80 results about "Dermatoscopes" patented technology

The invention discloses a medical image segmentation method and system based on guidance information and a multi-dimensional attention mechanism. The method comprises the following steps: collecting an original dermatoscope image for preprocessing; constructing a segmentation model, wherein the segmentation model comprises a double-path image encoder, a guide information encoder and a mask decoder; the two-way image encoder is used for extracting local detail features and global context semantic information in the image; the guide information encoder is used for converting a coarse segmentation mask predicted by the last round of network into guide feature information; the mask decoder fuses the image feature information and the guide feature information, gradually restores and refines the coarse-grained feature map, and finally outputs an accurate lesion segmentation mask; constructing a loss function, and training the segmentation model by using the preprocessed data; and inputting a to-be-segmented original dermatoscope image into the trained segmentation model, and outputting a lesion region segmentation mask of the image. According to the method, the segmentation precision and the model generalization ability can be improved, and the multi-scale lesion processing ability is enhanced.

The invention provides a dermatoscope image segmentation method, and relates to the technical field of medical image processing, and the method comprises the steps: inputting a to-be-segmented image into an improved encoder module, carrying out the multi-scale feature information extraction, and obtaining a deep advanced semantic feature map; inputting the deep advanced semantic feature map into the bridging module, and performing context information modeling and cross-scale feature fusion to obtain a fused feature map; inputting the fused feature map into the decoder module, and carrying out layer-by-layer up-sampling and feature integration to obtain a reconstructed feature map; inputting the reconstructed feature map into the boundary sensing double-branch module, and performing collaborative feature processing; wherein the main branch outputs a binary segmentation mask, and the auxiliary branch is used for measuring a sign distance function diagram to provide boundary perception supervision; obtaining a binary segmentation mask output by the main branch as a segmentation result; compared with an existing model, the optimized dermatoscope image segmentation model is higher in recognition accuracy.

The invention discloses an efficient medical image segmentation method considering global modeling and local enhancement, and relates to the technical field of image segmentation. According to the method, adaptive space shift operation is executed in different directions through the AS-MLP module, the long-range dependence modeling capability is effectively enhanced, and the recognition performance of a complex structure focus is improved; the channel and space double attention mechanism and multi-scale convolution of the LMCAM module are combined, so that fine-grained feature extraction is realized, and the segmentation precision of the lesion boundary and the small-scale structure is remarkably improved; a lightweight network design is adopted, the calculation complexity is low, the reasoning speed is high, and the method is suitable for resource-limited clinical terminals and real-time diagnosis application; besides, the method has good cross-modal adaptability, can keep stable and efficient segmentation performance in various medical imaging modalities such as CT, MRI, ultrasound and dermatoscope, and has wide application value.

The invention provides a skin lesion auxiliary detection method and system based on multi-modal information fusion, and belongs to the technical field of computer vision and application. The method comprises the following steps: firstly, acquiring and constructing bimodal data including a dermatoscope image and a text of a patient, and preprocessing the data; secondly, respectively adopting an improved convolutional neural network and a text coding model, and extracting deep and high-dimensional features from the skin disease image and the self-described text of the patient; afterwards, an improved symmetric gating cross attention fusion module is constructed, fine-grained interaction and alignment between visual and text features are realized through a bidirectional cross attention mechanism, and a gating unit is utilized to adaptively adjust a fusion weight; and finally, inputting the deeply fused multi-modal feature vector into a classifier to obtain a confidence score of each skin lesion type so as to provide reference for dermatologists. According to the method, the diagnosis accuracy, robustness and interpretability are synergistically improved, and the method has great clinical application value.

The invention belongs to the technical field of medical image and big data analysis, and provides an automatic skin disease diagnosis method and system based on a multi-modal big language model, and the method comprises the steps: obtaining a dermatoscope diagnosis report of a historical patient, and extracting an original image and a diagnosis text in the dermatoscope diagnosis report; constructing a multi-modal large language model, wherein the multi-modal large language model comprises a visual encoder, a linear projection layer and a large language model; training the multi-modal large language model; obtaining an external medical knowledge base, extracting text information in the external medical knowledge base, and constructing a vector database based on the text information; in response to an input image and a query text of a user, N vectors with the highest similarity are retrieved in the vector database according to the query text, the retrieved vectors are decoded into a text, and the text and the query text jointly construct complete prompt word input; and based on the input image and cue word input, obtaining a final dermatoscope diagnosis report by using the trained multi-modal large language model. The diagnosis report is automatically generated.

