Search Results for author: S. Kevin Zhou

Found 53 papers, 17 papers with code

Radiology Report Generation with a Learned Knowledge Base and Multi-modal Alignment

no code implementations30 Dec 2021 Shuxin Yang, Xian Wu, Shen Ge, Xingwang Wu, S. Kevin Zhou, Li Xiao

To promote the semantic alignment among reports, disease labels and images, we explicitly utilize textual embedding to guide the learning of the visual feature space.

Text Generation

Which images to label for few-shot medical landmark detection?

no code implementations7 Dec 2021 Quan Quan, Qingsong Yao, Jun Li, S. Kevin Zhou

We herein propose a novel Sample Choosing Policy (SCP) to select "the most worthy" images for annotation, in the context of few-shot medical landmark detection.

Few-Shot Learning

Medical Aegis: Robust adversarial protectors for medical images

no code implementations22 Nov 2021 Qingsong Yao, Zecheng He, S. Kevin Zhou

To the best of our knowledge, Medical Aegis is the first defense in the literature that successfully addresses the strong adaptive adversarial example attacks to medical images.

DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction

no code implementations21 Nov 2021 Ce Wang, Kun Shang, Haimiao Zhang, Qian Li, Yuan Hui, S. Kevin Zhou

While Computed Tomography (CT) reconstruction from X-ray sinograms is necessary for clinical diagnosis, iodine radiation in the imaging process induces irreversible injury, thereby driving researchers to study sparse-view CT reconstruction, that is, recovering a high-quality CT image from a sparse set of sinogram views.

Computed Tomography (CT)

GAN-based disentanglement learning for chest X-ray rib suppression

no code implementations18 Oct 2021 Luyi Han, Yuanyuan Lyu, Cheng Peng, S. Kevin Zhou

Clinical evidence has shown that rib-suppressed chest X-rays (CXRs) can improve the reliability of pulmonary disease diagnosis.

Computed Tomography (CT) Lung Disease Classification

Shallow Feature Matters for Weakly Supervised Object Localization

1 code implementation CVPR 2021 Jun Wei, Qin Wang, Zhen Li, Sheng Wang, S. Kevin Zhou, Shuguang Cui

In practice, our SPOL model first generates the CAMs through a novel element-wise multiplication of shallow and deep feature maps, which filters the background noise and generates sharper boundaries robustly.

Weakly-Supervised Object Localization

Shallow Attention Network for Polyp Segmentation

1 code implementation2 Aug 2021 Jun Wei, Yiwen Hu, Ruimao Zhang, Zhen Li, S. Kevin Zhou, Shuguang Cui

To address the above issues, we propose the Shallow Attention Network (SANet) for polyp segmentation.

Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal image

no code implementations24 Jun 2021 Yuanqi Du, Quan Quan, Hu Han, S. Kevin Zhou

Pseudo-normality synthesis, which computationally generates a pseudo-normal image from an abnormal one (e. g., with lesions), is critical in many perspectives, from lesion detection, data augmentation to clinical surgery suggestion.

Data Augmentation Image Generation +1

Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological Measurement

no code implementations CVPR 2021 Hao Lu, Hu Han, S. Kevin Zhou

Remote photoplethysmography (rPPG) based physiological measurement has great application values in health monitoring, emotion analysis, etc.

Emotion Recognition Heart Rate Variability

Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registration

1 code implementation14 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.

Domain Adaptation Image Registration +1

Conditional Training with Bounding Map for Universal Lesion Detection

no code implementations23 Mar 2021 Han Li, Long Chen, Hu Han, S. Kevin Zhou

Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis.

Pathological Image Segmentation with Noisy Labels

no code implementations20 Mar 2021 Li Xiao, Yinhao Li, Luxi Qv, Xinxia Tian, Yijie Peng, S. Kevin Zhou

Segmentation of pathological images is essential for accurate disease diagnosis.

