Shanghai Jiaotong University
Institute of Medical Robotics
CITI
The Center for Image-Guided Therapy and Interventions is one of the ten centers of the Institute of Medical Robotics (IMR), Shanghai Jiao Tong University (SJTU), and was established on January 1, 2019. The center focuses on the development and transformation of minimally invasive precision medical technology for major diseases such as tumor, cardiovascular and stroke. There are three PIs in the center, including a "Cross-century Outstanding Talent of the Ministry of Education" and "Shanghai Shuguang Scholar". Its projects include the construction of a public platform for the medical imaging in SJTU and a public computing platform for deep learning in IMR. The center currently purchases equipment worth 25 million yuan, including a 1.5T magnetic resonance scanner, a digital blood vessel silhouette machine, a three-dimensional Doppler ultrasound scanner and a DGX-2 deep learning computing platform.
Research Goals: The center develops a multi-mode image navigation intervention platform to realize the segmentation, registration, visualization and fusion of high-dimensional multi-mode image data, as well as the system integration of intelligent navigation and surgical robots based on multi-source information. For minimally invasive precision medical treatment for major diseases such as tumors, cardiovascular disease, and stroke, it carries out image navigation and robotic surgery applications for orthopedic surgery, abdominal puncture, and cardiovascular interventional surgery.
Title: Enforcing Answer-Location Consistency for Surgical Visual Question Localized-Answering via Reverse Question Learning. Congratulations to Jiale and Xiaoyang!
Title: HybPromptSeg: Spatial-frequency hybrid prompting for unified multi-task medical image segmentation. Congratulations to Yu'ang!
Title: SOM-GAN: A structure-preserving one-to-multiple generative adversarial network for unpaired medical image synthesis. Congratulations to Jinhao!
Title: A Novel Stereo Tracking Technology for Intraoperative Intervertebral Motion Compensation in Robot-Assisted Laminectomy. Congratulations to Wenyuan!
Congratulations to Housheng and Kangqing!
Title: Generating synthetic CT from MR images for radiation-free computer-assisted quantification of hip morphology. Congratulations to Kangqing!
Title: CIM-VTP: Correlation-Guided Image Modeling With Visual-Textual Task Prompt for Universal Medical Image Registration. Congratulations to Housheng and Xiaoru!
Title: TPDPM: Text promptable diffusion probabilistic model for referring surgical instrument segmentation. Congratulations to Jiale and Xiaoyang!
Title: CR-GLoCo: Cross-Resolution Learning via Global-Local Context Consistency for semi-supervised 3D medical segmentation. Congratulations to Peng!
Title: X2P-Net: Context-Aware 2D/3D Vertebra Localization. Congratulations to Rong and Kangqing!
Title: ReTri: Progressive domain bridging via representation disentanglement and triple-level consistency-driven feature alignment for unsupervised domain adaptive medical image segmentation. Congratulations to Xiaoru!
Title: St-Swin TransNet: a spatiotemporal swin transformer-based network for self-supervised depth estimation in stereoscopic surgical videos. Congratulations to Derong!
Title: Subclass-Aware Contrastive Semi-Supervised Learning for Inflammatory Bowel Disease Classification from Colonoscopy Images. Congratulations to Kechen and Xiaoyang!
Title: BIASNet: A bidirectional feature alignment and semantics-guided network for weakly-supervised medical image registration. Congratulations to Housheng!
Title: MCI-nnUNet: Multi-Cue Integration in nnUNet for Shape-Aware Segmentation of Femoral Bone Tumors. Congratulations to Derong!
Congratulations to Derong!
Title: PromptReg: Universal Medical Image Registration via Task Prompt Learning and Domain Knowledge Transfer. Congratulations to Housheng and Xiaoru!
Title: CASHNet: Context-Aware Semantics-driven Hierarchical Network for Hybrid Diffeomorphic CT-CBCT Image Registration. Congratulations to Xiaoru!
Title: SSIFNet: Spatial–temporal stereo information fusion network for self-supervised surgical video inpainting. Congratulations to Xiaoyang!
Congratulations to Jiale!
Title: Semi-GDE: generative distribution estimation for semi-supervised medical landmark localization. Congratulations to Kangqing and Xiaoyang!
Title: Capturing action triplet correlations for accurate surgical activity recognition. Congratulations to Xiaoyang and Derong!
Title: JISS: Joint Image Super-resolution and Segmentation of Magnetic Resonance Images via Disentangled Representation Learning. Congratulations to Jiale!
Title: Data-efficient generalization of AI transformers for noise reduction in ultra-fast lung PET scans. Congratulations to Jiale!
Title: 3D full-dose brain-PET volume recovery from low-dose data through deep learning: quantitative assessment and clinical evaluation. Congratulations to Jiale!
Title: AI-enabled diagnosis and localization of myocardial ischemia and coronary artery stenosis from magnetocardiographic recordings. Congratulations to Rong!
Title: Label-Guided Teacher for Surgical Phase Recognition via Knowledge Distillation. Congratulations to Jiale, Xiaoyang, and Rong!
Title: CycleSGAN: A cycle-consistent and semantics-preserving generative adversarial network for unpaired MR-to-CT image synthesis. Congratulations to Runze!
Congratulations to Runze!
Title: PFMNet: Prototype-based feature mapping network for few-shot domain adaptation in medical image segmentation. Congratulations to Runze!
Title: A fully automatic fiducial detection and correspondence establishing method for online C-arm calibration. Congratulations to Wenyuan and Xiaoyang!
