Abstract: The present disclosure provides an endoscopic image processing method and system, and a computer device. The method can include acquiring a current endoscopic image of a to-be-examined user, and predicting the current endoscopic image by using a deep convolutional network based on a training parameter. The training parameter can be determined according to at least one first endoscopic image and at least one second endoscopic image transformed from the at least one first endoscopic image, where the at least one endoscopic image corresponds to a human body part. The method can further include determining an organ category corresponding to the current endoscopic image. The method provided in the present disclosure can make a prediction process more intelligent and more robust, thereby improving resource utilization of a processing apparatus.

Abstract: This application relates to an endoscopic image display method, apparatus, computer device, and storage medium, and relates to the field of machine learning technologies. The method acquiring an endoscopic image; locating a target region image in the endoscopic image, the target region image being a partial image comprising a target region; inputting the target region image into a coding network to obtain a semantic feature of the target region image, the coding network being a part of an image classification network, and the image classification network being a machine learning network obtained through training with first training images; matching the semantic feature of the target region image against semantic features of image samples to obtain a matching result, the matching result indicating a target image sample that matches the target region image; and displaying the endoscopic image and the matching result in an endoscopic image display interface.

Abstract: A medical image processing method includes: determining a target mask of a target object in a medical image and a reference mask of a reference object in the medical image, the target mask indicating a position and a boundary of the target object, and the reference mask indicating a position and a boundary of the reference object; determining a feature size of the target object based on the target mask; determining a feature size of the reference object based on the reference mask; and determining a target size of the target object based on the feature size of the reference object, a preset mapping relationship between the feature size of the reference object and a reference size, and the feature size of the target object.

Abstract: A medical endoscope image recognition method is provided. In the method, endoscope images are received from a medical endoscope. The endoscope images are filtered with a neural network, to obtain target endoscope images. Organ information corresponding to the target endoscope images is recognized via the neural network. An imaging type of the target endoscope images is identified according to the corresponding organ information with a classification network. A lesion region in the target endoscope images is localized according to an organ part indicated by the organ information. A lesion category of the lesion region in an image capture mode of the medical endoscope corresponding to the imaging type is identified.

Abstract: This application relates to an image recognition model training method, an image recognition method, apparatus, and system. The method includes: obtaining a to-be-recognized image; extracting image feature information of the to-be-recognized image; and obtaining a lesion category recognition result of the to-be-recognized image by using the image feature information of the to-be-recognized image as an input parameter of a preset image recognition model, the image recognition model being trained by using a training image sample set comprising at least one strong-label training image sample, to determine the lesion category recognition result; and the strong-label training image sample representing an image sample having strong-label information, and the strong-label information comprising at least annotation information of a lesion category and a lesion position in the strong-label training image sample.

Abstract: The present disclosure provides an endoscopic image processing method and system, and a computer device. The method can include acquiring a current endoscopic image of a to-be-examined user, and predicting the current endoscopic image by using a deep convolutional network based on a training parameter. The training parameter can be determined according to at least one first endoscopic image and at least one second endoscopic image transformed from the at least one first endoscopic image, where the at least one endoscopic image corresponds to a human body part. The method can further include determining an organ category corresponding to the current endoscopic image. The method provided in the present disclosure can make a prediction process more intelligent and more robust, thereby improving resource utilization of a processing apparatus.

Abstract: Embodiments of this application include an image processing method and apparatus, a non-transitory computer-readable storage medium, and an electronic device. In the image processing method a to-be-predicted medical image is input into a multi-task deep convolutional neural network model. The multi-task deep convolutional neural network model includes an image input layer, a shared layer, and n parallel task output layers. One or more lesion property prediction results of the to-be-predicted medical image is output through one or more of the n task output layers. The multi-task deep convolutional neural network model is trained with n types of medical image training sets, n being a positive integer that is greater than or equal to 2.

Abstract: An endoscopic image processing method is provided. The method can include acquiring a current endoscopic image of a to-be-examined user, and predicting the current endoscopic image by using a deep convolutional network based on a training parameter. The training parameter can be determined according to at least one first endoscopic image and at least one second endoscopic image transformed from the at least one first endoscopic image, where the at least one endoscopic image corresponds to a human body part. The method can further include determining an organ category corresponding to the current endoscopic image. The method can make a prediction process more intelligent and more robust, thereby improving resource utilization of a processing apparatus.

Abstract: A colon polyp image processing method is provided. A value of a blood vessel color feature in an endoscopic image is classified by using an image classification model trained using a neural network algorithm to determine that the endoscopic image is a white light type picture or an endoscope narrow band imaging (NBI) type picture. A polyp in the endoscopic image is detected by using a polyp positioning model based on the determination that the endoscopic image is the white light type picture or the NBI type picture. A polyp type classification detection is performed on the detected polyp in the endoscopic image by using a polyp property identification model, and outputting an identification result.

Abstract: The present disclosure describes a method, an apparatus, and storage medium for recognizing medical image. The method includes obtaining, by a device, a medical image. The device includes a memory storing instructions and a processor in communication with the memory. The method further includes determining, by the device, the medical image through a first recognition model to generate a lesion recognition result used for indicating whether the medical image comprises a lesion; and in response to the lesion recognition result indicating that the medical image comprises a lesion, recognizing, by the device, the medical image through a second recognition model to generate a lesion degree recognition result of the medical image used for indicating a degree of the lesion. Manual analysis and customization of a feature extraction solution are not required, so that the efficiency and accuracy of medical image recognition are improved.