Semantic Segmentation

Universal Undersampled MRI Reconstruction

no code implementations9 Mar 2021 Xinwen Liu, Jing Wang, Feng Liu, S. Kevin Zhou

Simply mixing images from multiple anatomies for training a single network does not lead to an ideal universal model due to the statistical shift among datasets of various anatomies, the need to retrain from scratch on all datasets with the addition of a new dataset, and the difficulty in dealing with imbalanced sampling when the new dataset is further of a smaller size.

MRI Reconstruction

Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation

no code implementations9 Mar 2021 Ce Wang, Haimiao Zhang, Qian Li, Kun Shang, Yuanyuan Lyu, Bin Dong, S. Kevin Zhou

More importantly, we show that using such a sinogram extrapolation module significantly improves the generalization capability of the model on unseen datasets (e. g., COVID-19 and LIDC datasets) when compared to existing approaches.

Computed Tomography (CT)

One-Shot Medical Landmark Detection

2 code implementations8 Mar 2021 Qingsong Yao, Quan Quan, Li Xiao, S. Kevin Zhou

The success of deep learning methods relies on the availability of a large number of datasets with annotations; however, curating such datasets is burdensome, especially for medical images.

Self-Supervised Learning

Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets

no code implementations8 Mar 2021 Pengbo Liu, Li Xiao, S. Kevin Zhou

In each IL stage, we lose access to the previous annotations, whose knowledge is assumingly captured by the current model, and gain the access to a new dataset with annotations of new organ categories, from which we learn to update the organ segmentation model to include the new organs.

Incremental Learning

You Only Learn Once: Universal Anatomical Landmark Detection

1 code implementation8 Mar 2021 Heqin Zhu, QingsongYao, Li Xiao, S. Kevin Zhou

However, all of those methods are unary in the sense that a highly specialized network is trained for a single task say associated with a particular anatomical region.

U-DuDoNet: Unpaired dual-domain network for CT metal artifact reduction

no code implementations8 Mar 2021 Yuanyuan Lyu, Jiajun Fu, Cheng Peng, S. Kevin Zhou

Recently, both supervised and unsupervised deep learning methods have been widely applied on the CT metal artifact reduction (MAR) task.

Metal Artifact Reduction

Deep reinforcement learning in medical imaging: A literature review

no code implementations5 Mar 2021 S. Kevin Zhou, Hoang Ngan Le, Khoa Luu, Hien V. Nguyen, Nicholas Ayache

Deep reinforcement learning (DRL) augments the reinforcement learning framework, which learns a sequence of actions that maximizes the expected reward, with the representative power of deep neural networks.

Neural Architecture Search

CT Film Recovery via Disentangling Geometric Deformation and Illumination Variation: Simulated Datasets and Deep Models

no code implementations17 Dec 2020 Quan Quan, Qiyuan Wang, Liu Li, Yuanqi Du, S. Kevin Zhou

We also record all accompanying information related to the geometric deformation (such as 3D coordinate, depth, normal, and UV maps) and illumination variation (such as albedo map).

Computed Tomography (CT)

A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks

1 code implementation17 Dec 2020 Qingsong Yao, Zecheng He, Yi Lin, Kai Ma, Yefeng Zheng, S. Kevin Zhou

Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making.

Adversarial Attack Decision Making

Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models

1 code implementation16 Dec 2020 Pengbo Liu, Hu Han, Yuanqi Du, Heqin Zhu, Yinhao Li, Feng Gu, Honghu Xiao, Jun Li, Chunpeng Zhao, Li Xiao, Xinbao Wu, S. Kevin Zhou

Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.

Aggregative Self-Supervised Feature Learning from a Limited Sample

no code implementations14 Dec 2020 Jiuwen Zhu, Yuexiang Li, S. Kevin Zhou

Then, in self-aggregative SSL, we propose to self-complement an existing proxy task with an auxiliary loss function based on a linear centered kernel alignment metric, which explicitly promotes the exploring of where are uncovered by the features learned from a proxy task at hand to further boost the modeling capability.

