Daguang Xu
30Patents
7h-index
74Co-inventors
64Inventor score
Filing activity: Jan 30, 2015 → Aug 9, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US9760807B2 | Deep image-to-image network learning for medical image analysis | Physics | 40 | Active |
| US10210613B2 | Multiple landmark detection in medical images based on hierarchical feature learning and end-to-end training | Physics | 16 | Active |
| US10878219B2 | Method and system for artificial intelligence based medical image segmentation | Physics | 14 | Active |
| US11557036B2 | Method and system for image registration using an intelligent artificial agent | Physics | 13 | Active |
| US10062014B2 | Deep image-to-image network learning for medical image analysis | Physics | 12 | Active |
| US11393229B2 | Method and system for artificial intelligence based medical image segmentation | Physics | 11 | Active |
| US10600185B2 | Automatic liver segmentation using adversarial image-to-image network | Physics | 8 | Active |
| US9710880B2 | User-guided shape morphing in bone segmentation for medical imaging | Physics | 7 | Active |
| US11804050B1 | Processor and system to train machine learning models based on comparing accuracy of model parameters | Physics | 7 | Active |
| US11816185B1 | Multi-view image analysis using neural networks | Physics | 6 | Active |
| US10565707B2 | 3D anisotropic hybrid network: transferring convolutional features from 2D images to 3D anisotropic volumes | Physics | 5 | Active |
| US10037603B2 | Method and system for whole body bone removal and vascular visualization in medical image data | Physics | 4 | Active |
| US10636141B2 | Adversarial and dual inverse deep learning networks for medical image analysis | Physics | 3 | Active |
| US10079071B1 | Method and system for whole body bone removal and vascular visualization in medical image data | Physics | 3 | Active |
| US11100643B2 | Training strategy search using reinforcement learning | Physics | 3 | Active |
| US10779785B2 | Semantic segmentation for cancer detection in digital breast tomosynthesis | Physics | 3 | Active |
| US11741605B2 | Method and system for image registration using an intelligent artificial agent | Physics | 2 | Active |
| US12072954B1 | Neural network trained using federated learning with local training data preserved at local edge circuits | Physics | 2 | Active |
| US10607342B2 | Atlas-based contouring of organs at risk for radiation therapy | Physics | 2 | Active |
| US10188361B2 | System for synthetic display of multi-modality data | Physics | 1 | Active |
| US10366491B2 | Deep image-to-image recurrent network with shape basis for automatic vertebra labeling in large-scale 3D CT volumes | Physics | 0 | Active |
| US12367261B1 | Extending supervision using machine learning | Physics | 0 | Active |
| US12164599B1 | Multi-view image analysis using neural networks | Physics | 0 | Active |
| US11630995B2 | Characterization of amount of training for an input to a machine-learned network | Physics | 0 | Active |
| US12423583B2 | Selecting annotations for training images using a neural network | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.