System and methods for machine learning based trackingless volume reconstruction

RPI presents a novel, DCL-Net system, and method based on a machine learning/DL technique to reconstruct 3D volumes from a series of 2D images. The developed technology does not require the use of sensor tracking hardware/devices (e.g., robotic arms, touchless position/pose trackers) to operate. The technology acquires multiple (two or more) consecutive, 2D US-generated image frames using a handheld imaging sensor or a sensor mounted on a motion restricted device used as inputs for estimating a US probe trajectory and tracking its motion.

Simultaneous Interior MRI and X-ray Imaging System (MRX)

Hybrid imaging combines different imaging modalities to obtain information from both systems, such as anatomy and physiology through MRI while leveraging tools available for X-ray fluoroscopy. Hybrid image systems could offer the benefits of increased diagnostic accuracy, faster examinations, and a better understanding of different medical professions. Current medical imaging research leverages hybrid imaging, which is of particular value to interventional applications as additional information is provided with MRI and soft-tissue contrast.

Spectral Interior Tomography for Carotid Plaque Characterization

Strokes are one of the primary sources of long-term disability with billions in annual direct and indirect costs to the United States healthcare system. Nearly one-third of all strokes occur in patients with clogged carotid arteries. Carotid artery imaging types include digital subtraction angiography (DSA), duplex ultrasonography (DUS), CT angiography, and MR angiography. These imaging techniques provide information on the carotid artery’s shape, localized blood flow, and plaque composition.

Invention Title Ultrasound Imaging and Deep Learning Methods and Apparatus for Multi-dimensional image-based Biomarkers

Researchers at Rensselaer Polytechnic Institute are developing a non-invasive and user-friendly wearable

device for monitoring blood pressure, blood glucose, and biomarkers, which could improve quality of life, 

decrease healthcare expenditure, and allow for early intervention for potentially serious diseases. 


Currently, a major area of interest within the medical wearable device industry is the real-time monitoring

of blood pressure. More than 100 million adults in the United States and a third of the worldwide population

Nanoparticle-enabled X-ray Magnetic Resonance Imaging (NXMR)

Researcher Ge Wang and team created imaging systems and methods using excited nanoparticles coupled between CT and MRI to provide faster localization information for targeted, high resolution imaging. The study of biological systems is a complex pursuit that requires sufficient models and tools to measure responses to controlled changes in the system, however, there has been a lack of appropriate microscopy allowing insight into deep 3D models of molecular and cellular function due to the diffusive properties of optical light. Wang and his team overcame limitations in the field by using nan

Low-dimensional manifold constrained disentanglement network for metal artifact reduction in CT images

Commonly implanted medical devices containing metal parts (i.e., dental fillings, coils, hip replacements) generate streaks in computed tomography (CT) images, thereby impeding diagnosis and interfering with radiation therapy planning. Inventors at RPI created a novel technique to boost the efficacy of neural networks for metal artifact reduction (MAR) in CT images. Currently, deep neural network-based techniques need to be trained on synthetic, paired images. Unfortunately, these images may not accurately reflect clinical reality and technical factors.

Three-dimensional scaffolds, methods for fabricating the same, and methods of treating a peripheral nerve or spinal cord injury

Spinal Cord Injury (SCI) can result in catastrophic loss of function. In the US, 450,000 people live with SCI. Ongoing neuroscience research focuses on ways to improve nervous tissue regeneration, including development of innovative biomaterials. Implantable scaffolds composed of aligned polymer fibers have shown considerable promise in directing regenerating axons in vitro and in vivo. Highly aligned polymer fibers are necessary for neural tissue engineering applications to ensure that axonal extension occurs efficiently through a regenerating environment.

3D determination of cell chirality

Detecting differences at the cellular level is an ongoing problem which, if successfully addressed, could help solve several prevalent ailments, including cancers and prenatal diseases. Normal tissue function requires appropriate cell positioning and directional motion. This property, known as chirality, can be altered by genetic and environmental factors, leading to, for example, birth defects and tumor formation. Current methods to diagnose cancer are based on biomarkers, imaging, and analysis of tissue specimens.


The cross-section of an X-ray phase shift image is a thousand times greater than that of X-ray attenuation in soft tissue over the diagnostic energy range implying phase imaging can achieve a much higher signal-to-noise ratio and substantially lower radiation dose than attenuation-based X-ray imaging. Grating interferometry is a state of the art X-ray imaging approach, which can simultaneously acquire information of X-ray phase-contrast, dark-field, and linear attenuation. This imaging modality can reveal subtle texture of tissues.

Attenuation Map Reconstruction From TOF PET Data

Time of flight PET (TOF-PET) is an advance over traditional PET that uses the time difference in detection of the two photon events. TOF information provides better localization of the annihilation event along the line formed by each detector pair, resulting in an overall improvement in signal to noise ratio (SNR) of the reconstructed image. This technology uses a direct estimation of the sinogram only from TOF PET data.