A cannula with a proximally mounted camera and proximally mounted light sources. The lighting sources have beam axes directed distally, toward a workspace at the distal end of the cannula. The light sources are coupled with focusing lenses, to reduce the beam angle of the lighting sources and reduce glare within the cannula tube.

The present specification discloses a method capable of automatically recognizing an accurate wound boundary and a method of generating a 3D wound model based on the recognized wound boundary. The method of automatically recognizing a wound boundary according to the present specification is a method of automatically recognizing a wound boundary based on artificial intelligence, and may photograph several frames of the wound to be recognized with an RGB-D camera, separating measurement information in an image, amplifying image data for learning, and passing the amplified image data through an artificial neural network. The method may include generating a three-dimensional (3D) model by performing boundary recognition post-processing on the data passing through the artificial neural network to match a two-dimensional (2D) image with the 3D model.

In brain analysis, anatomical standardization is performed when analyzing a region of interest (ROI). There are individual differences in the shape and size of the brain and by converting the brain into a standard brain, these differences can be compared with each other and subjected to statistical analysis. When generating a standard brain analysis, a large number of pieces of image data are classified into a plurality of groups based on their anatomical features. An intermediate template that is an intermediate conversion image and a conversion map is calculated for each group, and the calculation of the intermediate template and the generation of the intermediate conversion image are repeated while gradually reducing the number of classifications, so that a final standard image is generated. Using the standard image and the intermediate template calculated during the generation of the standard image, spatial standardization of the measured image is performed.

An image processing system includes at least one processor including hardware. The processor performs a process that acquires, as a processing target image sequence, images captured in a time series manner with an inside of a living body by an endoscope imaging device, a process based on a database generated by using a plurality of in-vivo images captured at earlier timings than timings at which the processing target image sequence is captured, and a process that determines, when a bleeding has been occurring inside the living body, a kind of a desirable bleeding stopping treatment for a blood vessel on which the bleeding has been occurring based on the processing target image sequence and the database to present, to a user, the determined type of the bleeding stopping treatment.

Disclosed are methods, materials and devices for approximation of blood volume in a fluid, and/or blood loss from fluid collected during a surgical procedure. Methods of detecting blood in a sample, such as a fluid sample, and kits for performing the methods, are also provided. Methods for approximating a volume of blood in a fluid using a computer are also provided. The method may be performed using a computer device having a graphical user interface (GUI), a processor configured to receive information input by a user at the user interface (type of canister, red blood cell packing ratio of the canister, subject specific identifying information, blood hematocrit (Hct), etc.), and a means for the computing device to transmit to the user interface via an electronic network, a value of a volume of blood in a fluid and/or an approximate volume measure of blood loss. The processor determines a volume of blood in a fluid, and transmits the determined volume measure of blood to the user.

A blood pressure (BP) measuring device including a PPG sensor, having one or more light sources and one or more light detectors; a computing unit, including a receiver for receiving PPG signals from the PPG sensor and a sampling circuit, for generating PPG signals samples of the PPG signals, where the device also includes a processor having BP calculation functionality, for processing the PPG signals samples into sequential BP values and a BP output unit, for outputting the calculated BP values, where the sampling circuit is adapted to sample at high sampling rate and provide BP values at a rate higher than 1 BP value per second, where the device may also include an electrogram sensor, having one or more electrodes for outputting tissue electrical activity values, the computing unit is connected to the electrogram sensor.

Systems and methods for assessing fluids from a patient are disclosed. The system includes a receptacle including an inlet port, an outlet port, and a third port; a valve system in fluidic communication with the receptacle; and one or more features in the receptacle to aid in optical imaging of fluids. The system has a fill mode and a flush mode. In the fill mode, the valve system directs suction from a vacuum source through the third port into the receptacle, thereby drawing fluid through the inlet port into the receptacle. In the flush mode, the valve system directs suction from the vacuum source through the outlet port, thereby drawing fluid through the outlet port out of the receptacle. Fluid-related information such as, for example, concentration of a blood component, may be estimated based on images of fluids in the receptacle.

A technique for predicting fluid responsiveness in a critically ill patient comprises measuring physiological data of the patient, then generating an estimate of pulse pressure variability from a Fourier transform of the physiological waveform. Both invasive and non-invasive physiological data measurements may be used.

Novel tools and techniques for assessing, predicting and/or estimating effectiveness of fluid resuscitation of a patient and/or an amount of fluid needed for effective resuscitation of the patient, in some cases, noninvasively.

In accordance with the present disclosure, deep-learning techniques are employed to find anomalies corresponding to bleed events. By way of example, a deep convolutional neural network or combination of such networks may be trained to determine the location of a bleed event, such as an internal bleed event, based on ultrasound data acquired at one or more locations on a patient anatomy. Such a technique may be useful in non-clinical settings.