Congratulations to Peng!
Title: Incremental regression of localization context for automatic segmentation of ossified ligamentum flavum from CT data. Congratulations to Rong, Xiaoyang and Xiaoru!
Congratulations to Prof. Zheng!
Congratulations to Prof. Zheng!
Title: MAIRNet: weakly supervised anatomy-aware multimodal articulated image registration network. Congratulations to Xiaoru and Runze!
Title: SMILE: Siamese Multi-scale Interactive-representation LEarning for Hierarchical Diffeomorphic Deformable image registration. Congratulations to Xiaoru!
Title: Cross-Scanner Low-Dose Brain-PET Image Noise Reduction With Self-ensembling. Congratulations to Jiale!
Title: Nonlinear regression of remaining surgery duration from videos via Bayesian LSTM-based deep negative correlation learning. Congratulations to Xiaoyang and Rong!
Challenge: Ultra-low Dose PET Imaging (UDPET) challenge held on IEEE MIC 2023 in VANCOUVER. Congratulations to Jiale!
Challenge: Endoscopic Vision (EndoVis) - Workflow Recognition in Endoscopic Pituitary Surgery (PitVis) challenge held on MICCAI 2023 in VANCOUVER. Congratulations to Xiaoyang!
Challenge: Fast, Low-resource, and Accurate oRgan and Pan-cancer sEgmentation in Abdomen CT (FLARE) challenge held on MICCAI 2023 in VANCOUVER. Congratulations to Qin and Peng!
Title: EDRL: Entropy-guided Disentangled Representation Learning for Unsupervised Domain Adaptation in Semantic Segmentation. Congratulations to Runze and Qin!
Title: CT-guided, Unsupervised Super-resolution Reconstruction of Single 3D Magnetic Resonance Image. Congratulations to Jiale!
Title: Partially Supervised Multi-Organ Segmentation via Affinity-aware Consistency Learning and Cross Site Feature Alignment. Congratulations to Qin and Peng!
Title: FedContrast-GPA: Heterogeneous Federated Optimization via Local Contrastive Learning and Global Process-aware Aggregation. Congratulations to Qin!
Congratulations to Derong!
Title: Deep learning-based Stereo 3D Reconstruction of Surgical Scenario from Laparoscopic Vidoes. Congratulations to Derong!
Title: LAST: LAtent Space-constrained Transformers for Automatic Surgical Phase Recognition and Tool Presence Detection. Congratulations to Rong and Xiaoyang!
Title: CVCL: Context-aware Voxel-wise Contrastive Learning for label-efficient multi-organ segmentation. Congratulations to Peng!
Title: LatentPCN: Latent Space-constrained Point Cloud Network for Reconstruction of 3D Patient-specific Bone Surface Models from Calibrated Biplanar X-ray Images. Congratulations to Wenyuan, Yuyun and Jihao!
Congratulations to Runze!
Title: SVT-SDE: Spatiotemporal Vision Transformers-based Self-supervised Depth Estimation in Stereoscopic Surgical Videos. Congratulations to Rong and Xiaoyang!
Title: End-to-end transformer-based multi-task learning for surgical action triplet recognition. Congratulations to Xiaoyang!
Title: ARST: auto-regressive surgical transformer for phase recognition from laparoscopic videos. Congratulations to Xiaoyang and Rong!
Title: Towards bridging the distribution gap: Instance to Prototype Earth Mover’s Distance for distribution alignment. Congratulations to Qin and Runze!
Title: ACSGRegNet: A Deep Learning-based Framework for Unsupervised Joint Affine and Diffeomorphic Registration of Lumbar Spine CT via Cross-and Self-Attention Fusion. Congratulations to Xiaoru!
Title: Joint Lymphoma Lesion Segmentation and Prognosis Prediction From Baseline FDG-PET Images via Multitask Convolutional Neural Networks. Congratulations to Peng and Xiaoru!
[Paper #1] [Paper #2] [Paper #3] [Paper #4] [Paper #5]
Congratulations to Peng, Runze, Jiale, Zezhong, Rong, Qin and Junyang!
Title: Handling Imbalanced Data: Uncertainty-Guided Virtual Adversarial Training With Batch Nuclear-Norm Optimization for Semi-Supervised Medical Image Classification. Congratulations to Peng!
Title: BIDMIR: Bi-Directional Medical Image Registration with Symmetric Attention and Cyclic Consistency Regularization. Congratulations to Xiaoru and Rong!
Paper title: Entropy and distance maps-guided segmentation of articular cartilage: data from the Osteoarthritis Initiative. Congratulations to Zezhong and Peng!
Paper title: CyCMIS: Cycle-consistent Cross-domain Medical Image Segmentation via diverse image augmentation. Congratulations to Runze!
Paper title: MCG-Net: End-to-end Fine-grained Delineation and Diagnostic Classification of Cardiac Events from Magnetocardiographs. Congratulations to Rong!
Paper title: Spine-transformers: Vertebra labeling and segmentation in arbitrary field-of-view spine CTs via 3D transformers. Congratulations to Rong!
Title: Disentangled Representation Learning For Deep MR To CT Synthesis Using Unpaired Data. Congratulations to Runze Wang!
Title: Nonlinear Regression via Deep Negative Correlation Learning. Congratulations!
Title: Entropy Guided Unsupervised Domain Adaptation for Cross-Center Hip Cartilage Segmentation from MRI. Congratulations to Guodong!