Image Classification Self-Supervised Learning

Label-Free Segmentation of COVID-19 Lesions in Lung CT

no code implementations8 Sep 2020 Qingsong Yao, Li Xiao, Peihang Liu, S. Kevin Zhou

Scarcity of annotated images hampers the building of automated solution for reliable COVID-19 diagnosis and evaluation from CT. To alleviate the burden of data annotation, we herein present a label-free approach for segmenting COVID-19 lesions in CT via pixel-level anomaly modeling that mines out the relevant knowledge from normal CT lung scans.

COVID-19 Diagnosis Unsupervised Anomaly Detection

Limited View Tomographic Reconstruction Using a Deep Recurrent Framework with Residual Dense Spatial-Channel Attention Network and Sinogram Consistency

no code implementations3 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.

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

no code implementations2 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.

Bounding Maps for Universal Lesion Detection

no code implementations18 Jul 2020 Han Li, Hu Han, S. Kevin Zhou

The bounding maps (BMs) are used in two-stage anchor-based ULD frameworks to reduce the FP rate.

Region Proposal

Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detection

1 code implementation10 Jul 2020 Qingsong Yao, Zecheng He, Hu Han, S. Kevin Zhou

A comprehensive evaluation on a public dataset for cephalometric landmark detection demonstrates that the adversarial examples generated by ATI-FGSM break the CNN-based network more effectively and efficiently, compared with the original Iterative FGSM attack.

Adversarial Attack

Marginal loss and exclusion loss for partially supervised multi-organ segmentation

no code implementations8 Jul 2020 Gonglei Shi, Li Xiao, Yang Chen, S. Kevin Zhou

Annotating multiple organs in medical images is both costly and time-consuming; therefore, existing multi-organ datasets with labels are often low in sample size and mostly partially labeled, that is, a dataset has a few organs labeled but not all organs.

Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning

no code implementations10 Jun 2020 Jiuwen Zhu, Yuexiang Li, Yifan Hu, S. Kevin Zhou

To this end, self-supervised learning (SSL), as a potential solution for deficient annotated data, attracts increasing attentions from the community.

General Classification Image Classification +1

Human Recognition Using Face in Computed Tomography

no code implementations28 May 2020 Jiuwen Zhu, Hu Han, S. Kevin Zhou

With the mushrooming use of computed tomography (CT) images in clinical decision making, management of CT data becomes increasingly difficult.

Computed Tomography (CT) Decision Making +2

DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Prior

1 code implementation CVPR 2020 Bo Zhou, S. Kevin Zhou

In this work, we address the above two limitations by proposing a Dual Domain Recurrent Network (DuDoRNet) with deep T1 prior embedded to simultaneously recover k-space and images for accelerating the acquisition of MRI with a long imaging protocol.

MRI Reconstruction

First image then video: A two-stage network for spatiotemporal video denoising

1 code implementation2 Jan 2020 Ce Wang, S. Kevin Zhou, Zhiwei Cheng

This two-stage network, when trained in an end-to-end fashion, yields the state-of-the-art performances on the video denoising benchmark Vimeo90K dataset in terms of both denoising quality and computation.

Image Denoising Optical Flow Estimation +1

Encoding Metal Mask Projection for Metal Artifact Reduction in Computed Tomography

no code implementations2 Jan 2020 Yuanyuan Lyu, Wei-An Lin, Haofu Liao, Jing-Jing Lu, S. Kevin Zhou

Metal artifact reduction (MAR) in computed tomography (CT) is a notoriously challenging task because the artifacts are structured and non-local in the image domain.

Computed Tomography (CT) Metal Artifact Reduction

Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition

1 code implementation16 Sep 2019 Zeju Li, Han Li, Hu Han, Gonglei Shi, Jiannan Wang, S. Kevin Zhou

We hereby propose a decomposition generative adversarial network (DecGAN) to anatomically decompose a CXR image but with unpaired data.

Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation

no code implementations9 Sep 2019 Zengming Shen, Yifan Chen, S. Kevin Zhou, Bogdan Georgescu, Xuqi Liu, Thomas S. Huang

A self-inverse network shares several distinct advantages: only one network instead of two, better generalization and more restricted parameter space.

