|
Task-Oriented Deep Learning Image Denoising
RPI ID: 2022-015-201
Innovation Summary:
A deep learning-based image denoising method tailored to specific tasks such as segmentation or classification. Unlike generic denoising, it preserves features critical to downstream analysis. The model adapts its strategy based on the intended application, improving performance in real-world scenarios. It is...
Published: 3/10/2026
|
Updated: 3/10/2026
|
Inventor(s): Jiajin Zhang, Hanqing Chao, Ge Wang, Pingkun Yan
Keywords(s): Artificial Intelligence, deep learning, Image Denoising, image quality, medical imaging
Category(s): Computational Science and Engineering
|
|
System and methods for machine learning based trackingless volume reconstruction
RPI ID: 2020-060-201
Innovation Summary:
A machine learning system reconstructs imaging volumes without requiring external tracking devices. The method uses internal image features and learned spatial relationships to align and assemble slices into coherent 3D volumes. It is particularly useful in ultrasound and other modalities where tracking hardware...
Published: 3/10/2026
|
Updated: 3/10/2026
|
Inventor(s): Hengtao Guo, Pingkun Yan
Keywords(s): deep learning, image reconstruction, medical imaging
Category(s): Biotechnology and the Life Sciences
|
|
Trackerless 2D Ultrasound frames to 3D image volume registration
RPI ID: 2020-025-401
Innovation Summary:
A system and method are introduced for registering 2D ultrasound frames into a 3D image volume without the need for external tracking hardware. The approach uses internal image features and spatial inference to align slices, enabling coherent volume reconstruction. It is particularly suited for portable and...
Published: 3/10/2026
|
Updated: 3/10/2026
|
Inventor(s): Pingkun Yan
Keywords(s): image analysis, image-guided intervention, medical imaging
Category(s): Biotechnology and the Life Sciences
|
|
Patient-Specific Organ Dose Quantification and Optimization for CT
RPI ID: 2020-032-401
Innovation Summary:
A computational method enables quantification of organ-specific radiation dose during CT imaging and uses inverse optimization to adjust scan parameters accordingly. The system incorporates patient-specific anatomical models and dose-response data to guide personalized imaging protocols. It supports real-time...
Published: 3/10/2026
|
Updated: 3/10/2026
|
Inventor(s): Pingkun Yan, Birsen Yazici, Xie Xu
Keywords(s): AI workflow, Artificial Intelligence Radiology, Clinical Imaging, computed tomography (CT), CT dosimetry, CT Scanner, deep learning, Dosimetry, Imaging, medical imaging, Nuclear Medicine, Personalized Medicine, Radiology, X-Rays
Category(s): Biotechnology and the Life Sciences
|
|
A METHOD OF DIRECT MULTI-MODAL 2D TO 3D IMAGE REGISTRATION
RPI ID:
2023-082-301
Innovation Summary:
This technology introduces systems and methods for registering multi-modal and multi-dimensional images, enabling alignment of data from different imaging modalities and spatial dimensions. The system uses advanced algorithms to match features across modalities such as MRI, CT, PET, and others, improving the...
Published: 3/10/2026
|
Updated: 3/10/2026
|
Inventor(s): Pingkun Yan, Xinrui Song
Keywords(s): AI/ML, image-guided intervention, medical imaging
Category(s): Computational Science and Engineering
|
|
A Synergized Pulsing-Imaging Network (SPIN)
RPI ID: 2018-029-401Innovation Summary:This invention introduces a synergized pulsing-imaging network (SPIN) that jointly optimizes MRI pulse sequences and image reconstruction. The system uses a deep learning framework to co-train the pulse generation and image reconstruction modules, improving image quality and acquisition efficiency. It adapts to...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Qing Lyu, Tao Xu
Keywords(s): deep learning, machine-learning, medical imaging
Category(s): Biotechnology and the Life Sciences
|
|
Training a CNN with pseudo ground truth for CT metal artifact reduction
RPI ID: 2018-021-201 / 2018-021-601Innovation Summary:This invention introduces a method for training convolutional neural networks (CNNs) to reduce artifacts in CT images using pseudo ground truth data. The system includes an estimated ground truth generator that produces reference images from artifact-laden scans, enabling the CNN to learn artifact...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Lars Gjesteby, Hongming Shan
Keywords(s): Biomedical Engineering, machine-learning, medical imaging
Category(s): Computational Science and Engineering
|
|
Simultaneous Emission-Transmission Tomography
RPI ID: 2017-028-401Innovation Summary:This invention presents a system for simultaneous emission and transmission imaging in PET/CT scanners. It features a rotating source and detector configuration that enables concurrent acquisition of PET and CT data. This design improves image registration, reduces scan time, and enhances workflow efficiency. The...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Lars Gjesteby, Wenxiang Cong
Keywords(s): Biomedical Engineering, Diagnosis and treatment analysis of diseased tissue, medical imaging
Category(s): Biotechnology and the Life Sciences
|
