|
Dual Network Architecture for Few-view CT – Trained on ImageNet Data and Transferred for Medical Imaging
RPI ID: 2020-001-401Innovation Summary:This invention introduces a deep learning-based system for reconstructing CT images from a limited number of views. The model is trained to infer missing projection data and generate high-quality images from sparse inputs. It significantly reduces radiation exposure while maintaining diagnostic accuracy. The system...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Hongming Shan, Wenxiang Cong, Huidong Xie
Keywords(s): deep learning, Dual network architecture (DNA), few-view CT, generative adversarial network (GAN), machine-learning, sparse-view CT
Category(s): Biotechnology and the Life Sciences
|
|
Modularized Adaptive Processing Neural Network (MAP-NN) for Low-dose CT with Radiologists-in-the-loop
RPI ID: 2019-023-201Innovation Summary:This invention introduces a modularized adaptive processing neural network architecture designed for efficient and scalable AI applications. The system dynamically adjusts its structure and processing pathways based on input complexity and task requirements. It supports real-time learning and inference, making...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Hongming Shan
Keywords(s): deep learning, denoising, machine-learning, radiologists-in-the-loop, tomography reconstruction
Category(s): Biotechnology and the Life Sciences
|
|
CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE)
RPI ID: 2019-005-201 / 2019-005-601Innovation Summary:This invention introduces a deep learning framework called GAN-Circle for super-resolution reconstruction in computed tomography (CT) imaging. The system is based on a generative adversarial network (GAN) architecture constrained by three synergistic learning strategies: identical mapping, residual...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Chenyu You, Wenxiang Cong, Hongming Shan, Guang Li
Keywords(s): High-resolution CT image, Image super resolution, low-resolution CT image
Category(s): Computational Science and Engineering
|
|
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
|
|
Deep learning for metal artifact reduction in computed tomography images
RPI ID: 2018-008-401, 2018-008-601Innovation Summary:This invention from Rensselaer Polytechnic Institute introduces a deep learning-based framework for reducing metal artifacts in computed tomography (CT) images. The system leverages a neural network trained on paired CT datasets—with and without metal artifacts—to reconstruct high-fidelity images...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Lars Gjesteby, Qingsong Yang, Hongming Shan
Keywords(s): computed tomography (CT), deep learning, machine-learning, metal artifact reduction
Category(s): Biotechnology and the Life Sciences
|
|
3D Convolutional Autoencoder for Low-dose CT via Transfer Learning from a 2D Trained Network
RPI ID: 2018-007-401Innovation Summary:This invention introduces a 3D convolutional autoencoder that enhances low-dose CT image quality by learning from high-quality 2D training data. The system leverages transfer learning to bridge the gap between 2D and 3D imaging, enabling efficient training and robust performance. It corrects artifacts and improves...
Published: 7/21/2025
|
Updated: 7/3/2025
|
Inventor(s): Ge Wang, Hongming Shan, Wenxiang Cong
Keywords(s):
Category(s): Biotechnology and the Life Sciences
|
