Search Results for author: Dong Wei

Found 46 papers, 16 papers with code

Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes

no code implementations25 Mar 2024 Tianwei Zhang, Dong Wei, Mengmeng Zhu, Shi Gu, Yefeng Zheng

In this work, we propose two complementary pretext tasks for this group of medical image data based on the spatial relationship of the imaging planes.

Anatomy Representation Learning +3

Federated Modality-specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation

1 code implementation18 Mar 2024 Qian Dai, Dong Wei, Hong Liu, Jinghan Sun, Liansheng Wang, Yefeng Zheng

In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posing inter-modal heterogeneity as a challenge to effectively training a global model on all participants' data.

Brain Tumor Segmentation Federated Learning +1

Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retinal OCT Images with Full and Sparse Annotations

1 code implementation4 Dec 2023 Hong Liu, Dong Wei, Donghuan Lu, Xiaoying Tang, Liansheng Wang, Yefeng Zheng

Experiments on a synthetic dataset and three public clinical datasets show that our framework can effectively align the B-scans for potential motion correction, and achieves superior performance to state-of-the-art 2D deep learning methods in terms of both layer segmentation accuracy and cross-B-scan 3D continuity in both fully and semi-supervised settings, thus offering more clinical values than previous works.


Automatic view plane prescription for cardiac magnetic resonance imaging via supervision by spatial relationship between views

1 code implementation22 Sep 2023 Dong Wei, Yawen Huang, Donghuan Lu, Yuexiang Li, Yefeng Zheng

Then, a multi-view planning strategy is proposed to aggregate information from the predicted heatmaps for all the source views of a target plane, for a globally optimal prescription, mimicking the similar strategy practiced by skilled human prescribers.


A Global Transport Capacity Risk Prediction Method for Rail Transit Based on Gaussian Bayesian Network

no code implementations3 Aug 2023 Zhang Zhengyang, Dong Wei, Liu jun, Sun Xinya, Ji Yindong

This method obtains the training data of the prediction model based on the simulation model of the rail transit system with a three-layer structure including rail transit network, train flow and passenger flow.

Gait Cycle-Inspired Learning Strategy for Continuous Prediction of Knee Joint Trajectory from sEMG

no code implementations25 Jul 2023 Xueming Fu, Hao Zheng, Luyan Liu, Wenjuan Zhong, Haowen Liu, Wenxuan Xiong, Yuyang Zhang, Yifeng Chen, Dong Wei, Mingjie Dong, Yefeng Zheng, Mingming Zhang

This paper proposes a model integrating two gait cycle-inspired learning strategies to mitigate the challenge for predicting human knee joint trajectory.

You've Got Two Teachers: Co-evolutionary Image and Report Distillation for Semi-supervised Anatomical Abnormality Detection in Chest X-ray

no code implementations18 Jul 2023 Jinghan Sun, Dong Wei, Zhe Xu, Donghuan Lu, Hong Liu, Liansheng Wang, Yefeng Zheng

Inversely, we also use the prediction of the vision detection model for abnormality-guided pseudo classification label refinement (APCLR) in the auxiliary report classification task, and propose a co-evolution strategy where the vision and report models mutually promote each other with RPDLR and APCLR performed alternatively.

Anomaly Detection Pseudo Label

Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis

no code implementations23 May 2023 Dong Wei, Xiaoning Sun, Huaijiang Sun, Bin Li, Shengxiang Hu, Weiqing Li, Jianfeng Lu

The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently.

Motion Synthesis valid

M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities

1 code implementation9 Mar 2023 Hong Liu, Dong Wei, Donghuan Lu, Jinghan Sun, Liansheng Wang, Yefeng Zheng

In the first stage, a multimodal masked autoencoder (M3AE) is proposed, where both random modalities (i. e., modality dropout) and random patches of the remaining modalities are masked for a reconstruction task, for self-supervised learning of robust multimodal representations against missing modalities.

