Method and System of Building Hospital-Scale Medical Image Database

Developing computer systems that can recognize and locate image features associated with disease is a challenge for developing fully-automated and high precision computer assisted diagnostics. Joint learning of language tasks in association with vision tasks (association of image features with text annotation) adds an additional level of challenge.  Furthermore, scaling-up approaches from small to large datasets presents additional issues, particularly related to medical images.

Selective estrogen-receptor modulators (SERMs) confer protection against photoreceptor degeneration

Retinal degeneration is a deteriorative condition of the human retina caused by the progressive and eventual death of photoreceptor cells. To date, no effective treatment for genetically inherited or age-associated retinal degeneration, which includes a large patient population worldwide, is available.

Robotic Exoskeleton for Treatment of Crouch Gait in Children with Cerebral Palsy (CP)

Crouch gait is a common disorder in pediatric cerebral palsy (CP). Effective treatment of crouch during childhood is critical to maintain mobility into adulthood. Current interventions do not alleviate crouch gait long-term for most patients. This technology relates to a powered exoskeleton designed for gait assistance. The powered assistance may provide a physical therapy-type intervention to improve and maintain mobility.  

CODEFACS and LIRICS: Computation Tools for Identifying Cell-Type Specific Gene Expression Levels in Tumors and Other Types of Samples

The tumor microenvironment (TME) is a complex mixture of cell types whose interactions affect tumor growth and clinical outcome. Recent studies using fluorescence-activated cell sorting (FACS) and single-cell RNA sequencing (RNAseq) to elucidate tissue composition and cell-cell interactions in the TME led to improved biomarkers of patient response and new treatment opportunities. However, the use of FACS is limited to simultaneously measuring the expression of a few protein markers, whereas the use of single-cell RNAseq has been limited due to cost and scarcity of fresh tumor biopsies.

Optical Microscope Software for Breast Cancer Diagnosis

The successful treatment of cancer is correlated with the early detection of the cancerous cells. Conventional cancer diagnosis is largely based on qualitative morphological criteria, but more accurate quantitative tests could greatly increase early detection of malignant cells. It has been observed that the spatial arrangement of DNA in the nucleus is altered in cancer cells in comparison to normal cells. Therefore, it is possible to distinguish malignant cells by mapping the position of labeled marker genes in the nucleus.

Angiogenesis-Based Cancer Therapeutic

Vascular Endothelial Growth Factor-A (VEGF-A) is an angiogenic agent that drives blood vessel formation in solid tumors and other diseases, such as macular degeneration and diabetic retinopathy. Several therapies that target the ability of VEGF to stimulate angiogenesis have been approved. These therapies regulate VEGF-A activity by binding VEGF-A, thereby blocking VEGF-A from binding to its receptor on target cells. This technology utilizes a different approach to regulating VEGF-A activity by providing a VEGF-A protein antagonist that is produced by engineering native VEGF-A protein.