Abstract: During operation, a system may obtain first and second magnetic resonance (MR) measurements associated with a biological lifeform, where the first and second MR measurements were acquired while the biological lifeform engaged in free breathing and/or without prospective gating based on a cardiac rhythm of the biological lifeform, and the first and second MR measurements were acquired at different times. Then, the system may dynamically determine first and second instances of one or more anatomical structures associated with the biological lifeform based at least in part on the first and second MR measurements, and a segmentation technique. Next, the system may perform a quantitative comparison of the first instance of the one or more anatomical structures and the second instance of the one or more anatomical structures, where the quantitative comparison has an uncertainty of less than a predefined value.

Abstract: Methods include processing image data through a plurality of network stages of a progressively holistically nested convolutional neural network, wherein the processing the image data includes producing a side output from a network stage m, of the network stages, where m>1, based on a progressive combination of an activation output from the network stage m and an activation output from a preceding stage m?1. Image segmentations are produced. Systems include a 3D imaging system operable to obtain 3D imaging data for a patient including a target anatomical body, and a computing system comprising a processor, memory, and software, the computing system operable to process the 3D imaging data through a plurality of progressively holistically nested convolutional neural network stages of a convolutional neural network.

Abstract: The present disclosure provides a clinical target volume delineation method and an electronic device. The method includes: receiving a radiotherapy computed tomography (RTCT) image; and obtaining a plurality of binary images by delineating a gross tumor volume (GTV), lymph nodes (LNs), and organs at risk (OARs) in the RTCT image. A SDMs for each of the binary images is calculated. The RTCT image and all the SDM are finally input into a clinical target volume (CTV) delineation model; and a CTV in the RTCT image is delineated by the CTV delineation model. An automatic delineation of the CTV of esophageal cancer are realized, a delineation efficiency is high and a delineation effect is good.

Abstract: A medical image classification method such as CT (or CAT) scans includes receiving the CT scan or medical image, inputting the medical image into an image classification model, which provides a cross entropy (CE) loss function and an aggregated cross entropy (ACE) loss function. According to the ACE loss function, image samples with generic label are used as input data during model training. The medical image can be classified by using the image classification model, and a classification of the medical image is thereby obtained. The present disclosure can classify indeterminate or general medical images and even unlabeled images and thus realize supervision of medical data. A device for applying the method is also provided.

Abstract: A fracture detection method executed by an electronic device is provided. The fracture detection method includes obtaining a to-be-detected image; using a Fully Convolutional Networks (FCN) model to process the to-be-detected image to obtain a fracture probability map of the to-be-detected image; performing a maximum pooling process on the fracture probability map to obtain a first fracture probability; extracting Regions of Interests (ROIs) of the to-be-detected image based on the FCN model; inputting the ROIs into a classification model to obtain a second fracture probability; calculating a product of the first fracture probability and the second fracture probability as a probability of a fracture phenomenon in the to-be-detected image. The present disclosure combines the FCN model and the ROIs to realize an automatic fracture detection, and the accuracy is higher. A device employing the method is also disclosed.

Abstract: In a GTV segmentation method, a PET-CT image pair and an RTCT image of a human body are obtained. A PET image in the PET-CT image pair is aligned to the RTCT image to obtain an aligned PET image. A first PSNN performs a first GTV segmentation on the RTCT image to obtain a first segmentation image. The RTCT image and the aligned PET image are concatenated into a first concatenated image. A second PSNN performs a second GTV segmentation on the first concatenated image to obtain a second segmentation image. The RTCT image, the first segmentation image, and the second segmentation image are concatenated into a second concatenated image. A third PSNN performs a third GTV segmentation on the second concatenated image to obtain an object segmentation image.

Abstract: The present disclosure provides a clinical target volume delineation method and an electronic device. The method includes: receiving a radiotherapy computed tomography (RTCT) image; and obtaining a plurality of binary images by delineating a gross tumor volume (GTV), lymph nodes (LNs), and organs at risk (OARs) in the RTCT image. A SDMs for each of the binary images is calculated. The RTCT image and all the SDM are finally input into a clinical target volume (CTV) delineation model; and a CTV in the RTCT image is delineated by the CTV delineation model. An automatic delineation of the CTV of esophageal cancer are realized, a delineation efficiency is high and a delineation effect is good.

Abstract: A fracture detection method executed by an electronic device is provided. The fracture detection method includes obtaining a to-be-detected image; using a Fully Convolutional Networks (FCN) model to process the to-be-detected image to obtain a fracture probability map of the to-be-detected image; performing a maximum pooling process on the fracture probability map to obtain a first fracture probability; extracting Regions of Interests (ROIs) of the to-be-detected image based on the FCN model; inputting the ROIs into a classification model to obtain a second fracture probability; calculating a product of the first fracture probability and the second fracture probability as a probability of a fracture phenomenon in the to-be-detected image. The present disclosure combines the FCN model and the ROIs to realize an automatic fracture detection, and the accuracy is higher. A device employing the method is also disclosed.

Abstract: A medical image classification method such as CT (or CAT) scans includes receiving the CT scan or medical image, inputting the medical image into an image classification model, which provides a cross entropy (CE) loss function and an aggregated cross entropy (ACE) loss function. According to the ACE loss function, image samples with generic label are used as input data during model training. The medical image can be classified by using the image classification model, and a classification of the medical image is thereby obtained. The present disclosure can classify indeterminate or general medical images and even unlabeled images and thus realize supervision of medical data. A device for applying the method is also provided.

Abstract: In a GTV segmentation method, a PET-CT image pair and an RTCT image of a human body are obtained. A PET image in the PET-CT image pair is aligned to the RTCT image to obtain an aligned PET image. A first PSNN performs a first GTV segmentation on the RTCT image to obtain a first segmentation image. The RTCT image and the aligned PET image are concatenated into a first concatenated image. A second PSNN performs a second GTV segmentation on the first concatenated image to obtain a second segmentation image. The RTCT image, the first segmentation image, and the second segmentation image are concatenated into a second concatenated image. A third PSNN performs a third GTV segmentation on the second concatenated image to obtain an object segmentation image.

Abstract: Methods include processing image data through a plurality of network stages of a progressively holistically nested convolutional neural network, wherein the processing the image data includes producing a side output from a network stage m, of the network stages, where m>1, based on a progressive combination of an activation output from the network stage m and an activation output from a preceding stage m?1. Image segmentations are produced. Systems include a 3D imaging system operable to obtain 3D imaging data for a patient including a target anatomical body, and a computing system comprising a processor, memory, and software, the computing system operable to process the 3D imaging data through a plurality of progressively holistically nested convolutional neural network stages of a convolutional neural network.