The invention discloses a skin lesion image segmentation method based on feature interaction fusion, and relates to the technical field of medical image segmentation. Comprising the following steps: firstly, carrying out size normalization and noise suppression on a dermatoscope image, and expanding a data set through random rotation and overturning operation; inputting the training data into the network model for training to obtain a trained model weight; and finally, inputting a to-be-segmented skin lesion image into the trained network model to realize automatic segmentation of a skin lesion area. According to the invention, a focusing feature interaction fusion module is designed, and deep complementary fusion of CNN and Transform features is realized; a multi-scale context attention module is constructed, multi-scale accurate feature extraction is realized by extracting spatial information from local scale to global scale, and meanwhile, the calculation efficiency is kept. The invention aims to solve the problems of complex shape, variable size, low contrast and the like of the lesion area of the skin lesion image, and improve the segmentation precision and robustness of the skin lesion image.

The invention relates to the technical field of deep learning and skin lesion recognition, in particular to a skin lesion image segmentation method based on edge guidance and an attention mechanism, and the method comprises the steps: inputting a to-be-segmented dermatoscope image into an image segmentation model for segmentation, and outputting a skin lesion segmented image; wherein the image segmentation model performs edge feature extraction on a dermatoscope image through an EEM module; performing multi-scale hole convolution processing on the semantic feature map through a DASPP module; adaptive fusion of channel and space attention is carried out on the segmented feature map through a CSAM module, a channel dimension and a space dimension are processed in sequence by adopting a serial design of channel priority and space postposition, and edge information of an edge prior feature map is introduced to carry out feature enhancement. According to the invention, the marginal region of the skin lesion is subjected to refined learning, and the marginal information of the lesion region is fully utilized to realize accurate positioning of the skin lesion, so that the accuracy and effect of skin lesion image segmentation are improved.

Presented herein are systems and methods for detecting basal-cell carcinoma (BCC) in biomedical images of skin lesions. A computing system may identify, for a first subject at risk of BCC in a first lesion on a region of an epidermis: (i) a first biomedical image of an outer layer of the region on the epidermis of the first subject acquired in accordance with dermoscopy, and (ii) a plurality of second biomedical images of at least one inner layer in the region on the epidermis of the first subject acquired in accordance with reflection confocal microscopy (RCM). The computing system may apply the first biomedical image and the plurality of second biomedical images to a model architecture. The computing system may generate, based on applying to the model architecture, a score indicating a likelihood of BCC in the first lesion.

The invention provides a dermatoscope image segmentation method, system and device based on Mama and a medium, and belongs to the technical field of image processing and computer vision, and the method comprises the steps: obtaining an original dermatoscope image, carrying out the preprocessing of the original dermatoscope image, and obtaining a preprocessed dermatoscope image set; acquiring a skin lesion label image corresponding to the original dermatoscope image, pairing the preprocessed dermatoscope image with the corresponding skin lesion label image, constructing a dermatoscope image data set with a label, and dividing the dermatoscope image data set into a dermatoscope image training set and a dermatoscope image test set; a neural network model based on Mama is constructed; feeding the dermatoscope image training set into a neural network model in batches for training to obtain a trained neural network model; and inputting a to-be-segmented original dermatoscope image into the trained neural network model to obtain a corresponding focus region segmentation result. According to the method, the accuracy of skin lesion segmentation is remarkably improved.

This application provides a method and apparatus for visualizing dermoscopic image features based on orientation awareness, comprising: processing a dermoscopic image through a backbone network of a segmentation network, wherein the spatial resolution of multiple hierarchical modules is progressively reduced and the number of channels is progressively increased; decoupling the orientation features of the dermoscopic image and hierarchically propagating the orientation prior through orientation-aware base blocks; extracting directional latent priors containing global response information in multiple directions from deep orientation features; fusing orientation features under the guidance of the directional latent priors through a decoder to obtain a segmentation feature map; progressively decoupling and enhancing multi-scale orientation information during feature extraction, and extracting compact directional latent priors from deep features; and using the orientation priors to guide dual attention computation within a local window, enabling the model to achieve a balance between structural consistency and detail accuracy, thereby achieving robust recovery of the continuous boundaries and topological integrity of lesions.

The present invention relates to a multimodal skin disease analysis method based on deep learning, and relates to the field of auxiliary diagnosis technology. The present invention uses a photoacoustic imaging device to scan, and a dermatoscope to photograph the affected area of the skin disease to obtain photoacoustic imaging data and skin images of the affected area; aligns the photoacoustic imaging with the skin image, fills the space according to the skin image, and then combines it with the skin image to obtain multimodal skin data; constructs and pre-trains a skin analysis model based on multimodal skin data; the pre-trained skin analysis model analyzes the collected multimodal skin data to obtain skin disease analysis results. The present application constructs multimodal skin data, provides multivariate data support, and ensures that disease analysis is accurate and reliable. The skin analysis model extracts skin image feature maps and photoacoustic imaging feature maps of different scales to cover the association between features of different sizes and skin diseases of different specifications; uses another modality data to strengthen its own modality to better combine the two modality features; and has strong interpretability.

