A computer implemented method for providing output data comprising an indication regarding the affliction of a patient with an infectious respiratory disease, the method comprises receiving magnetic resonance imaging data, the magnetic resonance imaging data acquired using a magnetic resonance imaging system, the magnetic resonance imaging data comprising a lung region of the patient; applying a trained function to the magnetic resonance imaging data to generate the output data, the trained function being based on an artificial neural network and the output data comprising the indication regarding the affliction of the patience with the infectious respiratory disease; and proving the output data.

A method of identifying and locating tissue abnormalities in a biological tissue includes irradiating an electromagnetic signal, via a probe defining a transmitting probe, in the vicinity of a biological tissue. The irradiated electromagnetic signal is received at a probe, defining a receiving probe, after the signal is scattered/reflected by the biological tissue. Blood flow information pertaining to the biological tissue is provided. Based on the received irradiated electromagnetic signal and the blood flow information, tissue properties of the biological tissue are reconstructed. A tracking unit determines the position of at least one of the transmitting probe and the receiving probe while the step of receiving is being carried out, the at least one probe defining a tracked probe. The reconstructed tissue properties are correlated with the determined probe position so that tissue abnormalities can be identified and spatially located.

Systems and methods for assessing a flow of fluids suctioned from a patient. The flow of fluids may be divided according to a flow division ratio. An image of a first portion of the fluids may be evaluated to determine an estimated blood component quantity as a representative fraction of the flow of fluids. An intermittent estimate of blood loss may be determined based on the flow division ratio and the estimated blood component quantity, and a total estimate of blood loss updated based on the intermittent estimate. The representative fraction is projected or extended to be an estimated blood component quantity of the second portion of the fluids that bypasses the receptacle. The images may be continuously captured with a camera, and a fluid level of the fluids with a receptable may be continuously monitored. The total estimate of blood loss may be displayed in real-time on a display.

One aspect of the present subject matter provides an imaging method including: receiving a trigger signal; after a period substantially equal to a trigger delay minus an inversion delay, applying a non-selective inversion radiofrequency pulse to a region of interest followed by a slice-selective reinversion radiofrequency pulse to a slice of the region of interest of a subject; and after lapse of the trigger delay commenced at the cardiac cycle signal, acquiring a plurality of time-resolved images of the slice of the region of interest from an imaging device.

The present disclosure relates to an insert system for performing positron emission tomography (PET) imaging. The insert system can be reversibly installed to an existing system, such that PET functionality can be introduced into the existing system without the need to significantly modify the existing system. The present disclosure also relates to a multi-modality imaging system capable for conducting both PET imaging and magnetic resonance imaging (MRI). The PET and MRI imaging can be performed simultaneously or sequentially, while the performance of neither imaging modality is compromised for the operation of the other imaging modality.

Retinal imaging systems and related methods employ a user specific approach for controlling the reference arm length in an optical coherence tomography (OCT) imaging device. A method includes restraining a user's head relative to an OCT imaging device. A reference arm length adjustment module is controlled to vary a reference arm length to search a user specific range of reference arm lengths to identify a reference arm length for which the OCT image detector produces an OCT signal corresponding to the retina of the user. The user specific range of reference arm lengths covers a smaller range of reference arm lengths than a reference arm length adjustment range of the reference arm length adjustment module.

A method of displaying an area of interest within a surgical site includes modeling a patient's lungs and identifying a location of an area of interest within the model of the patient's lungs. The topography of the surface of the patient's lungs is determined using an endoscope having a first camera, a light source, and a structured light pattern source. Real-time images of the patient's lungs are displayed on a monitor and the real-time images are registered to the model of the patient's lungs using the determined topography of the patient's lungs. A marker indicative of the location of the area of interest is superimposed over the real-time images of the patient's lungs. If the marker falls outside of the field-of view of the endoscope, an arrow is superimposed over the real-time images to indicate the direction in which the marker is located relative to the field of view.

A method for lung nodule evaluation is provided. The method may include obtaining a target image including at least a portion of a lung of a subject. The method may also include segmenting, from the target image, at least one target region each of which corresponds to a lung nodule of the subject. The method may further include generating an evaluation result with respect to the at least one lung nodule based on the at least one target region.

A system includes a computing device that receives a query thyroid image, where the query thyroid image is an ultrasound image of a thyroid comprising a thyroid nodule of interest. The computing device processes the query thyroid nodule image using a machine learning model to identify at least one labelled thyroid image from a plurality of labelled thyroid images that is similar to the query thyroid nodule image. The plurality of labelled thyroid images are used as training data to generate the machine learning model. The at least one labelled thyroid image has labels associated therewith and comprises an ultrasound image of a thyroid nodule that has a confirmed diagnosis. The computing device generates an output report based on the labels associated with the at least one labelled thyroid image, where the output report indicates whether the thyroid nodule of interest resembles a malignant thyroid nodule or benign thyroid nodule.

A device and a method for detecting a tumor using a medical image and diagnosing a shape and a property of the detected tumor are disclosed. An exemplary medical image-based tumor detection and diagnostic device includes: an input unit configured to obtain a medical image related to a patient; a preprocessing unit configured to preprocess the obtained medical image to observe a tumor region; an analysis unit configured to divide the preprocessed image into a plurality of regions by applying a deep neural network-based deep learning technique; and a measurement unit configured to group the plurality of divided regions by performing clustering on the plurality of divided regions. The measurement unit extracts a group feature value in respect to each of the grouped regions and derives diagnosis information related to the tumor based on the extracted group feature value.