Abstract: One example method for gene expression prediction from whole slide images includes receiving one or more images of stained tissue; generating a set of image segments from the one or more images, each image segment comprising a group of pixels from an image of the one or more images; determining, for each image segment and using a first trained machine learning (“ML”) model, a vector of feature values; determining, using a second trained ML model and based on each of the vectors of feature values, a predicted gene expression; and outputting the predicted gene expression.

Abstract: The present disclosure relates to thin-film lead assemblies and neural interfaces with stent-assisted deployment, and methods of microfabricating thin-film lead assemblies and neural interfaces. Particularly, aspects of the present disclosure are directed to a medical device having a thin-film neural interface, a stent, and a cable. The thin-film neural interface includes a first supporting structure, electrodes formed on the first supporting structure, and an encapsulation material encasing a portion of the first supporting structure. The cable includes a second supporting structure, conducive traces formed on the second supporting structure and electrically connected with the electrodes, and the encapsulation material encasing at least a portion of the second supporting structure. The stent is at least partially embedded in the encapsulation material encasing the portion of the first supporting structure, and the thin-film neural interface is helically wrapped around at least a portion of the stent.

Abstract: An apparatus, system and process for guiding a surgeon during a medical procedure to prevent surgical mistakes are described. The system may include a machine learning medical procedure server that generates one or more machine learning medical procedure models using, at least, medical procedure data captured during medical procedures performed at a plurality of different medical procedure systems. The system may also include a medical procedure system communicably coupled with the machine learning medical procedure server that receives a selected machine learning medical procedure model from the machine learning medical procedure server, and utilizes the selected machine learning medical procedure model during a corresponding medical procedure to control one or more operations of the medical procedure system.

Abstract: An example continuous glucose monitor includes a printed circuit board (“PCB”) having first and second outer layers and an inner layer; a semiconductor package having a plurality of pins coupled to the first outer layer of the PCB; an electrical contact formed on the second outer layer of the PCB; a trace having a first portion disposed on the first outer layer, a second portion disposed on the inner layer, and a third portion disposed on the second outer layer, the trace having a first end coupled to a first pin of the plurality of pins and a second end coupled to the electrical contact; and an encapsulant disposed around a perimeter of the semiconductor package, the encapsulant covering the plurality of pins, the first portion of the sensor trace, the third portion of the sensor trace, wherein an upper surface of the semiconductor package remains exposed.

Abstract: The present disclosure relates to a monolithic thin-film lead assembly and methods of microfabricating a monolithic thin-film lead assembly. Particularly, aspects of the present disclosure are directed to a monolithic thin-film lead assembly that includes a cable having a proximal end, a distal end, a supporting structure that extends from the proximal end to the distal end, and conductive traces formed on a portion of the supporting structure. The supporting structure includes one or more layers of dielectric material. The monolithic thin-film lead assembly further includes an interface formed on the supporting structure at the distal end of the cable. The interface includes electrodes and/or sensors in electrical connection with the conductive traces, and the supporting structure has at least one curved portion disposed between a first set of electrodes and a second set of electrodes, and/or between a first set of sensors and a second set of sensors.

Abstract: Systems, devices, and methods for conducting an eye examination for visual acuity are provided. In one example, a system may include an optical subsystem positioned in front of one or both eyes of a user. The optical subsystem may comprise a handheld device or a head worn device, a visual indicator, and a plurality of vision modifiers. The system may determine a distance between the optical subsystem and the display based on comparing a fixed size of the visual indicator to a detected size of the visual indicator in an image obtained by a camera. The system may output an eye examination image for visual acuity based on the distance being within a valid range. The eye examination image may include a visual stimulus having an output size determined based on the distance. The system may receive an input from the user indicating a selection of the visual stimulus.

Abstract: Introduced here are diabetes management platforms able to examine glucose measurements associated with a subject to discover patterns indicative of similar behaviors/circumstances. More specifically, a diabetes management platform can acquire multiple data series generated by a glucose monitoring device that monitors the blood glucose level of an individual over multiple time intervals. The diabetes management platform can then apply a similarity algorithm to produce a distance measure (also referred to as a “similarity measure”) for each data series. For example, the diabetes management platform may, for each data series, perform dynamic time warping to produce a distance measure with respect to each of the other data series. The diabetes management platform can identify patterns indicative of similar behaviors/circumstances based on these distance measures.

Abstract: A wearable blood pressure meter includes a semi-conformable bladder, serving as a reservoir for an incompressible fluid, and a pressure sensor. The semi-conformable bladder includes a rigid housing defining a cavity within which the incompressible fluid is rigidly constrained and an elastic membrane for elastically constraining the incompressible fluid. The elastic membrane extends across an aperture into the cavity through the rigid housing. The elastic membrane conforms to a body part at the aperture when pressed against the body part. The pressure sensor mechanically couples to the incompressible fluid to measure pressure signals emanating from an artery within the body part and which propagate through the conformable membrane and the incompressible fluid to the pressure sensor.

Abstract: One example method includes obtaining one or more histopathology images of a sample from a cancer patient; selecting a plurality of tissue image patches from the one or more histopathology images; determining, by a deep learning system comprising a plurality of trained machine learning (“ML”) models, a plurality of image features for the plurality of tissue image patch, wherein each tissue image patch is analyzed by one of the trained ML models; determining, by the deep learning system, probabilities of patient survival based on the determined plurality of image features; and generating, by the deep learning system, a prediction of patient survival based on the determined probabilities.

