In this paper, we introduce a novel Fourier-anchor-based DTS framework called Fourier Feature Pyramid Network (FFPN) to address the aforementioned issues.
It can prevent the highly unfavorable scenarios, such as encountering a blank mask as the initial input after the first interaction.
In this paper, we propose RLIPv2, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data.
Ranked #1 on Zero-Shot Human-Object Interaction Detection on HICO-DET (using extra training data)
Second, to better preserve the integrity and textural information of US images, we implemented a dual-decoder that decouples the content and textural features in the generator.
In this paper, a semi-supervised Dual-stream Self-Attentive Adversarial Graph Contrastive learning framework (termed as DS-AGC) is proposed to tackle the challenge of limited labeled data in cross-subject EEG-based emotion recognition.
In addition, we design an object-level temporal aggregation (OTA) module that can automatically filter low-quality features and efficiently integrate temporal information from multiple frames to improve the accuracy of tumor diagnosis.
Ultrasound (US) imaging is a popular tool in clinical diagnosis, offering safety, repeatability, and real-time capabilities.
In this study, we construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyperparameter-free balance on multiple losses.
The Transformer structures have been widely used in computer vision and have recently made an impact in the area of medical image registration.
Deep neural networks have been widely applied in dichotomous medical image segmentation (DMIS) of many anatomical structures in several modalities, achieving promising performance.
First, to avoid the requirement of laborious and unreliable annotation, we propose a novel and effective video classification network for weakly-supervised CSG.
Second, we introduce a regularization technique that utilizes style interpolation consistency in the frequency space to encourage self-consistency in the logit space of the model output.
no code implementations • 28 Apr 2023 • Yuhao Huang, Xin Yang, Lian Liu, Han Zhou, Ao Chang, Xinrui Zhou, Rusi Chen, Junxuan Yu, Jiongquan Chen, Chaoyu Chen, Haozhe Chi, Xindi Hu, Deng-Ping Fan, Fajin Dong, Dong Ni
We conducted a comprehensive analysis of different SAM testing strategies on the so-called COSMOS 553K dataset.
Ultrasound is the primary modality to examine fetal growth during pregnancy, while the image quality could be affected by various factors.
To address these issues, we propose a non-iterative method where a stream of varying (pacing) pseudo-masks teach a network via consistency training, named PacingPseudo.
The task of Human-Object Interaction (HOI) detection targets fine-grained visual parsing of humans interacting with their environment, enabling a broad range of applications.
Ranked #14 on Human-Object Interaction Detection on HICO-DET
Breast cancer is one of the leading causes of cancer deaths in women.
To overcome this, we propose a novel deep learning framework called multi-attribute attention network (MAA-Net) that is designed to mimic the clinical diagnosis process.
First, leveraging the advantages of self- and fully-supervised learning, our proposed system is trained in weakly-supervised manner for keypoint detection.
no code implementations • 1 Jul 2022 • Yuxin Zou, Haoran Dou, Yuhao Huang, Xin Yang, Jikuan Qian, Chaojiong Zhen, Xiaodan Ji, Nishant Ravikumar, Guoqiang Chen, Weijun Huang, Alejandro F. Frangi, Dong Ni
First, we formulate SP localization in 3D US as a tangent-point-based problem in RL to restructure the action space and significantly reduce the search space.
Deep segmentation models often face the failure risks when the testing image presents unseen distributions.
Furthermore, finding an optimal way to integrate multi-view information also relies on the experience of clinicians and adds further difficulty to accurate diagnosis.
In this work, we propose to revisit the classic regression tasks with novel investigations on directly optimizing the fine-grained correlation losses.
Our main contributions include: 1) we present the first work that can synthesize realistic B-mode US images with high-resolution and customized texture editing features; 2) to enhance structural details of generated images, we propose to introduce auxiliary sketch guidance into a conditional GAN.
The hybrid framework consists of a pre-trained backbone and several searched cells (i. e., network building blocks), which takes advantage of the strengths of both NAS and the expert knowledge from existing convolutional neural networks.
Specifically, We propose to utilize a Verb Semantic Model (VSM) and use semantic aggregation to profit from this object-guided hierarchy.
Ranked #5 on Human-Object Interaction Detection on V-COCO
Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods.
Automatic segmentation of abdominal organs in computed tomography (CT) images can support radiation therapy and image-guided surgery workflows.
For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain?
Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers.
Within each interaction field, we apply DR to predict the relation matrix and DW to predict the dynamic walk offsets in a joint-processing manner, thus forming a person-specific interaction graph.
Ranked #3 on Group Activity Recognition on Volleyball
no code implementations • 11 Aug 2021 • Shuangchi He, Zehui Lin, Xin Yang, Chaoyu Chen, Jian Wang, Xue Shuang, Ziwei Deng, Qin Liu, Yan Cao, Xiduo Lu, Ruobing Huang, Nishant Ravikumar, Alejandro Frangi, Yuanji Zhang, Yi Xiong, Dong Ni
In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously.
Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation.
A style transfer model with style fusion is employed to generate the curriculum samples.
In this paper, we propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences.
Based on the continuity between slices/frames and the common spatial layout of organs across volumes/sequences, we introduced a novel bootstrap self-supervised representation learning method by leveraging the predictable possibility of neighboring slices.
In this study, we propose a multi-task framework to learn the relationships among landmarks and structures jointly and automatically evaluate DDH.
First, our proposed method is general and it can accurately localize multiple SPs in different challenging US datasets.
Our proposed framework is general and shows the potential to improve the efficiency of anatomical landmark detection.
2D US has to perform scanning for each SP, which is time-consuming and operator-dependent.
Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis.
no code implementations • 10 Oct 2020 • Haoming Li, Xin Yang, Jiamin Liang, Wenlong Shi, Chaoyu Chen, Haoran Dou, Rui Li, Rui Gao, Guangquan Zhou, Jinghui Fang, Xiaowen Liang, Ruobing Huang, Alejandro Frangi, Zhiyi Chen, Dong Ni
However, the lack of sharp boundaries in US images still remains an inherent challenge for segmentation.
Based on the zero-shot style transfer to remove appearance shift and test-time augmentation to explore diverse underlying anatomy, our proposed method is effective in combating the appearance shift.
The efficacy of our network is verified from a collected dataset of 418 patients with 145 benign tumors and 273 malignant tumors.
no code implementations • 30 Jul 2020 • Yuhao Huang, Xin Yang, Rui Li, Jikuan Qian, Xiaoqiong Huang, Wenlong Shi, Haoran Dou, Chaoyu Chen, Yuanji Zhang, Huanjia Luo, Alejandro Frangi, Yi Xiong, Dong Ni
In this study, we propose a novel Multi-Agent Reinforcement Learning (MARL) framework to localize multiple uterine SPs in 3D US simultaneously.
In this paper, we propose the first fully-automated solution to segment the whole fetal head in US volumes.
Automatic segmentation of the cortical plate, on the other hand, is challenged by the relatively low resolution of the reconstructed fetal brain MRI scans compared to the thin structure of the cortical plate, partial voluming, and the wide range of variations in the morphology of the cortical plate as the brain matures during gestation.
no code implementations • 26 Apr 2020 • Zhaohan Xiong, Qing Xia, Zhiqiang Hu, Ning Huang, Cheng Bian, Yefeng Zheng, Sulaiman Vesal, Nishant Ravikumar, Andreas Maier, Xin Yang, Pheng-Ann Heng, Dong Ni, Caizi Li, Qianqian Tong, Weixin Si, Elodie Puybareau, Younes Khoudli, Thierry Geraud, Chen Chen, Wenjia Bai, Daniel Rueckert, Lingchao Xu, Xiahai Zhuang, Xinzhe Luo, Shuman Jia, Maxime Sermesant, Yashu Liu, Kuanquan Wang, Davide Borra, Alessandro Masci, Cristiana Corsi, Coen de Vente, Mitko Veta, Rashed Karim, Chandrakanth Jayachandran Preetha, Sandy Engelhardt, Menyun Qiao, Yuanyuan Wang, Qian Tao, Marta Nunez-Garcia, Oscar Camara, Nicolo Savioli, Pablo Lamata, Jichao Zhao
Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) widely used for visualizing diseased cardiac structures, is a crucial first step for clinical diagnosis and treatment.
Efficiently synthesizing realistic, editable and high resolution US images can solve the problems.
no code implementations • 1 Apr 2020 • Chaoyu Chen, Xin Yang, Ruobing Huang, Wenlong Shi, Shengfeng Liu, Mingrong Lin, Yuhao Huang, Yong Yang, Yuanji Zhang, Huanjia Luo, Yankai Huang, Yi Xiong, Dong Ni
The performance of the proposed framework is evaluated on a 3D US dataset to detect five key fetal facial landmarks.
In this paper, we propose a novel and intuitive framework to remove the appearance shift, and hence improve the generalization ability of DNNs.
(i) This is the first work about 3D pose estimation of fetus in the literature.
In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US.
In this paper, we propose an effective framework for simultaneous segmentation and landmark localization in prenatal ultrasound volumes.
Myocardium segmentation of late gadolinium enhancement (LGE) Cardiac MR images is important for evaluation of infarction regions in clinical practice.
Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers.
In this paper, we propose a fully-automated framework to segment left atrium in gadolinium-enhanced MR volumes.
Additionally, our approach is general and can be extended to other medical image segmentation tasks, where boundary incompleteness is one of the main challenges.