no code implementations • 10 May 2022 • Cheng Xue, Lequan Yu, Pengfei Chen, Qi Dou, Pheng-Ann Heng
In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high quality annotated medical data.
no code implementations • 8 Apr 2022 • Yiqing Shen, Yuyin Zhou, Lequan Yu
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model.
1 code implementation • 9 Feb 2022 • Yuyin Zhou, Xianhang Li, Fengze Liu, Xuxi Chen, Lequan Yu, Cihang Xie, Matthew P. Lungren, Lei Xing
Specifically, our method dynamically adjusts the per-sample importance weight between the real observed labels and pseudo-labels, where the weights are efficiently determined in a meta process.
Ranked #5 on
Image Classification
on Clothing1M (using clean data)
(using extra training data)
no code implementations • 29 Sep 2021 • Ruichen Luo, Shoubo Hu, Lequan Yu
To this end, we study a new $\textit{selfish}$ variant of federated learning, in which the ultimate objective is to learn a model with optimal performance on internal clients $\textit{alone}$ instead of all clients.
1 code implementation • 28 Sep 2021 • Zhe Xu, Yixin Wang, Donghuan Lu, Lequan Yu, Jiangpeng Yan, Jie Luo, Kai Ma, Yefeng Zheng, Raymond Kai-yu Tong
Observing this, we ask an unexplored but interesting question: can we exploit the unlabeled data via explicit real label supervision for semi-supervised training?
Brain Tumor Segmentation
Semi-supervised Medical Image Segmentation
+1
no code implementations • 28 Sep 2021 • Lequan Yu, Zhicheng Zhang, Xiaomeng Li, Hongyi Ren, Wei Zhao, Lei Xing
We then design a novel FBP reconstruction loss to encourage the network to generate more perfect completion results and a residual-learning-based image refinement module to reduce the secondary artifacts in the reconstructed CT images.
no code implementations • 13 Sep 2021 • Yijun Yang, Shujun Wang, Pheng-Ann Heng, Lequan Yu
In this paper, we present a novel Hierarchical Consistency framework for Domain Generalization (HCDG) by ensembling Extrinsic Consistency and Intrinsic Consistency.
1 code implementation • 7 Sep 2021 • Hong-Yu Zhou, Jiansen Guo, Yinghao Zhang, Lequan Yu, Liansheng Wang, Yizhou Yu
Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community.
1 code implementation • 29 Mar 2021 • Junfei Xiao, Lequan Yu, Lei Xing, Alan Yuille, Yuyin Zhou
However, BN only calculates the global statistics at the batch level, and applies the same affine transformation uniformly across all spatial coordinates, which would suppress the image contrast of different semantic structures.
1 code implementation • 28 Feb 2021 • Zhicheng Zhang, Lequan Yu, Xiaokun Liang, Wei Zhao, Lei Xing
Low dose computed tomography (LDCT) has attracted more and more attention in routine clinical diagnosis assessment, therapy planning, etc., which can reduce the dose of X-ray radiation to patients.
1 code implementation • 7 Jan 2021 • Kang Li, Shujun Wang, Lequan Yu, Pheng-Ann Heng
In this way, the dual teacher models would transfer acquired inter- and intra-domain knowledge to the student model for further integration and exploitation.
no code implementations • 13 Oct 2020 • Shujun Wang, Lequan Yu, Kang Li, Xin Yang, Chi-Wing Fu, Pheng-Ann Heng
Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative.
no code implementations • 13 Oct 2020 • Shujun Wang, Yaxi Zhu, Lequan Yu, Hao Chen, Huangjing Lin, Xiangbo Wan, Xinjuan Fan, Pheng-Ann Hen
The multi-instance learning based on the most discriminative instances can be of great benefit for whole slide gastric image diagnosis.
no code implementations • 4 Oct 2020 • Kang Li, Lequan Yu, Shujun Wang, Pheng-Ann Heng
Considering multi-modality data with the same anatomic structures are widely available in clinic routine, in this paper, we aim to exploit the prior knowledge (e. g., shape priors) learned from one modality (aka., assistant modality) to improve the segmentation performance on another modality (aka., target modality) to make up annotation scarcity.
no code implementations • 16 Sep 2020 • Lequan Yu, Zhicheng Zhang, Xiaomeng Li, Lei Xing
Computed tomography (CT) has been widely used for medical diagnosis, assessment, and therapy planning and guidance.
