Abstract: Systems and methods for autofocus using artificial intelligence include (i) capturing a plurality of monochrome images over a nominal focus range, (ii) identifying one or more connected components within each monochrome image, (iii) sorting the identified connected components based on a number of pixels associated with each connected component, (iv) generating a focus quality estimate of at least a portion of the sorted connected components using a machine learning module, and (iv) calculating a target focus position based on the focus quality estimate of the evaluated connected components. The calculated target focus position can be used to perform cell counting using artificial intelligence, such as by (i) generating a seed likelihood image and a whole cell likelihood image based on output—a convolutional neural network and (ii) generating a mask indicative quantity and/or pixel locations of objects based on the seed likelihood image.

Abstract: Systems and methods for identifying clumps (or groupings) of cells in cell counting systems. One example method executed by an electronic processing device for an image processing system includes receiving an image, captured by an imaging device, of a sample having a plurality of cells. The image includes labeling data for each of the plurality of cells. The method includes applying filters, determined based on the labeling data, to the image, processing the image to identify a plurality of groupings of the plurality of cells, and fitting an ellipse around each of the groupings by determining ellipse data for each of the ellipses. Each respective grouping of the plurality of groupings includes at least two cells having a same viability whose cell membranes are touching at least one other cell in the respective grouping.

Abstract: Disclosed herein are machine learning-based particle classification systems, as well as related methods, computing devices, and computer-readable media. For example, in some embodiments, a particle classification system may include: an electronic processing device configured to: receive, from an imaging flow cytometer instrument, a test set comprising unlabeled data to classify; pool the test set and a training set into a concatenated dataset comprising a plurality of parameters, wherein the training set comprises labeled data; normalize the concatenated dataset by bringing the variance to one for each of the plurality of parameters; non-linearly reduce a dimensionality of the normalized concatenated dataset to a reduced dimension space; compute classification parameters by classifying the unlabeled data from the reduced dimension space using the labeled data from the reduced dimension space; and provide the classification parameters for further processing.

Abstract: Examples described herein provide systems and methods for quantifying cells. An example method includes receiving at least one image, improving a contrast of the at least one image to generate a contrast image, and performing a fit operation on the contrast image to generate a processed image. The method includes applying a filter to the processed image to generate a filtered image, identifying cells within the filtered image, and providing an output image including an indication of the cells.

Abstract: Aspects of the subject technology provide improved pixel detection techniques including improvements to motion detection and processing resource conservation. Improved techniques include determining a metric of mutual information between a pair of images from a sequence of images of a biological sample, detecting a motion of the biological sample based on the metric of mutual information, and, after the motion is detected, performing a measurement of the biological sample based on a test image of the sequence of images.

Abstract: An embodiment includes analyzing a body part perfused with a contrast agent, which has been pre-administered as a bolus to circulate through the body-part with at least a first passage during an analysis interval. The analyzing includes providing at least one input signal indicative of a response to an interrogation signal of a corresponding location of the body part during the analysis interval, and fitting each input signal over the analysis interval by an instance of a combined bolus function of time, based on a combination of a first simple bolus function of time modeling the first passage of the contrast agent and at least one second simple bolus function of time each one modeling a corresponding second passage of the contrast agent.

Abstract: Systems and methods for autofocus using artificial intelligence include (i) capturing a plurality of monochrome images over a nominal focus range, (ii) identifying one or more connected components within each monochrome image, (iii) sorting the identified connected components based on a number of pixels associated with each connected component, (iv) generating a focus quality estimate of at least a portion of the sorted connected components using a machine learning module, and (iv) calculating a target focus position based on the focus quality estimate of the evaluated connected components. The calculated target focus position can be used to perform cell counting using artificial intelligence, such as by (i) generating a seed likelihood image and a whole cell likelihood image based on output—a convolutional neural network and (ii) generating a mask indicative quantity and/or pixel locations of objects based on the seed likelihood image.

Abstract: A solution for diagnostic applications is proposed. Particularly, a corresponding diagnostic system includes means (903-906) for providing (A1-A3) a plurality of input signals representative of a body-part being perfused with a contrast agent over time, each input signal being indicative of a response to an interrogating stimulus of a corresponding location of the body-part possibly including the contrast agent, means (909-930) for generating (A4.1-A4.3) a plurality of filtered signals from selected input signals of selected locations, each filtered signal at each instant over time being generated from a corresponding selected input signal according to a portion of the selected input signal including said instant, and means (933-939) for monitoring (A4.4-A4.

