Abstract: A method, an apparatus, and a non-transitory computer readable medium for training an image processing model are provided. The method includes: acquiring a sample image comprising a target object to determine an object segmentation image of the target object in the sample image; constructing an object coordinate map corresponding to the object segmentation image according to the object segmentation image; and training an image processing model comprising a self-attention mechanism layer according to the sample image, the object segmentation image, and the object coordinate map.

Abstract: An image processing method is provided. The method includes obtaining a to-be-processed image comprising a target object, and inputting the to-be-processed image to a convolutional layer of an image processing model, to obtain an initial feature map of the to-be-processed image, wherein the image processing model comprises an encoder and a decoder; inputting the initial feature map to a self-attention mechanism layer of the encoder, and obtaining a target feature map corresponding to the initial feature map according to position information of each feature in the initial feature map and a position relationship between the each feature and other features; and inputting the target feature map to the decoder for processing, to obtain an object segmentation map and an object label of the target object in the to-be-processed image.

Abstract: Volumetric quantification can be performed for various parameters of an object represented in volumetric data. Multiple views of the object can be generated, and those views provided to a set of neural networks that can generate inferences in parallel. The inferences from the different networks can be used to generate pseudo-labels for the data, for comparison purposes, which enables a co-training loss to be determined for the unlabeled data. The co-training loss can then be used to update the relevant network parameters for the overall data analysis network. If supervised data is also available then the network parameters can further be updated using the supervised loss.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: A method, an apparatus, and a non-transitory computer readable medium for training an image processing model are provided. The method includes: acquiring a sample image comprising a target object to determine an object segmentation image of the target object in the sample image; constructing an object coordinate map corresponding to the object segmentation image according to the object segmentation image; and training an image processing model comprising a self-attention mechanism layer according to the sample image, the object segmentation image, and the object coordinate map.

Abstract: An image processing method is provided.

Abstract: Image detection methods, apparatus, and storage medium are provided. The method includes: acquiring a detection image obtained through computed tomography; extracting a target body part image corresponding to a target body part from the detection image; performing first image classification and segmentation on the target body part image through a first image detection model, to determine whether a first target lesion type and a lesion region corresponding to the first target lesion type exist in the target body part image; and performing second image classification and segmentation on the target body part image through a second image detection model, to determine whether a second target lesion type and a lesion region corresponding to the second target lesion type exist in the target body part image, wherein the second target lesion type is a subcategory of the first target lesion type.

Abstract: Volumetric quantification can be performed for various parameters of an object represented in volumetric data. Multiple views of the object can be generated, and those views provided to a set of neural networks that can generate inferences in parallel. The inferences from the different networks can be used to generate pseudo-labels for the data, for comparison purposes, which enables a co-training loss to be determined for the unlabeled data. The co-training loss can then be used to update the relevant network parameters for the overall data analysis network. If supervised data is also available then the network parameters can further be updated using the supervised loss.

Abstract: Apparatuses, systems, and techniques to improve federated learning for neural networks. In at least one embodiment, a federated server dynamically selects neural network weights according to one or more learnable aggregation weights indicating a contribution from each of one or more edge devices or clients during federated training according to various characteristics of each edge device or client model and training data.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: Comparison logic compares boundaries of features of or more images based, at least in part, on identifying boundaries and indication logic coupled to the comparison logic to indicate whether the boundaries differ by at least a first threshold. The boundaries might comprise a first label mask representing boundaries of objects in an image that are boundaries in a segmentation determined from a segmentation process and a second label mask from a shape evaluation process applied to the first label mask. The indication logic might be configured to compare the first label mask and the second label mask to determine a quality of the segmentation. A neural network might perform the segmentation. Shape evaluation using the first label mask as an input and the second label mask as an output might be performed by a variational autoencoder. A graphical processing unit (GPU) might be used for the segmentation and/or the autoencoder.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: Comparison logic compares boundaries of features of or more images based, at least in part, on identifying boundaries and indication logic coupled to the comparison logic to indicate whether the boundaries differ by at least a first threshold. The boundaries might comprise a first label mask representing boundaries of objects in an image that are boundaries in a segmentation determined from a segmentation process and a second label mask from a shape evaluation process applied to the first label mask. The indication logic might be configured to compare the first label mask and the second label mask to determine a quality of the segmentation. A neural network might perform the segmentation. Shape evaluation using the first label mask as an input and the second label mask as an output might be performed by a variational autoencoder. A graphical processing unit (GPU) might be used for the segmentation and/or the autoencoder.