Provided herein are systems, methods and apparatuses for an integrated system and architectures comprising a central processing unit (CPU) located a substantial physical distance from a sample.

In accordance with some embodiments of the disclosed subject matter, mechanisms (which can, for example, include systems, methods, and media) for low-power encoding of continuous physiological signals are provided. In some embodiments, a system comprises: a physiological sensor; and a remote monitor comprising: a battery; memory storing a k-ary tree including a root with k branches corresponding to k delta values, k nodes at a first depth below the root node each having k branches corresponding to the k delta values the nodes indexed to indicate the lateral position of the node within the depth; a processor programmed to: receive a first sample value from the sensor; receive a second sample value; calculate a difference between the second first sample values; determine that the delta corresponds to a first delta of the k delta values; encode a sequence of deltas based on a depth and node index.

Methods and systems for characterizing tissue of a subject include acquiring and receiving data for a plurality of time series of fluorescence images, identifying one or more attributes of the data relevant to a clinical characterization of the tissue, and categorizing the data into clusters based on the attributes such that the data in the same cluster are more similar to each other than the data in different clusters, wherein the clusters characterize the tissue. The methods and systems further include receiving data for a subject time series of fluorescence images, associating a respective cluster with each of a plurality of subregions in the subject time series of fluorescence images, and generating a subject spatial map based on the clusters for the plurality of subregions in the subject time series of fluorescence images. The generated spatial maps may then be used as input for tissue diagnostics using supervised machine learning.

Methods and systems for characterizing tissue of a subject include acquiring and receiving data for a plurality of time series of fluorescence images, identifying one or more attributes of the data relevant to a clinical characterization of the tissue, and categorizing the data into clusters based on the attributes such that the data in the same cluster are more similar to each other than the data in different clusters, wherein the clusters characterize the tissue. The methods and systems further include receiving data for a subject time series of fluorescence images, associating a respective cluster with each of a plurality of subregions in the subject time series of fluorescence images, and generating a subject spatial map based on the clusters for the plurality of subregions in the subject time series of fluorescence images. The generated spatial maps may then be used as input for tissue diagnostics using supervised machine learning.

A microcontroller for recording and storing physiological data includes an analog-to-digital converter for converting analog physiological sensor signals to digital signals, a sample buffer for holding a temporal sequence of the digital signals, a central processing unit (CPU), and a non-volatile memory. The non-volatile memory includes (i) a code storage encoding machine-readable data compression instructions that, when executed by the CPU, control the CPU to (a) transform the temporal sequence of the digital signals to produce transformed physiological data characterized by a set of transformation coefficients and (b) compress the set of transformation coefficients to generate compressed physiological data, and (ii) a data storage configured to contain several different instances of the compressed physiological data respectively associated with several different instances of the temporal sequence of the digital signals.

Certain aspects of the present disclosure relate to a method for compressed sensing (CS). The CS is a signal processing concept wherein significantly fewer sensor measurements than that suggested by Shannon/Nyquist sampling theorem can be used to recover signals with arbitrarily fine resolution. In this disclosure, the CS framework is applied for sensor signal processing in order to support low power robust sensors and reliable communication in Body Area Networks (BANs) for healthcare and fitness applications.

The present disclosure relates to a surgical system, a surgical device, and a surgical method with which startup time can be shortened. Upon receipt of an instruction from a startup execution process, a high-speed startup driver creates a high-speed startup image and writes it to an SSD. The startup execution process is a process that is executed first after an OS is started up, and has the function of executing, in cooperation with the high-speed startup driver, startup of various processes in an endoscope program, creation of a high-speed startup image, and return from the high-speed startup image. The present disclosure can be applied to, for example, a surgical system provided with an imaging device including an endoscope or a microscope.

An ECG signal lossless compression system includes: a signal difference value generating module and a compression module. The signal difference value generating module performs an adaptive linear prediction encoding on an ECG signal, so as to generate a plurality of signal difference values corresponding to each datum of the ECG signal; the compression module divides the signal difference values into a plurality of groups and performs an adaptive linear lossless compression encoding on each group, so as to generate a plurality of window compression streams, wherein each group corresponds to a bit reference index configured to be a compression encoding parameter of the adaptive linear lossless compression encoding.

The present invention is directed to an energy-efficient method of monitoring a physiological signal while maintaining high accuracy. The method may comprise a Deep Neural Network (DNN) receiving an uncompressed sample of a continuous ECG signal from a sensor. The method may further comprise the DNN determining a first probability that the received sample is abnormal and a second probability that the received sample is normal. Finally, the method may further comprise the DNN determining to transmit the uncompressed sample if a threshold of abnormality is less than or equal to the difference between the first probability and the second probability. In some embodiments, the DNN may be a Convolutional Neural Network (CNN).

Examples relate to a method, an apparatus and a computer program for processing an almost-periodic input signal comprising a plurality of signal portions of varying duration, and to a system comprising such an apparatus and a visual output device. The plurality of signal portions are characterized by a common signal shape. The method comprises assigning the plurality of signal portions to a plurality of sets of signal portions. Each set of signal portions comprises two or more signal portions. The method comprises adjusting a duration of at least a subset of the signal portions such that the signal portions of a set have the same duration. The method comprises superimposing the two or more signal portions of a set within a combined output signal.