1 code implementation • 21 Jul 2020 • Xiaomeng Li, Mengyu Jia, Md Tauhidul Islam, Lequan Yu, Lei Xing
The automatic diagnosis of various retinal diseases from fundus images is important to support clinical decision-making.
no code implementations • ECCV 2020 • Shujun Wang, Lequan Yu, Caizi Li, Chi-Wing Fu, Pheng-Ann Heng
To this end, we present a new domain generalization framework that learns how to generalize across domains simultaneously from extrinsic relationship supervision and intrinsic self-supervision for images from multi-source domains.
Ranked #16 on
Domain Generalization
on PACS
no code implementations • 13 Jul 2020 • Kang Li, Shujun Wang, Lequan Yu, Pheng-Ann Heng
Medical image annotations are prohibitively time-consuming and expensive to obtain.
no code implementations • 4 Jul 2020 • Yue Sun, Kun Gao, Zhengwang Wu, Zhihao Lei, Ying WEI, Jun Ma, Xiaoping Yang, Xue Feng, Li Zhao, Trung Le Phan, Jitae Shin, Tao Zhong, Yu Zhang, Lequan Yu, Caizi Li, Ramesh Basnet, M. Omair Ahmad, M. N. S. Swamy, Wenao Ma, Qi Dou, Toan Duc Bui, Camilo Bermudez Noguera, Bennett Landman, Ian H. Gotlib, Kathryn L. Humphreys, Sarah Shultz, Longchuan Li, Sijie Niu, Weili Lin, Valerie Jewells, Gang Li, Dinggang Shen, Li Wang
Deep learning-based methods have achieved state-of-the-art performance; however, one of major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners.
no code implementations • 28 Jun 2020 • Yingda Xia, Dong Yang, Zhiding Yu, Fengze Liu, Jinzheng Cai, Lequan Yu, Zhuotun Zhu, Daguang Xu, Alan Yuille, Holger Roth
Experiments on the NIH pancreas segmentation dataset and a multi-organ segmentation dataset show state-of-the-art performance of the proposed framework on semi-supervised medical image segmentation.
no code implementations • 6 Jun 2020 • Luyang Luo, Lequan Yu, Hao Chen, Quande Liu, Xi Wang, Jiaqi Xu, Pheng-Ann Heng
Recent researches have demonstrated that performance bottleneck exists in joint training on different CXR datasets, and few made efforts to address the obstacle.
1 code implementation • 15 May 2020 • Quande Liu, Lequan Yu, Luyang Luo, Qi Dou, Pheng Ann Heng
It is a consistency-based method which exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations, and leverages a self-ensembling model to produce high-quality consistency targets for the unlabeled data.
2 code implementations • 9 Feb 2020 • Quande Liu, Qi Dou, Lequan Yu, Pheng Ann Heng
However, the prostate MRIs from different sites present heterogeneity due to the differences in scanners and imaging protocols, raising challenges for effective ways of aggregating multi-site data for network training.
1 code implementation • 4 Nov 2019 • Xiaomeng Li, Xiao-Wei Hu, Lequan Yu, Lei Zhu, Chi-Wing Fu, Pheng-Ann Heng
In this paper, we present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring the internal relationship between the diseases with only image-level supervision.
1 code implementation • 10 Oct 2019 • Haoran Dou, Xin Yang, Jikuan Qian, Wufeng Xue, Hao Qin, Xu Wang, Lequan Yu, Shujun Wang, Yi Xiong, Pheng-Ann Heng, Dong Ni
In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US.
5 code implementations • 16 Jul 2019 • Lequan Yu, Shujun Wang, Xiaomeng Li, Chi-Wing Fu, Pheng-Ann Heng
We design a novel uncertainty-aware scheme to enable the student model to gradually learn from the meaningful and reliable targets by exploiting the uncertainty information.
no code implementations • 6 Jul 2019 • Xiaomeng Li, Lequan Yu, Chi-Wing Fu, Meng Fang, Pheng-Ann Heng
However, the importance of feature embedding, i. e., exploring the relationship among training samples, is neglected.
no code implementations • 30 Jun 2019 • Xiaomeng Li, Lequan Yu, Yueming Jin, Chi-Wing Fu, Lei Xing, Pheng-Ann Heng
Rare diseases have extremely low-data regimes, unlike common diseases with large amount of available labeled data.