Abstract: A colon polyp image processing method is provided. A value of a blood vessel color feature in an endoscopic image is classified by using an image classification model trained using a neural network algorithm to determine that the endoscopic image is a white light type picture or an endoscope narrow band imaging (NBI) type picture. A polyp in the endoscopic image is detected by using a polyp positioning model based on the determination that the endoscopic image is the white light type picture or the NBI type picture. A polyp type classification detection is performed on the detected polyp in the endoscopic image by using a polyp property identification model, and outputting an identification result.

Abstract: The present disclosure describes a method, an apparatus, and storage medium for recognizing medical image. The method includes obtaining, by a device, a medical image. The device includes a memory storing instructions and a processor in communication with the memory. The method further includes determining, by the device, the medical image through a first recognition model to generate a lesion recognition result used for indicating whether the medical image comprises a lesion; and in response to the lesion recognition result indicating that the medical image comprises a lesion, recognizing, by the device, the medical image through a second recognition model to generate a lesion degree recognition result of the medical image used for indicating a degree of the lesion. Manual analysis and customization of a feature extraction solution are not required, so that the efficiency and accuracy of medical image recognition are improved.

Abstract: A colon polyp image processing method and apparatus and a system are disclosed in the embodiments of this application to detect a position of a polyp in real time and determine a property of the polyp, and thereby improve the processing efficiency of a polyp image. Embodiment of this application provide a colon polyp image processing method that can include detecting a position of a polyp in a to-be-processed endoscopic image by using a polyp positioning model, and positioning a polyp image block in the endoscopic image. The polyp image block can include a position region of the polyp in the endoscopic image. The method can further include performing a polyp type classification type on the polyp image block by using a polyp property identification model, and outputting an identification result.

Abstract: The present disclosure describes a method, an apparatus, and storage medium for recognizing medical image. The method includes obtaining, by a device, a medical image. The device includes a memory storing instructions and a processor in communication with the memory. The method further includes determining, by the device, the medical image through a first recognition model to generate a lesion recognition result used for indicating whether the medical image comprises a lesion; and in response to the lesion recognition result indicating that the medical image comprises a lesion, recognizing, by the device, the medical image through a second recognition model to generate a lesion degree recognition result of the medical image used for indicating a degree of the lesion. Manual analysis and customization of a feature extraction solution are not required, so that the efficiency and accuracy of medical image recognition are improved.

Abstract: An object detection model training method includes: inputting an unannotated first sample image into an initial detection model of a current round, and outputting a first prediction result for a target object, transforming the first sample image and a first prediction position region within the first prediction result to obtain a second sample image and a prediction transformation result in the second sample image; inputting the second sample image into the initial detection model, and outputting a second prediction result for the target object; obtaining a loss value of unsupervised learning according to a difference between the second prediction result and the prediction transformation result; and adjusting model parameters of the initial detection model according to the loss value and returning to the operation of inputting a first sample image into an initial detection model of a current round to perform iterative training, to obtain an object detection model.

Abstract: This application relates to an endoscopic image display method, apparatus, computer device, and storage medium, and relates to the field of machine learning technologies. The method acquiring an endoscopic image; locating a target region image in the endoscopic image, the target region image being a partial image comprising a target region; inputting the target region image into a coding network to obtain a semantic feature of the target region image, the coding network being a part of an image classification network, and the image classification network being a machine learning network obtained through training with first training images; matching the semantic feature of the target region image against semantic features of image samples to obtain a matching result, the matching result indicating a target image sample that matches the target region image; and displaying the endoscopic image and the matching result in an endoscopic image display interface.

Abstract: A medical image processing method includes: determining a target mask of a target object in a medical image and a reference mask of a reference object in the medical image, the target mask indicating a position and a boundary of the target object, and the reference mask indicating a position and a boundary of the reference object; determining a feature size of the target object based on the target mask; determining a feature size of the reference object based on the reference mask; and determining a target size of the target object based on the feature size of the reference object, a preset mapping relationship between the feature size of the reference object and a reference size, and the feature size of the target object.

Abstract: A medical endoscope image recognition method is provided. In the method, endoscope images are received from a medical endoscope. The endoscope images are filtered with a neural network, to obtain target endoscope images. Organ information corresponding to the target endoscope images is recognized via the neural network. An imaging type of the target endoscope images is identified according to the corresponding organ information with a classification network. A lesion region in the target endoscope images is localized according to an organ part indicated by the organ information. A lesion category of the lesion region in an image capture mode of the medical endoscope corresponding to the imaging type is identified.

Abstract: This application relates to an image recognition model training method, an image recognition method, apparatus, and system. The method includes: obtaining a to-be-recognized image; extracting image feature information of the to-be-recognized image; and obtaining a lesion category recognition result of the to-be-recognized image by using the image feature information of the to-be-recognized image as an input parameter of a preset image recognition model, the image recognition model being trained by using a training image sample set comprising at least one strong-label training image sample, to determine the lesion category recognition result; and the strong-label training image sample representing an image sample having strong-label information, and the strong-label information comprising at least annotation information of a lesion category and a lesion position in the strong-label training image sample.

Abstract: Embodiments of this application include an image processing method and apparatus, a non-transitory computer-readable storage medium, and an electronic device. In the image processing method a to-be-predicted medical image is input into a multi-task deep convolutional neural network model. The multi-task deep convolutional neural network model includes an image input layer, a shared layer, and n parallel task output layers. One or more lesion property prediction results of the to-be-predicted medical image is output through one or more of the n task output layers. The multi-task deep convolutional neural network model is trained with n types of medical image training sets, n being a positive integer that is greater than or equal to 2.