Embodiments of the disclosure provide methods and systems for representation learning from a biomedical image with a sparse convolution. The exemplary system may include a communication interface configured to receive the biomedical image acquired by an image acquisition device. The system may further include at least one processor, configured to extract a structure of interest from the biomedical image. The at least one processor is also configured to generate sparse data representing the structure of interest and input features corresponding to the sparse data. The at least one processor is further configured to apply a sparse-convolution-based model to the biomedical image, the sparse data, and the input features to generate a biomedical processing result for the biomedical image. The sparse-convolution-based model performs one or more neural network operations including the sparse convolution on the sparse data and the input features.

A multi-modality phantom is provided. The multi-modality phantom includes a container and an insert. The container defines an exterior that is separated from an interior space and designed to receive a tissue-mimicking medium for an ultrasound imaging process. The container further includes at least one access port formed in the container to perform the ultrasound imaging process of the interior space. The insert can be dimensioned to be selectively arranged within the interior space of the container. The insert includes imaging features arranged to simulate an environment and constructed to yield simultaneous imaging results when performing the ultrasound imaging process and at least one non-ultrasound imaging process.

A computer aided method for analyzing fibrosis is provided. First, a segmentation algorithm is performed on a medical image to obtain a segmentation image. Circular fibrosis is detected according to the segmentation image to determine a score. In some cases, it is also necessary to determine a number of fibrosis bridges and the condition of fiber expansion.

An image segmentation apparatus for magnetic resonance imaging according to an embodiment includes processing circuitry. The processing circuitry is configured to obtain a localizer image of an organ, the localizer image being three-dimensional or being in a plurality of layers and two-dimensional. The processing circuitry is configured to temporarily localize, on a basis of the localizer image, a segment in which the organ is present in terms of the layer direction of a plurality of slices included in the localizer image. The processing circuitry is configured to obtain a segmentation result of the organ, by performing an image segmentation process on the localizer image positioned inside the segment in which the organ is present.

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.

A non-invasive ultrasound detection device for detecting liver fibrosis and method thereof is disclosed. The method comprises the steps of: creating a discriminant function of several parameters, each with a weight obtained by LDA, based on a database; and determining the degree of liver fibrosis by comparing a reference value and a numerical value calculated from the discriminant function. The parameters represent different probability distribution functions capable of identifying liver fibrosis or fatty liver. In the step of creating a discriminant function, the database provides the processed data based on numerous ultrasound images of patents' livers for LDA. In the step of determining the degree of liver fibrosis, the processed data based on ultrasound images of a person's liver are obtained for further calculation of the numerical value. The processed data includes an average value for each probability distribution function within an area corresponding to a liver.

A mechanism is provided in a data processing system for refining lesion contours with combined active contour and inpainting. The mechanism receives an initial segmented medical image having organ tissue including a set of object contours and a contour to be refined. The mechanism inpaints object voxels inside all contours of the set. The mechanism calculates an updated contour around the contour to be refined based on the in-painted object voxels to form an updated segmented medical image. The mechanism determines whether the updated segmented medical image is improved compared to the initial segmented medical image. The mechanism keeps the updated segmented medical image responsive to the updated segmented medical image being improved.

An image processing method includes obtaining a first quantity of to-be-analyzed images and performing fusion and enhancement processing on the first quantity of to-be-analyzed images through an image analysis model to obtain a first target image. Each to-be-analyzed image corresponds to a different target modality of a target imaging object. The first target image is used to enhance display of a distribution area of an analysis object of the first quantity of to-be-analyzed images. The analysis object belongs to the imaging object. The image analysis model is obtained by training a second quantity of sample images corresponding to different sample modalities. The first quantity is less than or equal to the second quantity. The target modality belongs to the sample modalities.

Provided are a medical image displaying apparatus and a medical image displaying method for registering an ultrasound image with a previously obtained medical image and outputting a result of the registration, the medical image displaying method including: transmitting ultrasound signals to an object and receiving ultrasound echo signals from the object via an ultrasound probe of the medical image displaying apparatus; obtaining a first ultrasound image based on the ultrasound echo signals; performing image registration between the first ultrasound image and a first medical image that is previously obtained; obtaining a second ultrasound image of the object via the ultrasound probe; obtaining a second medical image by transforming the first medical image to correspond to the second ultrasound image; and displaying the second medical image together with the second ultrasound image.

A method for evaluating efficacy of a therapeutic intervention includes obtaining, from each of paired liver biopsy samples of a subject comprising a first sample prior to the therapeutic intervention and a second sample after the therapeutic intervention, a first set of image data indicative of a first histopathological feature and a second set of image data indicative of a second histopathological feature. For each of the first and second samples, the second histopathological feature is quantified, the first and second sets of image data are overlapped based on a common reference frame, and the first histopathological feature present in an overlapping area of the first and second sets of image data is quantified. The method also includes determining the efficacy of the therapeutic intervention based on a comparison of the quantified second histopathological feature between the first and second samples and/or a comparison of the quantified first histopathological feature in the overlapping area between the first and second samples. The first and second pathological features include features selected from the group consisting of fibrosis, inflammation, ballooning and steatosis.