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

Thermally Stable Hydrocarbon-based Anion Exchange Membrane and Ionomers

Researchers at RPI have developed a prototype hydrocarbon-based membrane for use in AE fuel cells and electrolyzers. This membrane can operate in a stable manner at elevated temperatures with the potential to provide enhanced operational performance. This membrane could possibly effectively participate in the growing fuel cell/electrolyzer market, as tested, the DPE membrane provides increased Tg values as compared to non-functionalized PS materials and increased Tg values as compared to main chain Nafion-117.

Optical Reservoir Computing for Lung Tumor Movement Prediction in Radiation Therapy Applications

"Researchers at RPI developed an optical reservoir computer (ORC) with commercial off-the-shelf components to predict lung tumor motion during radiotherapy. The technology could improve radiation therapy outcomes and yield applications for other imaging modalities. The ORC shows comparable motion prediction accuracy and error rates to traditional neural networks (long short-term memory (LSTM), Multi-Layer Perceptron Neural Network (MLP-NN), and Adaptive Boosting and Multi-Layer Perceptron Neural Network (ABMLP-NN)).

Terahertz Plasmonics for Testing Very Large-Scale Integrated Circuits under Bias

Researchers at Rensselaer Polytechnic Institute have developed a technology which could improve VLSI testing by allowing for non-destructive testing of VLSI circuits under bias for electronic systems. With this new technology, researchers have focused on improving testing output as chip density increases along with decreasing chip sizes. Terahertz radiation (and related radiation at other frequencies – RF, sub-THz) is used to illuminate the chip under the test.

Apparatus and manufacturing method for in-situ impregnation of continuous fiber tows with thermoplastic resin for use in additive manufacturing.

Using raw materials (thermoplastic pellets and rolls of fiber tows), this invention will continuously impregnate fiber tows with molten thermoplastic resin for fabrication of custom composite shapes, unlike current methods, which do not use raw materials and are extremely expensive processes. The ‘In Situ’ process can be used to either directly “print” composite parts in an additive manufacturing approach or to manufacture pre-impregnated (prepreg) composite material for use in other manufacturing technologies.

Orbital Debris Capture and Deorbit System for Nanosatellites

Rensselaer inventors created a multi-launch system and capture method to effectively clean up debris in a cost-effective manner. Operationally, the method consists of deploying a small-sized object called the CubeSat. This is a small satellite with a low mass and can be part of the launch of another larger satellite or other space-based object. The CubeSat is launched into space at the same orbit as the main payload. From there, it uses its built-in capabilities to maneuver itself to the desired orbit where space debris of the right size are present that need to be captured and destroyed.

Interfacial Charge Valve Controlled Hybrid Fiber for Ultra-Sensitive Detection of UV light

Rensselaer inventors created a hybrid fiber UV photodetector with a completely new internal gain mechanism which can achieve extremely high external quantum efficiency for ultrasensitive UV sensing while at the same time only require low voltage supply. The new photodetector has a high potential for system integration; the size of hybrid fiber UV photodetector is comparable to a 2 cm long human hair, with negligible weight. It is highly flexible, can bend to any angle with a great flexibility and potential for smart system integration, such as Micro Robot, Lab on a Chip, etc.

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

Directed evolution for Membranes Development in 3 Dimensions

Researchers at Rensselaer Polytechnic Institute (RPI) created a 3D computer simulation tool to assess the behavior/interaction of a hydrophobic membrane material with waste/feed water particles to assist membrane manufacturers/end-users in identifying a high performing membrane filtration/separation system. This simulation protocol could represent a viable, more cost-effective technique for membrane system designers within the wastewater treatment, desalination, food processing, pharmaceutical biotech, and oil/gas industries.

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.