The invention belongs to the technical field of dermatoscope image analysis, and relates to a pathological space diagram modeling system and method for skin lesion intelligent diagnosis, the system comprises four parallel deployment visual representation learning and topological structure modeling, the modeling comprises a saliency map embedding layer and a plurality of pathological space diagram blocks, the pathological space graph block is sequentially composed of a pathological feature point digger, a layered graph connector and a geometric distribution learner; the method comprises the following steps: constructing a multi-scale saliency block embedding layer to extract initial visual representation, introducing a pathological feature point digger to realize intelligent identification of sparse key pathological points, constructing a hierarchical graph connector to organize a multi-scale topological relation, realizing hierarchical topological reasoning and vector distillation of a geometric distribution learner, and constructing a geometric distribution learner. Defining an attention fusion mechanism and a classification head to realize topological guidance diagnosis; according to the method, the defects in the aspects of structural modeling, calculation distribution, graph representation and the like in the prior art are overcome, and the diagnosis accuracy, robustness and clinical interpretability are remarkably improved.

The invention relates to the technical field of medical instruments, and discloses a rotary dermatoscope magnification adjusting ring which comprises an adjusting ring body, a lens body and a connecting ring, the connecting ring sleeves the outer side of the lens body and is in sliding connection with the lens body, and the adjusting ring body rotatably sleeves the outer side of the connecting ring; a plurality of damping grooves are formed in the inner wall of the adjusting ring body in the circumferential direction at intervals, a plurality of connecting pieces are symmetrically and fixedly connected to the surface of the connecting ring, an arc-shaped spring piece is fixedly connected to the surface of each connecting piece, and two damping columns are fixedly connected to the two sides of each arc-shaped spring piece; the damping column elastically abuts against an inner cavity of the damping groove through the elastic acting force of the arc-shaped spring piece to form a gear damping structure, through cooperation of the damping column and the triangular damping groove and the elastic acting force of the arc-shaped spring piece, clear'click 'sound and the sense of lagging are generated in the adjusting process, a clear gear switching signal is provided for a doctor, and the safety of the doctor is improved. The defect that the adjusting ring lacks positioning sensing in the prior art is overcome.

The application discloses a skin cancer multi-modal case retrieval method and device based on global-local alignment, equipment, medium and product, relates to the field of multi-modal information fusion, and comprises the following steps: constructing a case database containing dermoscope images and diagnosis labels and a composite query; extracting multi-level visual features of the query image by using a Swin Transformer; encoding the query text by using BERT, and interacting and fusing the multi-level visual features and the text features by using a cross-modal Transformer to obtain a query feature of the text-image fusion; respectively calculating global similarity and local similarity of the query feature of the text-image fusion and target image features; weighting and fusing the global and local similarity to obtain a final similarity score, and performing sorting retrieval and label consistency verification on the database based on the score. The application breaks through the limitation of traditional single-modal retrieval, realizes fine-grained semantic alignment, and significantly improves the accuracy of skin cancer case retrieval and the value of clinical decision support.

Examination device for optical medical examinations, in particular dermatoscope, with optics (14) and a lighting device (16), wherein the optics (14) has an optical axis (A) and defines an examination area (U), wherein the lighting device (16) has at least one first light source (30) and at least one second light source (32), wherein the at least one first light source (30) and the at least one second light source (32) are arranged such that they jointly illuminate the area of ​​investigation (U), wherein the at least one first light source (30) is configured to emit white light with a color temperature of 5000K and the at least one second light source (32) is configured to emit light that is bluer than the white light emitted by the at least one first light source (30), wherein the light emitted by the at least one second light source (32) has a wavelength of 400 nm to 550 nm, and wherein the examination device (10) is set up such that that when the lighting device (16) is activated, at least one first light source (30) is always switched on, that at least one second light source (32) can be switched on in addition to at least one first light source (30), that the luminous intensity of the light emitted by the at least one second light source (32) is variable, and that the color temperature of the light emitted by the lighting device (16) can be set within a color temperature range between 5000K and 12000K.