Image-to-Image Translation Translation

3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation

1 code implementation4 Sep 2019 Chao Huang, Hu Han, Qingsong Yao, Shankuan Zhu, S. Kevin Zhou

Instead of a collection of multiple models, it is highly desirable to learn a universal data representation for different tasks, ideally a single model with the addition of a minimal number of parameters steered to each task.

Image Classification Medical Image Segmentation

Deep Slice Interpolation via Marginal Super-Resolution, Fusion and Refinement

no code implementations15 Aug 2019 Cheng Peng, Wei-An Lin, Haofu Liao, Rama Chellappa, S. Kevin Zhou

We propose a marginal super-resolution (MSR) approach based on 2D convolutional neural networks (CNNs) for interpolating an anisotropic brain magnetic resonance scan along the highly under-sampled direction, which is assumed to axial without loss of generality.

Semantic Segmentation Super-Resolution

ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction

1 code implementation3 Aug 2019 Haofu Liao, Wei-An Lin, S. Kevin Zhou, Jiebo Luo

Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods that rely on synthesized metal artifacts for training.

Computed Tomography (CT) Image-to-Image Translation +3

Generative Mask Pyramid Network for CT/CBCT Metal Artifact Reduction with Joint Projection-Sinogram Correction

no code implementations29 Jun 2019 Haofu Liao, Wei-An Lin, Zhimin Huo, Levon Vogelsang, William J. Sehnert, S. Kevin Zhou, Jiebo Luo

A conventional approach to computed tomography (CT) or cone beam CT (CBCT) metal artifact reduction is to replace the X-ray projection data within the metal trace with synthesized data.

Computed Tomography (CT) Metal Artifact Reduction

Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction

1 code implementation5 Jun 2019 Haofu Liao, Wei-An Lin, Jianbo Yuan, S. Kevin Zhou, Jiebo Luo

Extensive experiments show that our method significantly outperforms the existing unsupervised models for image-to-image translation problems, and achieves comparable performance to existing supervised models on a synthesized dataset.

Computed Tomography (CT) Image-to-Image Translation +2

Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$)

no code implementations10 Mar 2019 Haofu Liao, Wei-An Lin, Jiarui Zhang, Jingdan Zhang, Jiebo Luo, S. Kevin Zhou

As the POI tracker is shift-invariant, $\text{POINT}^2$ is more robust to the initial pose of the 3D pre-intervention image.

Face Completion with Semantic Knowledge and Collaborative Adversarial Learning

no code implementations8 Dec 2018 Haofu Liao, Gareth Funka-Lea, Yefeng Zheng, Jiebo Luo, S. Kevin Zhou

Unlike a conventional background inpainting approach that infers a missing area from image patches similar to the background, face completion requires semantic knowledge about the target object for realistic outputs.

Facial Inpainting Semantic Segmentation

Select, Attend, and Transfer: Light, Learnable Skip Connections

no code implementations14 Apr 2018 Saeid Asgari Taghanaki, Aicha Bentaieb, Anmol Sharma, S. Kevin Zhou, Yefeng Zheng, Bogdan Georgescu, Puneet Sharma, Sasa Grbic, Zhoubing Xu, Dorin Comaniciu, Ghassan Hamarneh

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients.

Automatic Liver Segmentation Using an Adversarial Image-to-Image Network

no code implementations25 Jul 2017 Dong Yang, Daguang Xu, S. Kevin Zhou, Bogdan Georgescu, Mingqing Chen, Sasa Grbic, Dimitris Metaxas, Dorin Comaniciu

Automatic liver segmentation in 3D medical images is essential in many clinical applications, such as pathological diagnosis of hepatic diseases, surgical planning, and postoperative assessment.

Liver Segmentation

Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images

no code implementations7 Jul 2016 Hao Chen, Yefeng Zheng, Jin-Hyeong Park, Pheng-Ann Heng, S. Kevin Zhou

Accurate detection and segmentation of anatomical structures from ultrasound images are crucial for clinical diagnosis and biometric measurements.

Transfer Learning

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