In various example embodiments, techniques are provided for training and/or using a semantic deep learning model, such as a segmentation-enabled CNN model, to detect corrosion and enable its quantitative evaluation. An application may include a training dataset generation tool capable of semi-automatic generation of a training dataset that includes images with labeled corrosion segments. The application may use the labeled training dataset to train a semantic deep learning model to detect and segment corrosion in images of an input dataset at the pixel-level. The application may apply an input dataset to the trained semantic deep learning model to produce a semantically segmented output dataset that includes labeled corrosion segments. The application may include an evaluation tool that quantitatively evaluates corrosion in the semantically segmented output dataset, to allow severity of the corrosion to be classified.

An image processing apparatus according to an embodiment of the present disclosure includes processing circuitry. The processing circuitry is configured to obtain volume data of a subject. The processing circuitry is configured to obtain base tubular object data by segmenting the volume data. The processing circuitry is configured to obtain small tubular object data from the volume data. The processing circuitry is configured to generate updated base tubular object data, on the basis of the small tubular object data and the base tubular object data. The processing circuitry is configured to output the updated base tubular object data.

Disclosed herein are systems and methods for providing interactive graphical user interfaces (GUIs) for users, such as medical professionals, to glean insight about connectivity data associated with a particular brain. A method can include overlaying nodes representing locations of parcels of a patient's brain on a representation of a brain and displaying the representation of the brain with the overlaid nodes in a GUI. Nodes having connectivity above a first threshold can be represented in a first indicia and nodes having connectivity below a second threshold can be represented in a second indicia. The method can include receiving user input and taking an action based on the user input. The user input can include selecting an area of the representation of the brain for excision. Taking an action based on the input can include calculating an impact of excising the area of the brain on the particular patient.

An information processing apparatus sets a first line segment in an image obtained by image capturing, and also sets a second line segment in the image. Then, the information processing apparatus acquires color differences between points on the first line segment and points on the second line segments, and generates a color-difference map based on the acquired color differences.

Systems and methods are provided for pitch determination. An example method includes obtaining an image depicting a structure, the image being captured via a user device positioned proximate to the structure. The image is segmented to identify, at least, a roof facet of the structure. An eave vector and a rake vector which are associated with the roof facet are determined. A normal vector of the roof facet is calculated based on the eave vector and the rake vector, and compared to a vector indicating a vertical direction such as gravity. The angle made out by the normal and a gravity vector may be utilized to calculate the pitch of the roof facet.

A method and apparatus are disclosed which enable the analysis of a break in a vehicle glazing panel without the attendance of a technician, the method and apparatus utilize capturing an image of the break and processing the image of the break to enable the suitability for repair or replacement of the glazing panel to be determined.

A system for displaying medical imaging data comprising one or more data inputs, one or more processors, and one or more displays, wherein the one or more data inputs are configured for receiving first image data generated by a first medical imaging device, wherein the first image data comprises a field of view (FOV) portion and a non-FOV portion, and the one or more processors are configured for identifying the non-FOV portion of the first image data and generating cropped first image data by removing at least a portion of the non-FOV portion of the first image data, and transmitting the cropped first image data for display in a first portion of the display and additional information for display in a second portion of the display.

Systems and methods for image space control of a medical instrument are provided. In one example, a system is configured to display a two-dimensional medical image including a view of at least a distal end of an instrument. The system can determine, based on one or more fiducials on the instrument, a roll estimate of the instrument. The system further can receive a user input comprising a heading command to change a heading of the instrument within a plane of the medical image, or an incline command to change an incline of the instrument into or out of the plane of the medical image. Based on the roll estimate and the user input, the system can generate one or more motor commands configured to cause a robotic system coupled to the medical instrument to move the robotic medical instrument.

A method and a system for processing an image and transform it into a high resolution and high-definition image using a computationally efficient image transformation procedure is provided. The transformation of the image comprises receiving, at a first input interface, a layered distance field (DF) image including an ordered sequence of multiple layers. Each layer of the layered DF image includes a DF procedure defining DF values at all locations of the received intensity image and rules for mapping these DF values into intensity values of the layer. The transformation of the image further comprises, receiving, at a second input interface, a transformation instruction and transforming the layered DF image based on the transformation instruction.

The invention relates to a computer-implemented method for segmenting measurement data from a measurement of an object, the object having at least one Material transition region, the measurement data generating a digital representation of the object having the at least one at least one material transition region, the digital object representationhaving a plurality of pieces of spatially-resolved image information of the object, the method comprising the following steps: determining the measurement data; segmenting at least two homogenous regions of the digital object representation; and determining the position of at least one material transition region between the at least two homogeneous regions. The invention thus provides an improved computer-implemented method for segmenting measurement data from a measurement of an object, which correctly detects material transitions from the measurement data of the object.