Abstract: Much of the image processing that is applied to medical images is a form of “inverse problem”. This is a class of mathematical problems in which a “forward” model by which a signal is converted into dataset is known, to at least some degree, but where the aim is to reconstruct the signal given the resulting dataset. Thus, an inverse problem is essentially seeking to discover x given knowledge of A(x)+noise by finding an appropriate reconstruction operator A† such that A† (A(x)+noise)?x, thereby enabling us to obtain x (or a close approximation) given knowledge of an output dataset consisting of A(x)+noise. Generally, several such processes (or their equivalents) are applied to the image dataset.

Abstract: Image reconstruction can include using a statistical or machine learning, MAP estimator, or other reconstruction technique to produce a reconstructed image from acquired imaging data. A Conditional Generative Adversarial Network (CGAN) technique can be used to train a Generator, using a Discriminator, to generate posterior distribution sampled images that can be displayed or further processed such as to help provide uncertainty information about a mean reconstruction image. Such uncertainty information can be useful to help understand or even visually modify the mean reconstruction image. Similar techniques can be used in a segmentation use-case, instead of a reconstruction use case. The uncertainty information can also be useful for other post-processing techniques.

Abstract: Much of the image processing that is applied to medical images is a form of “inverse problem”. This is a class of mathematical problems in which a “forward” model by which a signal is converted into dataset is known, to at least some degree, but where the aim is to reconstruct the signal given the resulting dataset. Thus, an inverse problem is essentially seeking to discover x given knowledge of A(x)+noise by finding an appropriate reconstruction operator A† such that A† (A(x)+noise)?x, thereby enabling us to obtain x (or a close approximation) given knowledge of an output dataset consisting of A(x)+noise. Generally, several such processes (or their equivalents) are applied to the image dataset.

Abstract: Image reconstruction can include using a statistical or machine learning, MAP estimator, or other reconstruction technique to produce a reconstructed image from acquired imaging data. A Conditional Generative Adversarial Network (CGAN) technique can be used to train a Generator, using a Discriminator, to generate posterior distribution sampled images that can be displayed or further processed such as to help provide uncertainty information about a mean reconstruction image. Such uncertainty information can be useful to help understand or even visually modify the mean reconstruction image. Similar techniques can be used in a segmentation use-case, instead of a reconstruction use case. The uncertainty information can also be useful for other post-processing techniques.

Abstract: Image reconstruction can include using a statistical or machine learning, MAP estimator, or other reconstruction technique to produce a reconstructed image from acquired imaging data. A Conditional Generative Adversarial Network (CGAN) technique can be used to train a Generator, using a Discriminator, to generate posterior distribution sampled images that can be displayed or further processed such as to help provide uncertainty information about a mean reconstruction image. Such uncertainty information can be useful to help understand or even visually modify the mean reconstruction image. Similar techniques can be used in a segmentation use-case, instead of a reconstruction use case. The uncertainty information can also be useful for other post-processing techniques.

Abstract: Image reconstruction can include using a statistical or machine learning, MAP estimator, or other reconstruction technique to produce a reconstructed image from acquired imaging data. A Conditional Generative Adversarial Network (CGAN) technique can be used to train a Generator, using a Discriminator, to generate posterior distribution sampled images that can be displayed or further processed such as to help provide uncertainty information about a mean reconstruction image. Such uncertainty information can be useful to help understand or even visually modify the mean reconstruction image. Similar techniques can be used in a segmentation use-case, instead of a reconstruction use case. The uncertainty information can also be useful for other post-processing techniques.

Abstract: The present invention relates to a solution for solving an ill-posed inverse problem in image analysis, e.g. in an electron tomography application in order to recover a structure of a sample. The solution is provided for instance as a method comprising steps of determining reliable prior knowledge about the solution, determining initial guess for the solution and determining the corresponding forward operator, deciding upon model of stochasticity, deciding on suitable regularization method, deciding on updating scheme, and producing a sequence using the set configuration.

Abstract: An apparatus and a method for simulating the behaviour of a TEM based on the first-order Born approximation, the method including the following steps:—providing at least one mathematical model of a virtual specimen;—simulating the image formation in the TEM when imaging the specimen, the simulation being based on a model for image formation which fully accounts for the wave nature of the electrons within the realm of the first order Born approximation and one model for the imaging properties of the TEM instrument. This is particularly suitable for use in solving the structure determination problem in ET.

Abstract: A method to image objects from local three-dimensional parallel beam tomographic data (line integrals) over lines parallel an arbitrary curve of directions on a sphere. Such data are used in electron microscopy, SPECT (with weighted integrals), and synchrotron tomography. The algorithm is adaptable to a number of data sets including single-axis and double-axis tilt electron tomography and truly three-dimensional curves of directions. The method stably gives pictures of the internal structure of objects and does not add strong singularities or artefacts. It is less influenced by objects outside the region of interest than standard non-local methods. The algorithm is combined with an electron microscope and computer to provide computer readable files showing the pictures of small objects such as molecules.