Massachusetts Institute of Technology

Merck Sharp + Dohme Corp.

Albert Joseph Swiston

Patrick Seamus Doyle

Paul Bisso

Jiseok Lee

Robert E Cohen

Michael F Rubner

Robert Samuel Langer

Darrell J Irvine

Carlo Giovanni Traverso

Antong Chen

Kerry Alexander Johnson

Nuerxiati Nueraji

Tadd Bernard Hughes

Ronghua Chen

Tejash Mukesh Patel

Dani Kiyasseh

Lauren Milechin

Jack Gerald Fleischman

William Donald Pratt

Anna Nichole Honko

Methods and systems are described for image segmentation. A machine learning model is applied to a set of images to generate results. The results may be obtained as a probability map for each image in the set of images. The model may be trained by accessing a set of labeled images, each image associated with a label indicating a location of a feature within a respective image. An initial set of parameters is accessed. An encoder is initialized with the initial set of parameters. The encoder is applied to the set of labeled images to generate a prediction of a feature location within each image. The initial set of parameters are updated based on the predictions and the label associated with the labeled images. The updated set of parameters and an additional set of parameters generated using a set of unlabeled images are aggregated.

Meta-learning for cardiac MRI segmentation

Polymer microparticles spatially and spectrally encoded using upconversion nanocrystals (UCN) are described for labeling of articles and tissues. UCN having spectrally distinguishable emission spectra are disposed in different portions of an encoding region of each microparticle.

Rare earth spatial/spectral microparticle barcodes for labeling of objects and tissues

Systems and methods are disclosed herein for predicting whether a patient has been exposed to an agent. Physiological data is recorded from the patient during a first time interval, and one or more features are extracted from the physiological data. A plurality of classifiers is identified, wherein each classifier is trained using training data for a respective specific post-exposure time interval. For each classifier and based on a respective subset of the one or more features, a patient state classification that indicates an initial prediction of whether the patient has been exposed to the agent is determined. An indication of a prediction that the patient has been exposed to the agent is provided when a number of patient state classifications indicating a positive initial prediction that the patient has been exposed to the agent exceeds a first threshold.

Methods and systems for pre-symptomatic detection of exposure to an agent

Reliable, real-time heart and respiratory rates are key vital signs used in evaluating the physiological status in many clinical and non-clinical settings. Measuring these vital signs generally requires superficial attachment of physically or logistically obtrusive sensors to subjects that may result in skin irritation or adversely influence subject performance. Given the broad acceptance of ingestible electronics, the approach disclosed here enables vital sign monitoring internally from the gastrointestinal tract. The large animal (porcine) experiments and a robust processing disclosed herein demonstrate the feasibility of this approach. Implementing vital sign monitoring as a stand-alone technology or in conjunction with other ingestible devices has the capacity to significantly aid telemedicine, optimize performance monitoring of athletes, military service members, and first-responders, as well as provide a facile method for rapid clinical evaluation and triage.

Ingestible devices and methods for physiological status monitoring

Hydrogel microparticles spatially and spectrally encoded using upconverting phosphor nanoparticles are described for use in biochemical testing. In each microparticle, upconversion nanocrystals having spectrally distinguishable emission spectra are disposed in different pardons of an encoding region of the microparticle.

Rare earth spatial/spectral barcodes for multiplexed biochemical testing

A hydrophilic coating can be applied to virtually any surface to produce a long-lasting, durable antifog effect. The coating includes a molecular-level blend of hydrophilic polymers. The coating can be assembled using a layer-by-layer assembly process.

Coatings

Uniform, functional polymer patches can be attached to a fraction of the surface area of living individual cells. These surface-modified cells remain viable after attachment of the functional patch. The patch does not completely occlude the cellular surface from the surrounding environment. Functional payloads carried by the patch may include, for example, drugs or other small molecules, peptides, proteins, thermally responsive polymers, and nanoparticles, or any other material that can be incorporated in a polymer patch of subcellular dimensions. The patch can include one or more polyelectrolyte multilayers (PEMs).

Synthetically functionalized living cells

Growing community of inventors

Somerville, MA, United States of America

Albert Joseph Swiston