Junwei Yang

Junwei Yang

Auto-generated profile, based on publicly available information

Junwei Yang

School of Biomedical Engineering and State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
CWChong Wang
Chong Wang
ZCZhiming Cui
Zhiming Cui
JYJunwei Yang
Junwei Yang
MHMiaofei Han
Miaofei Han
GCGustavo Carneiro
Gustavo Carneiro
DSDinggang Shen
Dinggang Shen
Accurate bowel segmentation is essential for diagnosis and treatment of bowel cancers. Unfortunately, segmenting the entire bowel in CT images is quite challenging due to unclear boundary, large shape, size, and appearance variations, as well as diverse filling status within the bowel. In this paper, we present a novel two-stage framework, named BowelNet, to handle the challenging task of bowel segmentation in CT images, with two stages of 1) jointly localizing all types of the bowel, and 2) finely segmenting each type of the bowel. Specifically, in the first stage, we learn a unified localization network from both partially- and fully-labeled CT images to robustly detect all types of the bowel. To better capture unclear bowel boundary and learn complex bowel shapes, in the second stage, we propose to jointly learn semantic information (i.e., bowel segmentation mask) and geometric representations (i.e., bowel boundary and bowel skeleton) for fine bowel segmentation in a multi-task learning scheme. Moreover, we further propose to learn a meta segmentation network via pseudo labels to improve segmentation accuracy. By evaluating on a large abdominal CT dataset, our proposed BowelNet method can achieve Dice scores of 0.764, 0.848, 0.835, 0.774, and 0.824 in segmenting the duodenum, jejunum-ileum, colon, sigmoid, and rectum, respectively. These results demonstrate the effectiveness of our proposed BowelNet framework in segmenting the entire bowel from CT images.

7 December 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
JYJunwei Yang
Junwei Yang
XLXiao-Xin Li
Xiao-Xin Li
FLFeihong Liu
Feihong Liu
DNDong Nie
Dong Nie
PLPietro Lio
Pietro Lio
DSDinggang Shen
Dinggang Shen
Recent studies on multi-contrast MRI reconstruction have demonstrated the potential of further accelerating MRI acquisition by exploiting correlation between contrasts. Most of the state-of-the-art approaches have achieved improvement through the development of network architectures for fixed under-sampling patterns, without considering inter-contrast correlation in the under-sampling pattern design. On the other hand, sampling pattern learning methods have shown better reconstruction performance than those with fixed under-sampling patterns. However, most under-sampling pattern learning algorithms are designed for single contrast MRI without exploiting complementary information between contrasts. To this end, we propose a framework to optimize the under-sampling pattern of a target MRI contrast which complements the acquired fully-sampled reference contrast. Specifically, a novel image synthesis network is introduced to extract the redundant information contained in the reference contrast, which is exploited in the subsequent joint pattern optimization and reconstruction network. We have demonstrated superior performance of our learned under-sampling patterns on both public and in-house datasets, compared to the commonly used under-sampling patterns and state-of-the-art methods that jointly optimize the reconstruction network and the under-sampling patterns, up to 8-fold under-sampling factor.

30 December 2024 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
YLYuxuan Liu
Yuxuan Liu
KSKaicong Sun
Kaicong Sun
HQHaikun Qi
Haikun Qi
JYJunwei Yang
Junwei Yang
XZXiaopeng Zong
Xiaopeng Zong
DSDinggang Shen
Dinggang Shen
Multi-parametric magnetic resonance imaging (MRI) can provide complementary quantitative information by generating multi-parametric maps and is becoming a promising imaging technique for advanced medical diagnosis. However, multi-parametric MRI requires longer acquisition time than normal MRI scanning. The existing reconstruction methods for accelerated multi-parametric MRI suffer from suboptimal performance due to stagewise optimization, and inefficient utilization of intra- and inter-contrast information. To address these challenges, we propose an all-in-one joint Sampling, Reconstruction, and Mapping network, dubbed as SRM-Net, for multi-parametric MRI reconstruction on multi-coil and multi-contrast MR images. Specifically, our model consists of three modules including sampling, reconstruction, and mapping. In the sampling module, we introduce a sampling scheme to generate individually-optimized sampling pattern across multicontrast images. In the reconstruction module, we adopt a spatio-temporal attention mechanism, which is embedded in a dual-domain-based unrolling framework, to better exploit inter- and intra-contrast correlations. In the mapping module, we employ multi-layer perceptron to model complex nonlinear mapping. Integrating Sampling, Reconstruction, and Mapping, our SRM-Net enables the end-toend learning paradigm. Experimental results show that our SRM-Net generates superior multi-parametric maps including T1, T2∗, and PD for brain on 3T MR scanner compared to state-of-the-art methods, and meanwhile provides promising intermediate weighted MR images. Our code is available at https://github.com/aloneForLiu/fast_mri.

29 November 2019 in bioRxiv
Verified
Preprint
Open access
PDF file
JYJunwei Yang
Junwei Yang
DWDuo Wang
Duo Wang
CRColleen Rollins
Colleen Rollins
MLMatthew Leming
Matthew Leming
PLPietro Lio
Pietro Lio
ACArnaud Cachia
Arnaud Cachia
Many architectures of deep neural networks have been designed to solve specific biomedical problems, among which segmentation is a critical step to detect and locate the boundaries of the target object from an image. In this paper, we develop a deep learning based framework to automatically segment the paracingulate sulcus (PCS) from the MRI scan and estimate lengths for its segments. The study is the first work on segmentation and characterisation of the PCS, and the model achieves a Dice score of over 0.77 on segmentation, which demonstrates its potential for clinical use to assist human annotation. Moreover, the proposed architecture as a solution can be generalised to other problems where the object has similar patterns.

12 December 2022 in Computerized Medical Imaging and Graphics
Verified
Journal Article
Closed access
FLFeihong Liu
Feihong Liu
JYJunwei Yang
Junwei Yang
MFMingyue Feng
Mingyue Feng
ZCZhiming Cui
Zhiming Cui
XHXiaowei He
Xiaowei He
DSDinggang Shen
Dinggang Shen