An artificial neural network-based method for selecting a surface type of an object includes receiving at least one object image, performing surface type identification on each of the at least one object image by using a first predictive model to categorize the object image to one of a first normal group and a first abnormal group, and performing surface type identification on each output image in the first normal group by using a second predictive model to categorize the output image to one of a second normal group and a second abnormal group.

An artificial neural network-based method for selecting a surface type of an object includes receiving at least one object image, performing surface type identification on each of the at least one object image by using a first predictive model to categorize the object image to one of a first normal group and a first abnormal group, and performing surface type identification on each output image in the first normal group by using a second predictive model to categorize the output image to one of a second normal group and a second abnormal group.

In an example method, a computer system receives one or more images of one or more bones of a patient. The one or more images are generated by a magnetic resonance imaging (MRI). The computer system determines one or more metrics indicative of an image texture of the one or more images; and determines at least one of a bone risk or a bone health of the patient based on the one or more metrics.

Provided is a medical image analyzing system and a method thereof, which includes: acquiring a processed image having a segmentation label corresponding to a cancerous part of an organ (if present), generating a plurality of image patches therefrom, performing feature analysis on the image patches and model training to obtain prediction values, drawing a receiver operating characteristic curve using the prediction values, and determining a threshold with which determines whether the image patches are cancerous, so as to effectively improve the detection rate of, for example, pancreatic cancer.

A computed tomography (CT) method and apparatus including a radiation source configured to produce radiation directed to an object space, and a plurality of detector elements configured to detect the radiation produced from the radiation source through the object space and generate projection data. A rotation mount is configured to rotate the radiation source around the object space. Processing circuitry is configured to cause the rotation mount to rotate the radiation source, and to receive the projection data. The projection data includes a plurality of projection data sets. The processing circuitry calculates a set of weights based on the projection data sets, calculates a set of pre-weights based on the weights, and minimizes a penalized weighted least-squares cost function to produce a reconstructed image. The cost function is a sum of a weighted least-squares term, weighted using the weights, and a penalty term weighted using the pre-weights.

Certain aspects of the present disclosure provide techniques for performing tabular convolution, including performing a tabularization operation on input data to generate a tabularized representation of the input data and performing a convolution operation using the tabularized representation of the input data to generate a convolution output.

Certain aspects of the present disclosure provide techniques for performing tabular convolution, including performing a tabularization operation on input data to generate a tabularized representation of the input data and performing a convolution operation using the tabularized representation of the input data to generate a convolution output.

Disclosed are systems and methods for clinical trial assessment of skin disease treatment. The disclosure includes obtaining a series of digital images over a period of time, wherein each digital image includes an affected area of the subject; identifying characteristic morphologies and lesions in the affected area of the subject in each of the digital images; classifying each of the detected and segmented morphologies and lesions into one or more identified categories for each of the digital images; assigning a global score to each of the digital images based on a count of the detected and segmented characteristic morphologies and lesions in each of the one or more identified categories; analyzing the global scores of each of the digital images; and making an assessment of the clinical trial based on the analysis of the global scores of each of the digital images.

A method includes obtaining at least a first energy dependent spectral image volume and a second different energy dependent spectral image volume from reconstructed spectral image data. The method further includes generating a multi-dimensional spectral diagram that maps, for each voxel, a value of the first energy dependent spectral image volume to a corresponding value of the second energy dependent spectral image volume. The method further includes generating a set of spectral texture analysis weights from the multi-dimensional spectral diagram. The method further includes retrieving a set of texture analysis functions, which are generated as a function of voxel intensity and voxel gradient value from a co-occurrence matrix histogram. The method further includes generating a texture analysis map through a texture analysis of the reconstructed spectral image data with the set of texture analysis functions and the set of spectral texture analysis weights and visually presenting the texture analysis map.

A method includes obtaining at least a first energy dependent spectral image volume and a second different energy dependent spectral image volume from reconstructed spectral image data. The method further includes generating a multi-dimensional spectral diagram that maps, for each voxel, a value of the first energy dependent spectral image volume to a corresponding value of the second energy dependent spectral image volume. The method further includes generating a set of spectral texture analysis weights from the multi-dimensional spectral diagram. The method further includes retrieving a set of texture analysis functions, which are generated as a function of voxel intensity and voxel gradient value from a co-occurrence matrix histogram. The method further includes generating a texture analysis map through a texture analysis of the reconstructed spectral image data with the set of texture analysis functions and the set of spectral texture analysis weights and visually presenting the texture analysis map.