The present invention relates to methods for assessing or obtaining an indication of vascular pressure associated with organs or visceral tissues of the body by using MRI imaging methods. The invention particularly relates to methods for assessing or obtaining an indication of portal hypertension using Magnetic Resonance T1, or T1 and T2* relaxometry, and T1, T2, and/or T2* mapping of the liver or spleen.

Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are commonly used to assess patients with known or suspected pathologies of the lungs and liver. In particular, identification and quantification of possibly malignant regions identified in these high-resolution images is essential for accurate and timely diagnosis. However, careful quantitative assessment of lung and liver lesions is tedious and time consuming. This disclosure describes an automated end-to-end pipeline for accurate lesion detection and segmentation.

A liver fibrosis recognition method based on medical images and a computing device using thereof obtains a plurality of first binary images by segmenting a region of interest in each of a plurality of medical images of a liver. A rectangular region is created for each first binary image, and a plurality of second binary images is obtained by generating a second binary according to each rectangular region and the first binary image. A feature map is obtained from each liver medical image and images are generated according to the second binary images and corresponding to the plurality of feature maps. A model for recognition is iteratively trained based on the plurality of final images and recognition of liver fibrosis in patients is then achievable using the model.

The present disclosure is related to systems and methods for feature information determination. The method may include obtaining at least one image including a subject. The method may include determining a segmentation result by segmenting the at least one image using at least one segmentation model. The segmentation result may include at least one target region of the subject in the at least one image. The method may include determining feature information of the at least one target region based on at least one parameter of the at least one target region.

A lesion detection and classification artificial intelligence (AI) pipeline comprising a plurality of trained machine learning (ML) computer models is provided. First ML model(s) process an input volume of medical images (VOI) to determine whether VOI depicts a predetermined amount of an anatomical structure. The AI pipeline determines whether criteria, such as a predetermined amount of an anatomical structure of interest being depicted in the input volume, are satisfied by output of the first ML model(s). If so, lesion processing operations are performed including: second ML model(s) processing the VOI to detect lesions which correspond to the anatomical structure of interest; third ML model(s) performing lesion segmentation and combining of lesion contours associated with a same lesion; and fourth ML models processing the listing of lesions to classify the lesions. The AI pipeline outputs the listing of lesions and the classifications for downstream computing system processing.

A lesion detection ensemble machine learning model architecture comprising a plurality of trained machine learning (ML) computer models is provided. A first decoder of a lesion detection ML model processes a medical image input to generate a first lesion mapping prediction. A second decoder of the lesion detection ML model processes the medical image input to generate a second lesion mapping prediction. Combinational logic combines the first and second lesion mapping predictions to generate a combined prediction. Final lesion mapping output logic generates a final lesion prediction based on the combined lesion mapping prediction. The final lesion mapping output logic outputs the final lesion prediction for further downstream computing operations. The first decoder is trained with a first loss function that is configured to counterbalance a training of the second decoder that is trained using a second loss function different from the first loss function.

In a magnetic resonance method and apparatus for determination of a measurement variable that is relevant to a function of an organ of a patient, a first longitudinal relaxation rate R.sub.1.sup.1 is determined before a contrast medium is administered to the patient. A second longitudinal relaxation rate R.sub.1.sup.2 is determined after a contrast medium is administered to the patient. A property of the contrast medium in the organ is determined based on R.sub.1.sup.1 and R.sub.1.sup.2. The measurement variable is determined based on the property of the contrast medium in the organ.

The present invention relates to a novel automated pattern recognition and scoring method of histological images.

The present invention relates to a method for assessing the presence and/or the severity of a lesion in an organ or tissue of a subject through automated analysis of at least one image of said organ or tissue, wherein said organ or tissue is preferably a liver organ or liver tissue, comprising the calculation of a score combining descriptors of said image, wherein said method comprises the steps of: a. measuring on said at least one image at least two descriptors of said at least one image; b. mathematically combining said at least two descriptors in a score; and c. assessing the presence and/or the severity of a lesion in the organ or tissue based on the value of the score calculated at step (b).

Example embodiments of the described technology provide systems and methods for ultrasound imaging. An example method may detect the presence of shear waves within a tissue region of a patient. The method may comprise exciting the tissue region of the patient with one or more exciters to induce propagation of shear waves within the tissue. A plurality of ultrasound images of the tissue may be acquired. A first image mask indicating which pixels of the acquired images represent a desired tissue type using a first trained machine learning model may be generated. The method may also comprise generating a second image mask indicating which pixels of the acquired images represent shear waves using a second trained machine learning model.