Data, Algorithms, Software Summaries

Computer vision training system for robust artificial intelligence image classification
Tong, Liang ; Vorobeychik, Yevgeniy ; Wu, Tong
T-019303

— Technology Description Researchers in Prof. Yevgeniy Vorobeychik’s laboratory have developed a new adversarial model and training methods to defend deep neural networks against physical attacks that corrupt image classifications. This system outperforms previous state-of-the-art techniques a…

Pressure recovery ratio (PRR) index for real-time assessment of heart failure
Chung, Charles ; Kovacs, Sandor ; Shmuylovich, Leonid ; Zhang, Weixiong
T-007562

— Technology Description Researchers in the Cardiovascular Biophysics Laboratory at Washington University developed a patented, real-time, automated index to reliably detect delayed relaxation during cardiac catheterization diagnostics. This technique, called pressure recovery ratio (PRR), serves as…

Machine learning methods for real-time MRI image processing: MRI-only radiation treatment planning and improving MR image resolution
Green, Olga ; Mutic, Sasa ; Park, Chunjoo (Justin) ; Zhang, Hao
T-018522

— Technology Description A team of researchers at Washington University School of Medicine developed deep learning image processing techniques to improve MRI diagnostics and potentially enable faster, more precise MRI-guided radiation therapy without exposing patients to radiation from CT imaging. S…

Real-time air and water quality monitoring with AI-based data analysis and low cost sensors
Biswas, Pratim ; Li, Jiayu
T-018523

— Technology Description Prof. Pratim Biswas and colleagues have developed an artificial intelligence platform to provide accurate, low-cost analysis of air and water quality by integrating data gathered from particulate matter (PM) sensors and other sources. This technology could be used to make th…

Machine learning method for fast, reliable quality assurance of patient imaging in radiation therapy or computer-aided detection
Altman, Michael ; Green, Olga ; Kavanaugh, James ; Li, Hua ; Mutic, Sasa ; Wooten, Hasani
T-013577

— Technology Description A team of researchers at Washington University has created a machine learning method to quickly and reliably validate patient contours in digital medical images for radiation therapy and computer aided image analysis. Currently, automated contouring tools for delineating tu…

Blockchain-based algorithms for secure, collaborative risk assessment and decision making
Jain, Raj ; Salman, Tara
T-018710

— Technology Description Researchers in Prof. Raj Jain’s laboratory have developed a new type of algorithm that extends the security of decentralized blockchains from consensus validation to efficient group decision making. This technology, called “probabilistic blockchains”, provi…

Self-powered, solid-state devices for remote sensing, timing and security of internet-of-things and other passive assets
Chakrabartty, Shantanu ; Zhou, Liang
T-015908

— Technology Description Engineers in Prof. Shantanu Chakrabartty’s laboratory have developed a self-powered, CMOS-based, nano-scale “smart sensor” and timer system that uses quantum-tunneling for reliable, long-lasting memory or authentication. This technology is a floating gate …

Multiparametric Cardiac Strain Analysis of Myocardial Viability
Cupps, Brian ; Kar, Julia ; Pasque, Michael
T-014564

— Background: Assessing left ventricle (LV) cardiac contractile function is a good indicator of overall heart health and is used to determine which patients are good candidates for revascularization surgery. With over 3 million new coronary artery disease patients annually and over 1 million annual re…

Method To Remove Brain Stimulation Artifacts in Neural Signals
Brunner, Peter ; Leuthardt, Eric ; Willie, Jon ; Xie, Tao
T-020083

— Value proposition: Method and system for removing multiple types of brain stimulation artifacts in neural signals to improve neurological diagnoses and therapies. Technology Description Researchers at Washington University in St. Louis have developed a method to remove brain stimulation artifact…

Myocardial perfusion SPECT optimization
Jha, Abhinav Kumar ; Rahman, Md Ashequr ; Siegel, Barry ; Yu, Zitong
T-020357

— T-020357, T-020358, T-020744 Myocardial perfusion SPECT optimization Technology Description Researchers from the laboratory of Abhinav Jha at Washington University have devised methods to reliably improve and personalize myocardial perfusion SPECT imaging. The inventions include the following capa…

Software to predict low back pain from brain imaging
Hawasli, Ammar ; Jayasekera, Dinal ; Lamichhane, Bidhan ; Leuthardt, Eric ; Ray, Wilson
T-019322

— Technology Description: Researchers at Washington University, led by Eric Leuthardt, have developed software that can identify specific brain regions involved in chronic low back pain from neuroimaging data. This software, powered by machine learning, relies on differences in cortical thickness an…

Method to characterize gut microbiome
Gordon, Jeffrey ; Raman, Arjun
T-018977

— Technology Description Researchers at Washington University in St. Louis have developed a method to stratify gut microbiota dysbiosis and monitor treatments to correct it. In order to efficiently treat microbiota imbalance, it would first be beneficial to understand the healthy organization and in…

EMMI- non-invasive imaging method for safe, accurate, robust monitoring of uterine contractions
Cahill, Alison ; Cuculich, Phillip ; Schwartz, Alan ; Wang, Yong
T-015805

— Technology Description Researchers at Washington University in St. Louis have developed an electromyometrial imaging (EMMI) method to non-invasively monitor uterine contractions. During pregnancy, many women experience preterm contractions. Sometimes these contractions progress to pre-term labor a…

Accurate, efficient 2D strain mapping with robust detection of strain localization
Boyle, John ; Genin, Guy ; Pless, Robert ; Thomopoulos, Stavros
T-014090

— Summary DDE (Direct Deformation Estimation) and SIMPLE (Strain Interference with Measures of Probable Local Elevation) are two simple Digital Image Correlation algorithms that combine image analysis techniques with mechanical engineering principles to provide accurate, efficient, quantitative strai…