Systems and methods for comprehensive medical diagnosis, prognosis, and treatment optimization are provided. A neural network is trained on a large dataset of medical images or raw data from various imaging modalities, such as ultrasound, MRI, CT, and X-ray, which are labeled with ground truth diagnoses of a wide range of medical conditions. The trained neural network can then be provided with medical images of a patient, and the neural network can make predictions and provide insights related to the presence, absence, severity, progression, or risk of various medical conditions. These predictions and insights can support clinical decision-making and enable early intervention, personalized treatment, and improved patient outcomes. The system can be continually updated with new data to improve its performance over time, and can be integrated into healthcare workflows to enhance the accuracy, efficiency, and effectiveness of medical diagnosis and treatment.

Some embodiments of the present disclosure provide methods and systems for determining a hemodynamic parameter. The method may include: obtaining image data of a subject being acquired in a rest state; obtaining a trained machine learning model; and determining, based on the trained machine learning model, at least one target hemodynamic parameter of the subject. The trained machine learning model may be obtained based on multiple sets of sample image data. Each set of the multiple sets of sample image data may include a first image data and at least one of a second image data or a third image data. The first image data may be acquired in a rest state of a first sample subject, the second image data may be acquired in a hyperemic state of the first sample subject, and the third image data may be acquired in a hyperemic state of a second sample subject including the first sample subject.

A computer-implemented method for determining a vascular function of a perfusion imaging sequence, includes the steps of: (i) receiving a perfusion imaging sequence comprising a voxel time series for a plurality of voxels; (ii) applying a trained classifier on the perfusion imaging sequence for receiving voxel-wise weights; (iii) receiving voxel-wise weights from the classifier; and (iv) determining the vascular function as the weighted sum of the voxel time series; wherein the classifier is trained by optimizing over the similarity between a predicted vascular function and a ground truth vascular function using a set of examples.

The invention relates to a method for imaging a living biological tissue, comprising: obtaining (S1) a plurality of successive colour images of said biological tissue, the processing method comprising a calibration phase (S2) in which at least one zonal time-dependent vector representative of the time evolution of spatial averages of intensity values of each of the colours in an area of the images is determined (S21), a bandpass filter centred on a heartbeat frequency is applied (S24), then a projection basis is determined (S26) by principal component analysis of the filtered zonal time-dependent vector, the method comprising deriving (S33) colour data representative of the time evolution of luminous intensities of the living biological tissue in the tissue images, and projecting (S35) colour data onto the projection basis.

Methods for characterizing fluids from a patient. A time series of images of a conduit are received, and a conduit image region in the images is identified. A flow type of the fluids passing through the conduit may be classified as one of air, laminar liquid, and turbulent liquid by evaluating an air-liquid boundary of the fluid. A volumetric flow rate of the fluids in the conduit is estimated. The volumetric flow rate may be based on the classified flow type. A concentration of a blood component of the fluids passing through the conduit may be estimated based on the images. A proportion of the fluid that is blood may also be determined, and a volume of blood that has passed through the conduit within a predetermined period of time may be estimated based on the estimated total volumetric flow rate and the determined proportion.

The present disclosure includes methods, apparatuses, and systems for three-dimensional phenotyping and physiologic characterization of brain lesions and tissue encompassing one or more enlarged boundaries surrounding the brain lesion to study the metabolic and physiologic profiles from tissue within and around lesions and their impacts on lesion shape and surface texture. The non-invasive biomarker blood-oxygen their impacts on lesion shape and surface texture. The non-invasive biomarker blood-oxygen-level-dependent (BOLD) slope was used to metabolically characterize lesions. Metabolically active lesions with more intact tissue and myelin architecture have more symmetrical shapes and more complex surface textures compared to metabolically inactive lesions with less intact tissue and myelin architecture. The association of lesions' shapes and surface features with their metabolic signatures aid in the translation of MRI data to clinical management by providing information related to metabolic activity, lesion age, and risk for disease reactivation and self-repair.

The method comprises identifying, in a 3D volume, a zone of a first type (H), a zone of a second type (BZ) and a zone of a third type (C) and: automatically identifying as a candidate channel (bz) a path running through the zone of a second type (BZ) and extending between two points of the zone of a first type (H); andautomatically performing, on a topological space (H_and_BZ_topo), homotopic operations between the candidate channel (bz) and paths (h) running only through the zone of a first type (H), and if the result of said homotopic operations is that the candidate channel (bz) is not homotopic to any path running only through the zone of a first type (H) identifying the candidate channel (bz) as a constrained channel. The computer program product implements the steps of the method of the invention.

Computer aided visualization and diagnosis by volume analysis of optical coherence tomography (OCT) angiographic data. In one embodiment, such analysis comprises acquiring an OCT dataset using a processor in conjunction with an imaging system; evaluating the dataset, with the processor, for flow information using amplitude or phase information; generating a matrix of voxel values, with the processor, representing flow occurring in vessels in the volume of tissue; performing volume rendering of these values, the volume rendering comprising deriving three dimensional position and vector information of the vessels with the processor; displaying the volume rendering information on a computer monitor; and assessing the vascularity, vascular density, and vascular flow parameters as derived from the volume rendered images.

A medical system is provided for three-dimensional hemodynamic quantification. Comprehensive three-dimensional (3D) plus time (3D+t) assessment of flow patterns inside the heart are provided by a combination of lumped-parameter modeling and computational flow dynamic modeling. Using medical scanning, the lumped parameter model is personalized to a given patient. The personalized lumped-parameter model provides pressure curves (i.e., pressure as a function of time) for one or more locations. Using geometry of the patients heart segmented from the medical scanning and the pressure curves as boundary conditions, the computational flow dynamics model calculates the absolute pressure for any location (e.g., for a three-dimensional field of locations) in the patient heart at any one or more phases of the cardiac cycle. More accurate absolute pressure may be provided without invasive measurement.

A system and method for estimating perfusion parameters using medical imaging is provided. In one aspect, the method includes receiving a perfusion imaging dataset acquired from a subject using an imaging system, and assembling for a selected voxel in the perfusion imaging dataset a perfusion patch that extends in at least two spatial dimensions around the selected voxel and time. The method also includes correlating the perfusion patch with an arterial input function (AIF) patch corresponding to the selected voxel, and estimating at least one perfusion parameter for the selected voxel by propagating the perfusion patch and AIF patch through a trained convolutional neural network (CNN) that is configured to receive a pair of inputs. The method further includes generating a report indicative of the at least one perfusion parameter estimated.