Abstract: An embodiment is proposed for analyzing a body-part perfused with a contrast agent, which has been pre-administered as a bolus to circulate through the body-part with a first passage and possibly with at least one second passage during an analysis interval.

Abstract: An embodiment includes analyzing a body part perfused with a contrast agent, which has been pre-administered as a bolus to circulate through the body-part with at least a first passage during an analysis interval. The analyzing includes providing at least one input signal indicative of a response to an interrogation signal of a corresponding location of the body part during the analysis interval, and fitting each input signal over the analysis interval by an instance of a combined bolus function of time, based on a combination of a first simple bolus function of time modeling the first passage of the contrast agent and at least one second simple bolus function of time each one modeling a corresponding second passage of the contrast agent.

Abstract: A data-processing method includes providing a parametric map including a plurality of parameter values, each one characterizing a corresponding location of a body-part. The method includes determining at least one statistical indicator of at least one distribution of a plurality of analysis parameter values corresponding to selected analysis locations, each statistical indicator being indicative of a condition of an analysis region of the body-part defined by the analysis locations.

Abstract: A system for facilitating the detection of an immobilized contrast agent in medical imaging applications is proposed.

Abstract: A tissue response in a predetermined unit of volume or area tissue of interest is determined by excluding some data of the adjacent tissues based upon a blood flow direction with respect to the tissue of interest. The exclusion is based upon a predetermined time-related parameter such as time-to-peak and mean-transit time in the fitted curves of the uptake of a contrast agent in the adjacent tissues and the tissue of interest. Furthermore, the blood flow direction is determined in terms of a 3D vector based upon a plurality of weighted individual vectors from the adjacent or neighboring voxels with respect to the voxel of interest.

Abstract: An embodiment for analyzing a body-part of a patient is proposed.

Abstract: A tissue response in a predetermined unit of volume or area tissue of interest is determined by excluding some data of the adjacent tissues based upon a blood flow direction with respect to the tissue of interest. The exclusion is based upon a predetermined time-related parameter such as time-to-peak and mean-transit time in the fitted curves of the uptake of a contrast agent in the adjacent tissues and the tissue of interest. Furthermore, the blood flow direction is determined in terms of a 3D vector based upon a plurality of weighted individual vectors from the adjacent or neighboring voxels with respect to the voxel of interest.

Abstract: An embodiment of a system is proposed for imaging a body part including a tissue, the body part being perfused with a contrast agent. The system includes means for providing a sequence of original images offering a digital representation over time of the body-part, each original image including a plurality of original values each one indicative of a response to an interrogation signal of a corresponding location of the body-part possibly including the contrast agent with a contribution of the tissue substantially reduced.

Abstract: An input image includes a plurality of input values (i.e., pixel or voxel values), each input value indicative of a response to an interrogation signal of a corresponding location of a body-part, which possibly includes a contrast agent. At least one filtered image is generated from a plurality of selected input images and includes a filtered value for each of a plurality of selected ones of the locations. Each filtered value is indicative of the contrast agent leaving the selected location and is obtained by reducing a contribution of the contrast agent that is substantially stationary at the selected location along the selected input images for a period of time equal to or shorter than a first threshold and by reducing a contribution of the contrast agent that is substantially stationary for a period of time equal to or longer than a second higher threshold.

Abstract: A perfusion assessment system is proposed. The system includes means for providing an echo-power signal indicative of a perfusion of a contrast agent in a body-part under analysis, the contrast agent being administered as a bolus and undergoing a significant destruction during a passage of the contrast agent in the body-part, means for associating the echo-power signal to a model function including the product between a bolus function indicative of the passage of the contrast agent without said destruction and a reperfusion function indicative of a reperfusion of the contrast agent in the body part following the destruction corresponding to a substantially constant inflow of the contrast agent, and means for estimating at least one perfusion indicator from the bolus function and/or the reperfusion function.

Abstract: An embodiment includes analyzing a body part perfused with a contrast agent, which has been pre-administered as a bolus to circulate through the body-part with at least a first passage during an analysis interval. The analyzing includes providing at least one input signal indicative of a response to an interrogation signal of a corresponding location of the body part during the analysis interval, and fitting each input signal over the analysis interval by an instance of a combined bolus function of time, based on a combination of a first simple bolus function of time modeling the first passage of the contrast agent and at least one second simple bolus function of time each one modeling a corresponding second passage of the contrast agent.

Abstract: An embodiment for analyzing a body-part of a patient is proposed.