Abstract: Introduced here are health management platforms able to infer the health state of a subject based on behavioral changes reflected in the digital activities performed by a subject. A health management platform can initially acquire contextual data pertaining to digital activities performed by the subject. The health management platform can identify the target(s) of the digital activities by parsing the contextual data, and then compile the digital activities and corresponding activities into a personalized valence index. Thereafter, the health management platform can compare digital activities performed by the subject to the entries included in the personalized valence index. If a matching entry is not discovered, the health management platform can identify an instance of behavior change. These instances of behavior change may be indicative of changes in the subject's health state.

Abstract: Introduced here are health management platforms able to infer the health state of a subject based on behavioral changes reflected in the digital activities performed by a subject. A health management platform can initially acquire contextual data pertaining to digital activities performed by the subject. The health management platform can identify the target(s) of the digital activities by parsing the contextual data, and then compile the digital activities and corresponding activities into a personalized valence index. Thereafter, the health management platform can compare digital activities performed by the subject to the entries included in the personalized valence index. If a matching entry is not discovered, the health management platform can identify an instance of behavior change. These instances of behavior change may be indicative of changes in the subject's health state.

Abstract: One example method for generating images of virtually stained biological samples includes receiving a first image pair comprising a first image of a biological sample and a second image of the biological sample, the first image captured using a first imaging technique and the biological sample being unstained, the second image captured using a second imaging technique different from the first imaging technique and the biological sample being stained; receiving a proposed alignment of the first image and the second image; generating alignment quality information corresponding to the first image pair, the alignment quality information indicating an alignment confidence of the first and second images; training a machine learning (“ML”) model, using the first image pair and the alignment quality information, to generate an output image of the biological sample having a virtual stain according to the second imaging technique from the first image; receiving, by the ML model, a first input image of a first biologica

Abstract: A modular system can be used with commercial eyeglasses to interface with an electronic eye-mounted ocular device and used to control and/or actuate the electronic eye-mounted ocular device, exchange data with the electronic eye-mounted ocular device, and/or charge the electronic eye-mounted ocular device. The modular system includes an electroactive stick-on component attachable to a portion of an eyeglasses lens; and an electronic system attachable to an eyeglass frame in electrical communication with the electroactive stick-on component.

Abstract: A shunt valve for removing biofluid from an eye of a user, the valve including a tubular body defining an inlet and a plurality of outlets formed through a wall of the tubular body; a plunger accommodated within the tubular body and fluidically coupled to the inlet; wherein the plunger is movable relative to the plurality of outlets; and an energized material coupled to the plunger and the tubular body; wherein the energized material is compressible to expose a portion of the plurality of outlets dependent on the pressure applied to the energized material.

Abstract: A device can include a capsule containing an array of microneedles and a mechanical actuator. The device can be in an ingestible form for delivery to a duodenum or other target location within a subject and can release a first shell portion and a second shell portion of the capsule from one another in response to stimuli or conditions in or en route to the duodenum or other target location. The launcher can drive the released first shell portion and the second shell portion away from one another to expose the array of microneedles in a position for achieving penetrating engagement with a lining of the duodenum or other target location. The penetrating engagement can facilitate delivery of a biotherapeutic agent or other payload via the microneedles.

Abstract: Introduced here is a method, a system, a device, etc. for displaying health-related data (e.g., blood glucose measurements) relevant to user's selection. The method, the system, the device, etc. can be based on: receiving healthcare-related data from data streams associated with a profile of a patient; identifying, based on a least a subset of the data streams, a time window corresponding to a contextual event indicative of a patient activity that has a potential of affecting metabolism of the patient; determining a graphical representation of the contextual event; generating a graph of blood glucose level over time for display; detecting a user indication of a user interest in a time point along the graph of the blood glucose level; and highlighting the graphical representation of the contextual event in response to the time point falling within the identified time window.

Abstract: A computer system may perform an image-related function using a segmentation (e.g., an image mask) that has been generated by a custom segmentation machine learning model. To begin, the system may receive image data corresponding to a surgical scene including a background that includes an anatomical feature and at least one surgical tool. The system may also generate segmentation data using the custom segmentation machine learning model based on inputting the first image data to the custom segmentation machine learning model. The system may also include generating a segmentation of the at least one surgical tool using the segmentation data. Once the segmentation has been generated, the system may perform an image-related function using the segmentation.

Abstract: An implant that is to be implanted inside the eye of a person contains a laser projection scanning subsystem that is configured to “paint” an image of the scene that is before the person, on the retina. The image of the scene may be acquired by a digital camera that is attached to a head unit that may be worn by the person, and then transmitted to the implant. Other aspects are also described and claimed.

Abstract: Introduced here are retinal cameras having one or more optical components whose position can be modified so that the left and right eyes can be imaged during a single imaging operation. Collectively, the optical component(s) may be referred to as an “optical assembly.” An optical assembly can include the objective lens, lens tube, and other optical components such as mirror(s), light source(s), capturing medium(s), etc. An optical assembly of a retinal camera may be movable between a first position and a second position along an arcuate path. By moving the optical assembly between the first and second positions along the arcuate path, the retinal camera can align the lens tube with the left and right eyes of an individual while clearing her nose. Thus, the retinal camera may generate images of the left and right eyes during an imaging procedure without requiring that the individual move her head.

Abstract: Introduced here are diabetes management platforms able to make annotations to physiological data of a subject whose glycemic health state is being monitored. These annotations can be used to classify excursions detected in the physiological data to facilitate the identification of a therapeutic behavior change intended to improve the glycemic health state of the subject. For example, a health coach may review the annotation(s) associated with the subject before generating a recommendation for improving the glycemic health state. As another example, the diabetes management platform can automatically identify an appropriate recommendation based on the annotation(s).