Brain Tumor Segmentation Representation Learning +3

RECIST Weakly Supervised Lesion Segmentation via Label-Space Co-Training

no code implementations1 Mar 2023 Lianyu Zhou, Dong Wei, Donghuan Lu, Wei Xue, Liansheng Wang, Yefeng Zheng

As an essential indicator for cancer progression and treatment response, tumor size is often measured following the response evaluation criteria in solid tumors (RECIST) guideline in CT slices.

Lesion Segmentation Weakly supervised segmentation

Lesion Guided Explainable Few Weak-shot Medical Report Generation

1 code implementation16 Nov 2022 Jinghan Sun, Dong Wei, Liansheng Wang, Yefeng Zheng

To this end, we propose a lesion guided explainable few weak-shot medical report generation framework that learns correlation between seen and novel classes through visual and semantic feature alignment, aiming to generate medical reports for diseases not observed in training.

Medical Report Generation

Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction

no code implementations12 Oct 2022 Dong Wei, Huaijiang Sun, Bin Li, Jianfeng Lu, Weiqing Li, Xiaoning Sun, Shengxiang Hu

This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence.

motion prediction Stochastic Human Motion Prediction

A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays

1 code implementation5 Sep 2022 Haoqin Ji, Haozhe Liu, Yuexiang Li, Jinheng Xie, Nanjun He, Yawen Huang, Dong Wei, Xinrong Chen, Linlin Shen, Yefeng Zheng

Such a point annotation setting can provide weakly instance-level information for abnormality localization with a marginal annotation cost.

Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation

1 code implementation18 Jul 2022 Xinyu Shi, Dong Wei, Yu Zhang, Donghuan Lu, Munan Ning, Jiashun Chen, Kai Ma, Yefeng Zheng

A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images.

Few-Shot Semantic Segmentation Segmentation +1

mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation

1 code implementation6 Jun 2022 Yao Zhang, Nanjun He, Jiawei Yang, Yuexiang Li, Dong Wei, Yawen Huang, Yang Zhang, Zhiqiang He, Yefeng Zheng

Concretely, we propose a novel multimodal Medical Transformer (mmFormer) for incomplete multimodal learning with three main components: the hybrid modality-specific encoders that bridge a convolutional encoder and an intra-modal Transformer for both local and global context modeling within each modality; an inter-modal Transformer to build and align the long-range correlations across modalities for modality-invariant features with global semantics corresponding to tumor region; a decoder that performs a progressive up-sampling and fusion with the modality-invariant features to generate robust segmentation.

Brain Tumor Segmentation Segmentation +1

Myocardial Segmentation of Late Gadolinium Enhanced MR Images by Propagation of Contours from Cine MR Images

no code implementations21 May 2022 Dong Wei, Ying Sun, Ping Chai, Adrian Low, Sim Heng Ong

Automatic segmentation of myocardium in Late Gadolinium Enhanced (LGE) Cardiac MR (CMR) images is often difficult due to the intensity heterogeneity resulting from accumulation of contrast agent in infarcted areas.


A Comprehensive 3-D Framework for Automatic Quantification of Late Gadolinium Enhanced Cardiac Magnetic Resonance Images

no code implementations21 May 2022 Dong Wei, Ying Sun, Sim-Heng Ong, Ping Chai, Lynette L Teo, Adrian F Low

To achieve accurate quantification, LGE CMR images need to be processed in two steps: segmentation of the myocardium followed by classification of infarcts within the segmented myocardium.


Learning Shape Priors by Pairwise Comparison for Robust Semantic Segmentation

no code implementations23 Apr 2022 Cong Xie, Hualuo Liu, Shilei Cao, Dong Wei, Kai Ma, Liansheng Wang, Yefeng Zheng

A cosine similarity based attention module is proposed to fuse the information from both encoders, to utilize both types of prior information encoded by the template-encoder and model the inter-subject similarity for each foreground class.

