Abstract: A computer-implemented method of segmenting computed tomography images of teeth comprising obtaining a first 3D digital model representing crowns of erupted teeth of a first jaw and a 2D CT image sequence of the first jaw; using a local image classification model to select from the sequence, for each erupted tooth, a 2D CT image from which segmentation of the erupted tooth starts, the local image classification model being a trained deep neural network for classifying a local 2D CT image as crown or root; obtaining position and coverage information of each erupted tooth based on the first 3D digital model; and using the position and coverage information and a local image segmentation model to segment local images of the erupted tooth starting from the selected 2D CT image towards the crown and the root of the erupted tooth to obtain a binary mask image sequence of the tooth.

Abstract: The present disclosure provides a fluorescence image registration method, the method includes: acquiring a fluorescence image of a biochip; selecting a preset local region of the fluorescence image; acquiring a position of a minimum value of a sum of brightness values of pixels in a first direction and a second direction, and obtaining pixel-level registration points; dividing the pixel-level registration points into non-defective pixels and defective pixels; if the fluorescence image meets the preset standard, correcting positions of the defective pixels according to positions of the non-defective pixels; acquiring a position of a center of gravity of image points of fluorescent molecules according to a center of gravity method; fitting straight lines in the first direction and the second direction respectively according to the position of the center of gravity; and acquiring boundary points of the fluorescence image and calculating the positions of the boundary points.