This invention discloses a cross-modal medical image segmentation method based on pathological anchoring. Using pathological priors as semantic anchors, this method integrates cross-scale collaboration and uncertainty perception in a closed-loop prompting refinement process. This achieves interpretable suppression and robust learning of cross-modal domain shifts, forming a closed-loop path from structure to semantics to noise control. Under strong cross-modal zero-sample settings such as multi-source ultrasound cross-domain segmentation and color dermoscopy, stable and consistent improvements are achieved, manifested in more precise boundaries, better calibration, and more robust generalization. This provides technical support for disease image diagnosis.

The invention discloses a radiodermatitis dermatoscope imageomics prediction method and system and an application program, the system comprises a hardware module and a software module, the hardware module comprises a dermatoscope image acquisition device, and the dermatoscope image acquisition device is used for acquiring a high-resolution dermatoscope image of a radiotherapy treatment area of a patient; the software module is integrated in an application program of a mobile terminal and comprises a radiomics feature extraction module used for extracting quantitative features from dermatoscope images; the parameter calculation module is used for calculating radiomics parameters associated with the skin microstructure change; and the risk prediction module is used for constructing an interpretable machine learning risk prediction model and inputting the patient feature data and the radiomics parameters into the risk prediction model to generate a personalized radiodermatitis risk score for the patient. According to the invention, accurate prediction of acute radiodermatitis is realized.

The invention relates to the technical field of medical image processing, and particularly discloses a dermatosis auxiliary diagnosis method and system based on multi-mode optical image fusion, and the method comprises the steps: carrying out the semantic segmentation of an obtained dermatoscope image of a target skin region, and recognizing at least one target feature region; based on the semantic category and position information of the target feature region, screening out at least one associated feature region from an obtained RCM image set of a target skin region; extracting a first feature vector in the target feature region, and extracting a second feature vector in the associated feature region; and fusing the first feature vector and the second feature vector, and performing disease classification on the fused feature vector based on a trained classification model to obtain a skin disease classification result of the target skin area. According to the method, the corresponding associated region can be screened out from the RCM image set according to the semantic segmentation result of the dermatoscope, and the efficiency and reliability of multi-modal data integration are remarkably improved.

The invention discloses a lightweight skin disease lesion area segmentation method and system. The lightweight skin disease lesion area segmentation method comprises the following steps: acquiring a to-be-segmented dermatoscope image; the dermatoscope image to be segmented is input into a trained image segmentation model TinyDenseUNet, and the trained image segmentation model TinyDenseUNet is used for segmenting the dermatoscope image to be segmented; the TinyDenseUNet model is a U-Net type network and is composed of three parts, namely an encoder, a decoder and a jump connection part; wherein the LDCM module and the down-sampling module form an encoder of the image segmentation model, and the up-sampling module and the LDCM module form a decoder of the image segmentation model; and outputting a final segmentation result. According to the method, efficient, rapid and accurate segmentation can be realized under limited computing resources and data set scale, and the method is suitable for clinical diagnosis and medical research.

A diagnostic imaging system for analysing skin tissue image data received from a remote user for evaluating the image data for screening for a skin disease or skin condition, the system comprising: a manipulator arm and slider system of a robot, the manipulator arm moving on the slider along a patient body and comprising a plurality of elements interconnected to each other by a plurality of joints whereby each element is rotatable relative to an adjoining element of the manipulator arm; a non-invasive dermatoscope module comprising one or more dermatoscopes arranged to acquire tissue image data, the dermatoscope module being coupled to one of the elements of the manipulator arm by a coupling arrangement to allow movement of the dermatoscope module relative to said one of the elements of the manipulator arm; and a controller coupled to the manipulator arm and a coupling arrangement to employ the manipulator arm to move the dermatoscope module relative to the subject's anatomy; a server in communication with a distribution network for receiving tissue image data from the dermatoscope module, the tissue image data; a processor for executing a learning machine algorithm, wherein the algorithm is trained using image data sets having known outcomes for a plurality of skin diseases or skin conditions, the processor being operable for receiving image data from the dermatoscope module and processing the image data to produce processed image data and introducing the processed image data into the learning machine to provide an output indication of whether the tissue image data is associated with a skin condition or skin disease.