Semantic Segmentation

Deep Convolutional Neural Networks for Molecular Subtyping of Gliomas Using Magnetic Resonance Imaging

no code implementations10 Mar 2022 Dong Wei, Yiming Li, Yinyan Wang, Tianyi Qian, Yefeng Zheng

Methods: A DCNN model was developed for the prediction of the five glioma subtypes based on a hierarchical classification paradigm.

Conquering Data Variations in Resolution: A Slice-Aware Multi-Branch Decoder Network

no code implementations7 Mar 2022 Shuxin Wang, Shilei Cao, Zhizhong Chai, Dong Wei, Kai Ma, Liansheng Wang, Yefeng Zheng

Based on the aforementioned innovations, we achieve state-of-the-art results on the MICCAI 2017 Liver Tumor Segmentation (LiTS) dataset.

Segmentation Tumor Segmentation

Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retina OCT Images

1 code implementation4 Mar 2022 Hong Liu, Dong Wei, Donghuan Lu, Yuexiang Li, Kai Ma, Liansheng Wang, Yefeng Zheng

To the best of our knowledge, this is the first study that attempts 3D retinal layer segmentation in volumetric OCT images based on CNNs.


Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship

no code implementations31 Dec 2021 Quanziang Wang, Renzhen Wang, Yuexiang Li, Dong Wei, Kai Ma, Yefeng Zheng, Deyu Meng

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data.

Continual Learning Meta-Learning

A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data

no code implementations18 Oct 2021 Hengji Cui, Dong Wei, Kai Ma, Shi Gu, Yefeng Zheng

In this work, we propose a unified framework for generalized low-shot (one- and few-shot) medical image segmentation based on distance metric learning (DML).

Image Segmentation Medical Image Segmentation +3

Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification

1 code implementation9 Oct 2021 Jinghan Sun, Dong Wei, Kai Ma, Liansheng Wang, Yefeng Zheng

Second, we integrate the URL with pseudo-label supervised classification for effective self-distillation of the knowledge about the rare diseases, composing a hybrid approach taking advantages of both unsupervised and (pseudo-) supervised learning on the base dataset.

Classification Few-Shot Learning +2

Training Automatic View Planner for Cardiac MR Imaging via Self-Supervision by Spatial Relationship between Views

1 code implementation24 Sep 2021 Dong Wei, Kai Ma, Yefeng Zheng

Then, a multi-view planning strategy is proposed to aggregate information from the predicted heatmaps for all the source views of a target view, for a globally optimal prescription.


ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones

no code implementations24 Aug 2021 Shan An, Guangfu Che, Jinghao Guo, Haogang Zhu, Junjie Ye, Fangru Zhou, Zhaoqi Zhu, Dong Wei, Aishan Liu, Wei zhang

To this concern, this work proposes a real-time augmented reality virtual shoe try-on system for smartphones, namely ARShoe.

Pose Estimation Virtual Try-on

Multi-Anchor Active Domain Adaptation for Semantic Segmentation

2 code implementations ICCV 2021 Munan Ning, Donghuan Lu, Dong Wei, Cheng Bian, Chenglang Yuan, Shuang Yu, Kai Ma, Yefeng Zheng

Unsupervised domain adaption has proven to be an effective approach for alleviating the intensive workload of manual annotation by aligning the synthetic source-domain data and the real-world target-domain samples.

Active Learning Domain Adaptation +1

A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework

no code implementations18 Aug 2021 Munan Ning, Cheng Bian, Dong Wei, Chenglang Yuan, Yaohua Wang, Yang Guo, Kai Ma, Yefeng Zheng

Domain shift happens in cross-domain scenarios commonly because of the wide gaps between different domains: when applying a deep learning model well-trained in one domain to another target domain, the model usually performs poorly.

