Cancer Detection

no code implementations16 Dec 2019 Yiyuan Yang, Riqiang Gao, Yucheng Tang, Sanja L. Antic, Steve Deppen, Yuankai Huo, Kim L. Sandler, Pierre P. Massion, Bennett A. Landman

To improve performance on the primary task, we propose an Internal-Transfer Weighting (ITW) strategy to suppress the loss functions on auxiliary tasks for the final stages of training.

Multi-Task Learning

Contrast Phase Classification with a Generative Adversarial Network

no code implementations14 Nov 2019 Yucheng Tang, Ho Hin Lee, Yuchen Xu, Olivia Tang, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Camilo Bermudez, Michael R. Savona, Richard G. Abramson, Yuankai Huo, Bennett A. Landman

Dynamic contrast enhanced computed tomography (CT) is an imaging technique that provides critical information on the relationship of vascular structure and dynamics in the context of underlying anatomy.

Classification Computed Tomography (CT) +2

Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervision

no code implementations12 Nov 2019 Ho Hin Lee, Yucheng Tang, Olivia Tang, Yuchen Xu, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael R. Savona, Richard G. Abramson, Yuankai Huo, Bennett A. Landman

The contributions of the proposed method are threefold: We show that (1) the QA scores can be used as a loss function to perform semi-supervised learning for unlabeled data, (2) the well trained discriminator is learnt by QA score rather than traditional true/false, and (3) the performance of multi-organ segmentation on unlabeled datasets can be fine-tuned with more robust and higher accuracy than the original baseline method.

Medical Image Segmentation

Enabling Multi-Shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE

no code implementations15 Jul 2019 Vishwesh Nath, Ilwoo Lyu, Kurt G. Schilling, Prasanna Parvathaneni, Colin B. Hansen, Yucheng Tang, Yuankai Huo, Vaibhav A. Janve, Yurui Gao, Iwona Stepniewska, Adam W. Anderson, Bennett A. Landman

In the in-vivo human data, Deep SHORE was more consistent across scanners with 0. 63 relative to other multi-shell methods 0. 39, 0. 52 and 0. 57 in terms of ACC.

Fully Automatic Liver Attenuation Estimation Combing CNN Segmentation and Morphological Operations

1 code implementation23 Jun 2019 Yuankai Huo, James G. Terry, Jiachen Wang, Sangeeta Nair, Thomas A. Lasko, Barry I. Freedman, J. Jeffery Carr, Bennett A. Landman

Manually tracing regions of interest (ROIs) within the liver is the de facto standard method for measuring liver attenuation on computed tomography (CT) in diagnosing nonalcoholic fatty liver disease (NAFLD).

Computed Tomography (CT) Liver Segmentation

3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles

2 code implementations28 Mar 2019 Yuankai Huo, Zhoubing Xu, Yunxi Xiong, Katherine Aboud, Prasanna Parvathaneni, Shunxing Bao, Camilo Bermudez, Susan M. Resnick, Laurie E. Cutting, Bennett A. Landman

To address the first challenge, multiple spatially distributed networks were used in the SLANT method, in which each network learned contextual information for a fixed spatial location.

Brain Segmentation

Lung Cancer Detection using Co-learning from Chest CT Images and Clinical Demographics

no code implementations21 Feb 2019 Jiachen Wang, Riqiang Gao, Yuankai Huo, Shunxing Bao, Yunxi Xiong, Sanja L. Antic, Travis J. Osterman, Pierre P. Massion, Bennett A. Landman

The results show that the AUC obtained from clinical demographics alone was 0. 635 while the attention network alone reached an accuracy of 0. 687.

Computed Tomography (CT)

Reproducibility Evaluation of SLANT Whole Brain Segmentation Across Clinical Magnetic Resonance Imaging Protocols

no code implementations7 Jan 2019 Yunxi Xiong, Yuankai Huo, Jiachen Wang, L. Taylor Davis, Maureen McHugo, Bennett A. Landman

Recently, we obtained a clinically acquired, multi-sequence MRI brain cohort with 1480 clinically acquired, de-identified brain MRI scans on 395 patients using seven different MRI protocols.

Brain Segmentation

Montage based 3D Medical Image Retrieval from Traumatic Brain Injury Cohort using Deep Convolutional Neural Network

no code implementations10 Dec 2018 Cailey I. Kerley, Yuankai Huo, Shikha Chaganti, Shunxing Bao, Mayur B. Patel, Bennett A. Landman

For instance, in a typical sample of clinical TBI imaging cohort, only ~15% of CT scans actually contain whole brain CT images suitable for volumetric brain analyses; the remaining are partial brain or non-brain images.

