6 results about "Optic disc" patented technology

The application provides an eye fundus image acquisition method and device based on an eye fundus camera. A first eye position shooting request is received, and an internal fixation light mark is set to move a preset distance in a nasal direction in a center area of a display interface. A preview image of an eye of a detected person is acquired by a preview image acquisition unit, and a macula, a disc, and an artifact of the preview image are identified. When the artifact does not block a macula position and a disc position, an eye fundus image of the eye of the detected person is acquired by an eye fundus image capture unit. When the artifact blocks the macula position and / or the disc position, the internal fixation light mark is moved between the macula and the disc. This method can change the response position of the internal fixation light by adjusting the internal fixation light mark, so that the artifact in the finally acquired eye fundus image does not block the macula position and the disc position, thereby effectively avoiding information loss and helping doctors diagnose diseases.

The invention discloses a layered double-flow diffusion model fundus image generation method for marking optic disk atrophy arcing, a double-flow generation framework is designed, the framework decouples a diffusion process into macroscopic semantic generation and fine-grained detail refinement, and the contradiction between generation of fine details and characterization of high-level perception features of a submerged space diffusion model is balanced. A corresponding two-stage generation strategy is designed to enhance the guidance from semantics to details, so that the authenticity and quality of the generated image are remarkably improved; an eye fundus perception loss is designed, a basic model for training on a large amount of eye fundus data is adopted as an image feature extractor, the problem of domain offset caused by the fact that a traditional feature extraction network based on natural image pre-training calculates perception loss is solved, and the representation capacity of an encoder for eye fundus image features is improved; according to the method, image generation is controlled by the optic disk atrophy arc mask in the training stage, and the normal form of generating the eye fundus image only by inputting the optic disk atrophy arc mask is realized.

According to an embodiment of the present invention, a UFI conversion system comprises: a collection unit for collecting a plurality of fundus images; a memory for storing a program for generating, from UFI, a CFI generation image corresponding to a CFI; and a processor for generating the CFI generation image on the basis of the plurality of fundus images by executing the program, wherein the processor comprises: a scale adjustment unit that identifies the positions of an optic disk and a macula from a first UFI from among the plurality of fundus images, and cutting the first UFI and adjusting the size thereof on the basis of the position of the optic disk; a matching unit for matching the first UFI with a first CFI matched to the first UFI from among the plurality of fundus images; and an image conversion unit for training a deep learning model for generating the CFI generation image from the UFI on the basis of the first UFI and the first CFI.

The invention discloses an optic disc atrophy arc weakly supervised segmentation method based on a visual language model, and belongs to the field of fundus retina image processing. The method comprises the following steps: constructing a bimodal encoder comprising a visual feature encoder and a text encoder; a visual language multi-modal feature alignment mechanism is introduced, visual representation learning is guided by using priori knowledge in medical text description, cross-modal association of images and lesion semantics is established in a unified feature space, and accurate alignment of visual and text features is realized; generating a focus attention heat map based on the alignment features, designing an adaptive multi-channel prompt generation network, and automatically mining high-confidence positive and negative prompt points from the heat map; and taking the generated prompt point as a position guide input segmentation basic model SAM, and realizing fine extraction of the optic disk atrophy arc boundary under the weak supervision condition of only text description by utilizing the strong zero sample segmentation capability of the SAM.

The application discloses a disc and cup segmentation method based on unsupervised domain adaptation, which comprises the following steps: obtaining a source domain fundus image dataset and a target domain fundus image dataset and processing; constructing a disc and cup segmentation original model and training to obtain a source domain disc and cup segmentation result and a disc and cup segmentation model; using the disc and cup segmentation model to perform disc and cup segmentation on the target domain fundus image dataset to obtain a target domain disc and cup segmentation result; constructing a disc and cup region discriminator and a disc and cup boundary discriminator; using the disc and cup region discriminator and the disc and cup boundary discriminator to discriminate the segmentation result; optimizing and verifying the disc and cup segmentation model to obtain a disc and cup segmentation application model; and using the disc and cup segmentation application model to perform actual disc and cup segmentation. The application also discloses an imaging method comprising the disc and cup segmentation method based on unsupervised domain adaptation. The application has high reliability, good accuracy and wide application range.