Representation Learning Unsupervised Domain Adaptation

RECIST-Net: Lesion detection via grouping keypoints on RECIST-based annotation

no code implementations19 Jul 2021 Cong Xie, Shilei Cao, Dong Wei, HongYu Zhou, Kai Ma, Xianli Zhang, Buyue Qian, Liansheng Wang, Yefeng Zheng

Universal lesion detection in computed tomography (CT) images is an important yet challenging task due to the large variations in lesion type, size, shape, and appearance.

Computed Tomography (CT) Lesion Detection +1

Generalized Organ Segmentation by Imitating One-shot Reasoning using Anatomical Correlation

no code implementations30 Mar 2021 Hong-Yu Zhou, Hualuo Liu, Shilei Cao, Dong Wei, Chixiang Lu, Yizhou Yu, Kai Ma, Yefeng Zheng

In this paper, we show that such process can be integrated into the one-shot segmentation task which is a very challenging but meaningful topic.

One-Shot Segmentation Organ Segmentation +1

Fast and Incremental Loop Closure Detection with Deep Features and Proximity Graphs

2 code implementations29 Sep 2020 Shan An, Haogang Zhu, Dong Wei, Konstantinos A. Tsintotas, Antonios Gasteratos

In recent years, the robotics community has extensively examined methods concerning the place recognition task within the scope of simultaneous localization and mapping applications. This article proposes an appearance-based loop closure detection pipeline named ``FILD++" (Fast and Incremental Loop closure Detection). First, the system is fed by consecutive images and, via passing them twice through a single convolutional neural network, global and local deep features are extracted. Subsequently, a hierarchical navigable small-world graph incrementally constructs a visual database representing the robot's traversed path based on the computed global features. Finally, a query image, grabbed each time step, is set to retrieve similar locations on the traversed route. An image-to-image pairing follows, which exploits local features to evaluate the spatial information.

Loop Closure Detection Simultaneous Localization and Mapping

Learning from Manipulable Signals

no code implementations17 Jul 2020 Mehmet Ekmekci, Leandro Gorno, Lucas Maestri, Jian Sun, Dong Wei

The principal learns about the agent's type from a noisy performance measure, which can be manipulated by the agent via a costly and hidden action.

Superpixel-Guided Label Softening for Medical Image Segmentation

no code implementations17 Jul 2020 Hang Li, Dong Wei, Shilei Cao, Kai Ma, Liansheng Wang, Yefeng Zheng

If a superpixel intersects with the annotation boundary, we consider a high probability of uncertain labeling within this area.

Image Segmentation Medical Image Segmentation +2

Learning and Exploiting Interclass Visual Correlations for Medical Image Classification

no code implementations13 Jul 2020 Dong Wei, Shilei Cao, Kai Ma, Yefeng Zheng

In this paper, we present the Class-Correlation Learning Network (CCL-Net) to learn interclass visual correlations from given training data, and produce soft labels to help with classification tasks.

General Classification Image Classification +2

Optimal Attention Management: A Tractable Framework

no code implementations13 Jun 2020 Elliot Lipnowski, Laurent Mathevet, Dong Wei

We study optimal information provision in a tractable model with quadratic payoffs where full disclosure is not optimal.


Population pharmacokinetics and dosing regimen optimization of tacrolimus in Chinese lung transplant recipients

no code implementations1 Feb 2020 Xiaojun Cai, Huizhu Song, Zheng Jiao, Hang Yang, Min Zhu, Chengyu Wang, Dong Wei, Lingzhi Shi, Bo Wu, Jinyu Chen

Given the nonlinear kinetics of tacrolimus and large variability, population pharmacokinetic model should be combined with therapeutic drug monitoring to optimize individualized therapy.

OctopusNet: A Deep Learning Segmentation Network for Multi-modal Medical Images

no code implementations5 Jun 2019 Yu Chen, Jia-Wei Chen, Dong Wei, Yuexiang Li, Yefeng Zheng

Two approaches are widely used in the literature to fuse multiple modalities in the segmentation networks: early-fusion (which stacks multiple modalities as different input channels) and late-fusion (which fuses the segmentation results from different modalities at the very end).


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