Abstract: This application describes a medical image classification method, a model training method, and a server. The medical image classification method includes: obtaining, by a device, a medical image data set. The device includes a memory storing instructions and a processor in communication with the memory. The method includes performing, by the device, quality analysis on the medical image data set, to extract feature information of a medical image in the medical image data set; and classifying, by the device, the medical image data set based on the feature information and by using a pre-trained deep learning network for performing anomaly detection and classification, to obtain a classification result.

Abstract: Embodiments of this application disclose methods, systems, and devices for medical image analysis and medical video stream processing. In one aspect, a method comprises extracting video frames from a medical image video stream that includes at least two pathological-section-based video frames. The method also comprises identifying single-frame image features in the video frames, mapping the single-frame image features into single-frame diagnostic classification results, and performing a classification mapping based on a video stream feature sequence that comprises the single-frame image features. The classification mapping comprises performing a convolution operation on the video stream feature sequence through a preset convolutional layer, obtaining a convolution result in accordance with the convolution operation, and performing fully connected mapping on the convolution result through a preset fully connected layer.

Abstract: This application discloses an artificial intelligence-based image processing method, apparatus, device, and storage medium, and relates to the field of computer technology. The method includes: obtaining a slice image; dividing the slice image to obtain a plurality of image blocks; feeding the plurality of image blocks into a labeling model, extracting, by the labeling model, a pixel feature of the slice image based on the plurality of image blocks, determining a plurality of vertex positions of a polygonal region in the slice image based on the pixel feature, concatenating the plurality of vertex positions, and outputting label information of the slice image, the polygonal region being a region in which a target pathological tissue of interest is located.

Abstract: A computer device obtains a to-be-annotated image having a first magnification. The device obtains an annotated image from an annotated image set, the annotated image distinct from the to-be-annotated image and having a second magnification that is distinct from with the first magnification. The annotated image set includes at least one annotated image. The device matches the to-be-annotated image with the annotated image to obtain an affine transformation matrix, and generates annotation information of the to-be-annotated image according to the affine transformation matrix and the annotated image. In this way, annotations corresponding to images at different magnifications may be migrated. For example, the annotations may be migrated from the low-magnification images to the high-magnification images, thereby reducing the manual annotation amount and avoiding repeated annotations, and further improving annotation efficiency and reducing labor costs.

Abstract: This application describes a medical image classification method, a model training method, and a server. The medical image classification method includes: obtaining, by a device, a medical image data set. The device includes a memory storing instructions and a processor in communication with the memory. The method includes performing, by the device, quality analysis on the medical image data set, to extract feature information of a medical image in the medical image data set; and classifying, by the device, the medical image data set based on the feature information and by using a pre-trained deep learning network for performing anomaly detection and classification, to obtain a classification result.

Abstract: Embodiments of this application disclose methods, systems, and devices for medical image analysis and medical video stream processing. In one aspect, a method comprises extracting video frames from a medical image video stream that includes at least two pathological-section-based video frames. The method also comprises identifying single-frame image features in the video frames, mapping the single-frame image features into single-frame diagnostic classification results, and performing a classification mapping based on a video stream feature sequence that comprises the single-frame image features. The classification mapping comprises performing a convolution operation on the video stream feature sequence through a preset convolutional layer, obtaining a convolution result in accordance with the convolution operation, and performing fully connected mapping on the convolution result through a preset fully connected layer.