Abstract: The present disclosure relates to a technology field of artificial intelligence and provides a method for selecting image samples and related equipment. The method trains an instance segmentation model with first image samples and trains a score prediction model with third image samples. An information quantum score of second image samples is calculated through the score prediction model and feature vectors extracted. The second image samples are clustered according to the feature vectors of the second image samples and sample clusters of the second image samples are obtained. Target image samples are selected from the second image samples according to the information quantum score of the second image samples and the sample clusters. Target image samples from the image samples are selected for labelling, improving an accuracy of sample selection.

Abstract: The present disclosure provides a method, device, computer apparatus, and storage medium for training recognition model and recognizing fundus features. The method includes: obtaining a color fundus image sample associated with a label value, inputting the color fundus image sample into a preset recognition model containing initial parameters; extracting a red channel image; inputting the red channel image into the first convolutional neural network to obtain a first recognition result and a feature image of the red channel image; combining the color fundus image sample with the feature image to generate a combined image, and inputting the combined image into the second convolutional neural network to obtain a second recognition result; obtaining a total loss value through a loss function, and when the total loss value is less than or equal to a preset loss threshold, ending the training of the preset recognition model.

Abstract: A Pancreatic Ductal Adenocarcinoma (PDAC) image segmentation method, an electronic device, and a storage medium are provided. In the PDAC image segmentation method, a first model is trained using a first data set; and a second model is trained using a second data set. A third data set is obtained by annotating a to-be-annotated data set using the first model and the second model and a third model is trained using a fourth data set. A training set is obtained by modifying the first data set and the third data set using the third model and a segmentation model is obtained by training an nnUNet using the training set. A to-be-segmented PDAC image is input into the segmentation model, and a segmentation result is obtained. By utilizing the PDAC image segmentation method, a more accurate PDAC image segmentation is achieved.

Abstract: A method for detecting and locating a lesion in a medical image is provided. A target medical image of a lesion is obtained and input into a deep learning model to obtain a target sequence. A first feature map output from the last convolution layer in the deep learning model is extracted. A weight value of each network unit corresponding to each preset lesion type in a fully connected layer is extracted. For each preset lesion type, a fusion feature map is calculated according to the first feature map and the corresponding weight value and resampled to the size of the target medical image to generate a generic activation map. The maximum connected area in each generic activation map is determined, and a mark border surrounding the maximum connected area is created. A mark border corresponding to each preset lesion type is added to the target medical image.

Abstract: A method for cutting or extracting video clips from a video, including the audio content relevant to points of particular interest, and combining the same for instruction or training on particular points; a computing device applying the method extracts text information from the spoken audio content of a video to be cut and obtains multiple paragraph segmentation positions as candidates for inclusion in a desired and finished presentation by analyzing the information from text representing the spoken audio content, the analysis being carried out by a semantic segmentation model. Candidate items of text are obtained by isolating pieces of text according to the paragraph segmentation positions. Time stamps of the candidate text segments are acquired, and candidate video clips are obtained by cutting the video according to the acquired time stamps.

Abstract: Provided is an unbalanced sample data preprocessing method, which includes: a data acquisition request is received and initial data is acquired according to the data acquisition request, and the initial data is classified according to a preset classification rule to obtain first-class sample sets and second-class sample sets; characteristics of K first sample points extracted are analyzed to obtain a new data characteristic of the first-class sample sets; a new data label of the first-class sample sets is generated according to a first label corresponding to the first-class sample sets; a ratio between the number of first-class sample sets and the number of second-class sample sets is calculated; and new data of the first-class sample sets is generated according to the new data characteristic and the new data label, and the amount of new data is adjusted according to the ratio to increase the number of first-class sample sets.

Abstract: A system and a method for image-based crop identification are disclosed. The image-based crop identification system includes a database, a communication module and a model library. The database stores sample aerial data and annotated aerial data. The communication module is coupled to the database, and is configured to provide the sample aerial data to a user and receive the annotated aerial data from the user. The model library is coupled to the database, and is configured to obtain the annotated aerial data, train a crop classification model based on the annotated aerial data, and provide the trained crop classification model for subsequent crop identification. The annotated aerial data include determination of the type of the crop appearing in the sample aerial data.

Abstract: The present disclosure provides a method of positioning vertebra in a CT image, an apparatus, a computer device, and a computer readable storage medium. The method includes: pre-processing vertebra CT image data; inputting the pre-processed vertebra CT image data into a pre-trained neural network to obtain regression results of heat maps of key points corresponding to the pre-processed vertebra CT image data; regressing of 3D heat maps corresponding to the positions of the key points of the vertebra mass center based on the regression results of the heat maps of the key points and the pre-processed vertebra CT image data; serving 3D heat maps corresponding to the positions of the key points of the vertebra mass center as labels, and networked regressing 3D heat map information to position the vertebra. Effects caused by scanning machine difference and scanning noise are avoided, and the vertebra with complex forms is accurately positioned.

Abstract: A target cell marking method, including: determining an original image format of the original scanned image, and converting the original scanned image into a first image in a preset image format; segmenting the first image into a plurality of image blocks and recording arrangement positions of the image blocks in the first image; respectively inputting the image blocks into a preset deep learning detection model to obtain first position information of target cells in the image blocks; determining second position information of the target cells in the first image according to the first position information and the corresponding arrangement positions; integrating the image blocks according to the arrangement positions to obtain a second image, and marking the target cells in the second image; and converting the second image marked by the target cells into a third image in the original image format, and displaying the third image.