The invention relates to the technical field of medical apparatus and instruments, and discloses a foldable telescopic portable dermatoscope main body structure which comprises a holding seat, the upper surface of the holding seat is fixedly connected with a dermatoscope body, a pressing block drives an ejector rod to ascend, a telescopic spring is extruded, then a movable block and a mounting seat are driven to move, and the dermatoscope body is fixed to the holding seat. The length of the holding base can be flexibly adjusted according to the holding habit of a user, more comfortable and stable holding experience is provided, the telescopic block can be stored in the holding base when the dermatoscope is not used, the size of the dermatoscope is greatly reduced, the dermatoscope is more convenient to carry, and the dermatoscope is more convenient to use. The dermatoscope can be easily placed in a bag or other narrow spaces, carrying inconvenience and possible damage caused by the too large size are avoided, the sealing shell is connected with the dermatoscope body, the protective pad on the outer surface and the buffer plate on the inner wall form inner and outer double-layer protection, dust and impurities are prevented from being attached, and the definition of the dermatoscope is ensured.

The method of analyzing digital dermoscopy images records, stores and transfers digital dermoscopy images (DDIs) and provides an initial characterization based on clinically accepted dermoscopy criteria. A digital dermoscopy image is received and a determination is made to determine if the digital dermoscopy image meets a quality threshold. If the digital dermoscopy image meets the quality threshold, then a determination is made if the digital dermoscopy image potentially shows a pre-malignant or malignant skin lesion or an atypical melanocytic lesion with uncertain malignant potential. The determination of the potential showing of the pre-malignant or malignant skin lesion or the atypical melanocytic lesion with uncertain malignant potential is performed using an artificial intelligence system or an augmented intelligence system pre-trained with a dataset of diverse dermoscopy images. The results of the determination are visually indicated to the user.

The invention relates to the technical field of medical instruments, and discloses a focal length-adjustable portable dermatoscope device, which comprises a dermatoscope body, the bottom of the dermatoscope body is connected with a focal length adjusting structure through a detachable connecting structure; the focal length adjusting structure comprises an inner ring connected to the bottom of the dermatoscope body through a detachable connecting structure, the surface of the inner ring is rotationally connected with an adjusting ring, an inner cavity of the inner ring is slidably connected with a sliding ring, axial sliding grooves are symmetrically formed in the surface of the inner ring in a penetrating mode, and spiral guide grooves are symmetrically formed in the inner wall of the adjusting ring. A connecting pin is arranged at the intersection of the axial sliding groove and the spiral guide groove in a penetrating mode, one end of the connecting pin is fixedly connected with the surface of the sliding ring, the other end of the connecting pin extends into the spiral guide groove, and through transmission fit of the adjusting ring and the spiral guide groove, rotary motion is converted into axial displacement of the sliding ring; the relative distance between the lens group structure and the dermatoscope body can be flexibly changed, and the focal length can be continuously adjusted.

The invention relates to the technical field of medical images, and particularly discloses a skin cancer artificial intelligence diagnosis system based on medical images, comprising: an image preprocessing module for acquiring and preprocessing a dermatoscope single-mode image; the feature extraction and compensation module is used for performing visual feature extraction on the preprocessed image and performing skin color deviation compensation by adopting a skin color perception attention mechanism; the classification and visualization module is used for performing classification based on the corrected features, generating a focus heat map and calculating a benign and malignant classification probability; the report generation module is used for outputting a structured report containing the result, a skin color sensitive channel attention layer (SACA) and skin color balance loss joint mechanism is embedded in the dermatoscope single-mode network, and the misdiagnosis rate is reduced; under the condition that the system only uses dermatoscope images, the overall accuracy of the HAM10000 data set is improved; and calibrating a curve according to the skin color classification of the current case, the baseline misdiagnosis rate of the corresponding crowd and the skin color specific confidence coefficient predicted by the model.

This invention discloses a dermoscopic hair loss classification method, device, and medium using expert-guided attention and multi-model fusion. The method includes: acquiring a dermoscopic image to be detected and performing standardized preprocessing; inputting the preprocessed image into a pre-constructed hair loss subtype auxiliary classification model, wherein the hair loss subtype auxiliary classification model outputs the classification result and its confidence score. This invention introduces an expert-guided attention optimization mechanism and confidence score calibration under image-level weak supervision to improve the accuracy of hair loss subtype model classification.

A portable, foldable and handheld multipurpose medical instrument for use in a telemedicine application including a first housing and a second housing placed over the first housing. The second housing includes a disposable examining tip having an image capturing unit, a temperature sensor and a light source. The medical instrument includes a plurality of buttons for operating the image capturing unit, the temperature sensor and the light source. The medical instrument includes a plurality of display screens for displaying the images, or recorded video and displaying the temperature readings during the examination of ears, eyes, nasal cavity and mouth and detection of body's temperature. In one implementation, the medical instrument transmits the data remotely to a server or a user device.

AI-POWERED DERMATOSCOPE FOR AUTOMATED SKIN LESION DETECTION AND CLASSIFICATION