Computed Tomography (CT) Medical Image Retrieval

Towards Machine Learning Prediction of Deep Brain Stimulation (DBS) Intra-operative Efficacy Maps

no code implementations26 Nov 2018 Camilo Bermudez, William Rodriguez, Yuankai Huo, Allison E. Hainline, Rui Li, Robert Shults, Pierre D. DHaese, Peter E. Konrad, Benoit M. Dawant, Bennett A. Landman

We show an improvement in the classification of intraoperative stimulation coordinates as a positive response in reduction of symptoms with AUC of 0. 670 compared to a baseline registration-based approach, which achieves an AUC of 0. 627 (p < 0. 01).

General Classification

Splenomegaly Segmentation on Multi-modal MRI using Deep Convolutional Networks

no code implementations9 Nov 2018 Yuankai Huo, Zhoubing Xu, Shunxing Bao, Camilo Bermudez, Hyeonsoo Moon, Prasanna Parvathaneni, Tamara K. Moyo, Michael R. Savona, Albert Assad, Richard G. Abramson, Bennett A. Landman

A clinically acquired cohort containing both T1-weighted (T1w) and T2-weighted (T2w) MRI splenomegaly scans was used to train and evaluate the performance of multi-atlas segmentation (MAS), 2D DCNN networks, and a 3D DCNN network.

Splenomegaly Segmentation On Multi-Modal Mri

SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth

1 code implementation15 Oct 2018 Yuankai Huo, Zhoubing Xu, Hyeonsoo Moon, Shunxing Bao, Albert Assad, Tamara K. Moyo, Michael R. Savona, Richard G. Abramson, Bennett A. Landman

SynSeg-Net is trained by using (1) unpaired intensity images from source and target modalities, and (2) manual labels only from source modality.

Semantic Segmentation

Data-driven Probabilistic Atlases Capture Whole-brain Individual Variation

no code implementations6 Jun 2018 Yuankai Huo, Katherine Swett, Susan M. Resnick, Laurie E. Cutting, Bennett A. Landman

By indexing the dictionary, the whole brain probabilistic atlases adapt to each new subject quickly and can be used as spatial priors for visualization and processing.

Less is More: Simultaneous View Classification and Landmark Detection for Abdominal Ultrasound Images

no code implementations25 May 2018 Zhoubing Xu, Yuankai Huo, Jin-Hyeong Park, Bennett Landman, Andy Milkowski, Sasa Grbic, Shaohua Zhou

However, this is a challenging problem given not only the inherent difficulties from the ultrasound modality, e. g., low contrast and large variations, but also the heterogeneity across tasks, i. e., one classification task for all views, and then one landmark detection task for each relevant view.

Classification General Classification +1

Adversarial Synthesis Learning Enables Segmentation Without Target Modality Ground Truth

1 code implementation20 Dec 2017 Yuankai Huo, Zhoubing Xu, Shunxing Bao, Albert Assad, Richard G. Abramson, Bennett A. Landman

Herein, we proposed a novel end-to-end synthesis and segmentation network (EssNet) to achieve the unpaired MRI to CT image synthesis and CT splenomegaly segmentation simultaneously without using manual labels on CT.

Image-to-Image Translation Medical Image Segmentation +1

Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks

1 code implementation2 Dec 2017 Yuankai Huo, Zhoubing Xu, Shunxing Bao, Camilo Bermudez, Andrew J. Plassard, Jiaqi Liu, Yuang Yao, Albert Assad, Richard G. Abramson, Bennett A. Landman

However, variations in both size and shape of the spleen on MRI images may result in large false positive and false negative labeling when deploying DCNN based methods.

Semantic Segmentation

Improved Stability of Whole Brain Surface Parcellation with Multi-Atlas Segmentation

no code implementations2 Dec 2017 Yuankai Huo, Shunxing Bao, Prasanna Parvathaneni, Bennett A. Landman

Herein, the MaCRUISE surface parcellation (MaCRUISEsp) method is proposed to perform the surface parcellation upon the inner, central and outer surfaces that are reconstructed from MaCRUISE.

Brain Segmentation

4D Multi-atlas Label Fusion using Longitudinal Images

no code implementations29 Aug 2017 Yuankai Huo, Susan M. Resnick, Bennett A. Landman

(2) The proposed algorithm is a longitudinal generalization of a lead-ing joint label fusion method (JLF) that has proven adaptable to a wide variety of applications.

Medical Image Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.