1 code implementation • 26 Jun 2019 • Shujun Wang, Lequan Yu, Kang Li, Xin Yang, Chi-Wing Fu, Pheng-Ann Heng
The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets. In this work, we present an unsupervised domain adaptation framework, called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions.
no code implementations • 5 May 2019 • Xianzhi Li, Lequan Yu, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng
This paper presents a novel approach to learn and detect distinctive regions on 3D shapes.
1 code implementation • 28 Feb 2019 • Xiaomeng Li, Lequan Yu, Hao Chen, Chi-Wing Fu, Lei Xing, Pheng-Ann Heng
In this paper, we present a novel semi-supervised method for medical image segmentation, where the network is optimized by the weighted combination of a common supervised loss for labeled inputs only and a regularization loss for both labeled and unlabeled data.
no code implementations • 20 Feb 2019 • Shujun Wang, Lequan Yu, Xin Yang, Chi-Wing Fu, Pheng-Ann Heng
In this paper, we present a novel patchbased Output Space Adversarial Learning framework (pOSAL) to jointly and robustly segment the OD and OC from different fundus image datasets.
Ranked #2 on
Optic Disc Segmentation
on REFUGE
no code implementations • 29 Nov 2018 • Yingda Xia, Fengze Liu, Dong Yang, Jinzheng Cai, Lequan Yu, Zhuotun Zhu, Daguang Xu, Alan Yuille, Holger Roth
Meanwhile, a fully-supervised method based on our approach achieved state-of-the-art performances on both the LiTS liver tumor segmentation and the Medical Segmentation Decathlon (MSD) challenge, demonstrating the robustness and value of our framework, even when fully supervised training is feasible.
no code implementations • 12 Aug 2018 • Xiaomeng Li, Lequan Yu, Hao Chen, Chi-Wing Fu, Pheng-Ann Heng
In this paper, we present a novel semi-supervised method for skin lesion segmentation, where the network is optimized by the weighted combination of a common supervised loss for labeled inputs only and a regularization loss for both labeled and unlabeled data.
no code implementations • ECCV 2018 • Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng
In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds.
1 code implementation • 8 Jul 2018 • Xiaomeng Li, Lequan Yu, Chi-Wing Fu, Pheng-Ann Heng
Our best model achieves 77. 23\%(JA) on the test dataset, outperforming the state-of-the-art challenging methods and further demonstrating the effectiveness of our proposed deeply supervised rotation equivariant segmentation network.
3 code implementations • CVPR 2018 • Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng
Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data.
Ranked #3 on
Point Cloud Super Resolution
on SHREC15
2 code implementations • 2 Aug 2017 • Lequan Yu, Jie-Zhi Cheng, Qi Dou, Xin Yang, Hao Chen, Jing Qin, Pheng-Ann Heng
Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data.
no code implementations • 6 Dec 2016 • Xin Yang, Lequan Yu, Lingyun Wu, Yi Wang, Dong Ni, Jing Qin, Pheng-Ann Heng
Additionally, our approach is general and can be extended to other medical image segmentation tasks, where boundary incompleteness is one of the main challenges.
3 code implementations • 21 Aug 2016 • Hao Chen, Qi Dou, Lequan Yu, Pheng-Ann Heng
Recently deep residual learning with residual units for training very deep neural networks advanced the state-of-the-art performance on 2D image recognition tasks, e. g., object detection and segmentation.
no code implementations • 3 Jul 2016 • Qi Dou, Hao Chen, Yueming Jin, Lequan Yu, Jing Qin, Pheng-Ann Heng
Automatic liver segmentation from CT volumes is a crucial prerequisite yet challenging task for computer-aided hepatic disease diagnosis and treatment.
no code implementations • CVPR 2016 • Hao Chen, Xiaojuan Qi, Lequan Yu, Pheng-Ann Heng
The morphology of glands has been used routinely by pathologists to assess the malignancy degree of adenocarcinomas.
Ranked #3 on
Optic Disc Segmentation
on REFUGE