Abstract: The application belongs to the field of big data, and particularly relates to an official document processing method, device, computer equipment and storage medium. The method includes the following steps of: performing format analysis on the to-be-reviewed official document, then acquiring the to-be-reviewed official document of standard file type, and identifying all file components and contents in the to-be-reviewed official document of standard file type; performing text format detection, text content detection and frame layout detection synchronously by a preset text processing model, obtaining a format detection result, a content detection result and a layout detection result; generating a detected error content according to the format detection result, content detection result and layout detection result, calling out a standard writing rule corresponding to the detected error content, marking the detected error content and the standard writing rule in the to-be-reviewed official document.

Abstract: A method for pancreatic mass diagnosis and patient management includes: receiving CT images of a pancreas of a patient, the pancreas of the patient including a mass; performing a segmentation process on the CT images of the pancreas and the mass to obtain a segmentation mask of the pancreas and the mass of the patient; performing a mask-to-mesh process on the segmentation mask of the pancreas and the mass of the patient to obtain a mesh model of the pancreas and the mass of the patient; performing a classification process on the mesh model of the pancreas and the mass of the patient to identify a type and a grade of a segmented pancreatic mass; and outputting updated CT images of the pancreas of the patient, the updated CT images including the segmented pancreatic mass highlighted thereon and the type and the grade of the segmented pancreatic mass annotated thereon.

Abstract: The present disclosure provides a computer-implemented method, a device, and a storage medium. The method includes inputting an image into an attention-enhanced high-resolution network (AHRNet) to extract feature maps for generating a first feature map; generating a first probability map which is concatenated with the first feature map to form a concatenated first feature map, and updating the AHRNet using the first segmentation loss; generating a second feature map, and scaling the second feature map to form a third feature map; generating a second probability map which is concatenated with the third feature map to form a concatenated third feature map, and updating the AHRNet using the second segmentation loss; generating a fourth feature map, and scaling the fourth feature map to form a fifth feature map; updating the AHRNet using the third segmentation loss and the regional level set loss; and outputting the third probability map.

Abstract: A finger vein comparison method, a computer equipment, and a storage medium are provided. The finger vein comparison method includes: two finger vein images to be compared are obtained (S10); image channel fusion is performed on the two finger vein images to be compared to obtain a two-channel target finger vein image to be compared (S20); the target finger vein image to be compared is input into a feature extractor, and a feature vector of the target finger vein image to be compared is extracted by the feature extractor (S30); the feature vector of the target finger vein image to be compared is input into a dichotomy classifier to obtain a dichotomy result (S40); and it is determined according to the dichotomy result whether the two finger vein images to be compared come from the same finger (S50).

Abstract: A system and method for multimodal video segmentation in a multi-speaker scenario are provided. A transcript of a video with a plurality of speakers is segmented into a plurality of sentences. Speaker change information is detected between each two adjacent sentences of the plurality of sentences based on at least one of audio content or visual content of the video. The video is segmented into a plurality of video clips based on the transcript of the video and the speaker change information.

Abstract: The application discloses a main-machine interaction method and system, a computer device, and a storage medium. The method includes: an interaction end collects user information including biological sample information and preprocesses and filters the user information, and sends the preprocessed information to a central server; the central server assigns a biological recognition task and distributes the biological recognition task to a computing server; the computing server extracts biological characteristics from the biological sample information according to the biological recognition task, and returns obtained extraction results to the central server; the central server combines the extraction results to get a processing result; the processing result is returned to the interaction end; the interaction end responds to the processing result to complete a man-machine interaction with the user.

Abstract: Knowledge distillation method for fracture detection includes obtaining medical images including region-level labeled images, image-level diagnostic positive images, and image-level diagnostic negative images, in chest X-rays; performing a supervised pre-training process on the region-level labeled images and the image-level diagnostic negative images to train a neural network to generate pre-trained weights; and performing a semi-supervised training process on the image-level diagnostic positive images using the pre-trained weights. A teacher model is employed to produce pseudo ground-truths (GTs) on the image-level diagnostic positive images for supervising training of a student model, and the pseudo GTs are processed by an adaptive asymmetric label sharpening (AALS) operator to produce sharpened pseudo GTs to provide positive detection responses on the image-level diagnostic positive images.

Abstract: The present disclosure provides a computer-implemented method, a device, and a computer program product using a user-guided domain adaptation (UGDA) architecture. The method includes training a combined model using a source image dataset by minimizing a supervised loss of the combined model to obtain first sharing weights for a first FCN and second sharing weights for a second FCN; training a discriminator by inputting extreme-point/mask prediction pairs for each of the source image dataset and a target image dataset and by minimizing a discriminator loss to obtain discriminator weights; and finetuning the combined model by predicting extreme-point/mask prediction pairs for the target image dataset to fool the discriminator by matching a distribution of the extreme-point/mask prediction pairs for the target image dataset with a distribution of the extreme-point/mask prediction pairs for the source image dataset.

Abstract: A method for accelerated detection of objects in videos, a server, and a non-transitory computer readable storage medium are provided. The method realizes the detection of a target object in a video by dividing all frame images in video images into preset groups of frame images, each group of frame images including a keyframe image and a non-keyframe image, using a detection box of a target in the keyframe image to generate a preselection box in the non-keyframe image, and detecting the location of the target in the preselection box.

Abstract: The present disclosure provides a system, a method, an electronic device, and a storage medium for identifying risk event based on social information.

Abstract: A method for tracking a target includes: acquiring original position information of an original target point selected by a user contained in a locating request if the locating request for tracking a target is received; carrying out target prediction on a current frame image according to a preset target prediction model to obtain a target prediction result; calculating an Euclidean distance between each of the targets to be tracked and the original target point according to the target position information and original coordinates of each of the target regions to obtain N distances; selecting a distance with the smallest numerical value from the N distances as a target distance, acquiring target position information corresponding to the target distance, and determining a target to be tracked in a target region corresponding to the obtained target position information as a tracked target corresponding to an original target point.