A CPU acquires a radiographic image obtained by imaging an imaging region where a patient is present, with a radioscopy apparatus using radiation emitted from a radiation source and applied to an irradiation field adjusted by a collimator. The CPU specifies a structure image that is included in the radiographic image and represents a structure of a specific shape having transmittance of radiation lower than the patient, based on the specific shape. The CPU executes image processing corresponding to the structure image on a patient image region imaged by a radioscopy apparatus in a case where an irradiation field excluding a position of the structure is set as the irradiation field, in a region in the radiographic image.

A console includes a CPU as at least one processor. The CPU acquires a radiographic image obtained by imaging an imaging region where a patient is present, with a radioscopy apparatus. The CPU specifies a structure image that is included in the radiographic image and represents a structure of a specific shape having transmittance of radiation lower than the patient, based on the specific shape. The CPU executes image processing corresponding to the structure image to the radiographic image.

This invention presents a system that can be used for object identification and classification by training multiple neural networks on large quantities of images efficiently, The first in a series of convolutional neural networks is trained on a low resolution version of the image; in each successive stage of the series a model is trained on a smaller and more specific subregion of the original image. GradCAM is used to identify an area of focus in the image which later models will classify. The models are strung together into a single mega-classifier. The training time of this approach is significantly less, as smaller and lower resolution images are easier to manipulate and the implementation of GradCAM presented is much faster than standard library implementations The effectiveness of the proposed approach is demonstrated by applying it on the task of Intracranial Hemorrhage detection and classification.

Intracranial hemorrhage is a critical brain injury characterized by bleeding and swelling in the tissue surrounding a broken artery. Hemorrhages often cause strokes which are the 5th leading cause of death in the U.S. Current diagnostic procedures need a highly trained radiologist with specialized training in identifying brain hemorrhage. As a result, diagnosis is expensive, and in remote areas where radiologists are hard to find, diagnosis is difficult and often inaccurate. My research develops a computer aid to radiologists that can screen brain scans to cut costs and accelerate diagnosis. Through image windowing, data augmentation, and Convolutional Neural Networks (CNNs), the system I present achieves high accuracies in detecting hemorrhage and 5-way subtype classification. The system consists of a two-model ensemble; one model is trained to detect hemorrhage and potential regions of hemorrhage in the CT scans, and the second model analyzes hemorrhagic regions found by the first model more closely. The two-model ensemble reduces the error rate by 17% relative to the first model alone, increasing the overall detection accuracy to 97.0%. It also applies Gradient Class Activation Maps (GradCAM), which provide a coarse mapping of the regions of the image that were most influential in the model's predictions. The activation maps provide a strong visual aid for explaining and justifying the model's outputs and can be used by radiologists to assist them in identifying the areas of focus in an image.

According to one embodiment, a medical image processing apparatus includes processing circuitry. The processing circuitry specifies, before position alignment between a first X-ray image and a second X-ray image which is acquired with a device inserted, a device area candidate in the second X-ray image as a candidate of an area where the device appears. The processing circuitry performs the position alignment using first processing of removing the specified device area candidate or second processing of reducing a contribution of the specified device area candidate.

An image processor applies computation processing to a plurality of CT images formed by irradiation of radiation of a plurality of energy levels to acquire monochromatic CT images. The image processor acquires a first energy level CT image formed by irradiation of first energy level radiation and a second energy level CT image formed by irradiation of second energy level radiation, applies a plurality of weighted computations to the first and second energy level CT images to compute a plurality of monochromatic CT images as a result of the weighted computations, segments a surrounding region of a highly-absorbent material circumferentially into a plurality of regions of interest having a predetermined area and calculates a standard deviation of the surrounding region by using a mean value of image data of each region of interest, for each monochromatic CT image, and selects a monochromatic CT image with a small standard deviation.

A deep-learning-based method for metal artifact reduction in CT images includes providing a dataset and a cGAN. The dataset includes CT image pairs, randomly partitioned into a training set, a validation set, and a testing set. Each Pre-CT and Post-CT image pairs is respectively acquired in a region before and after an implant is implanted. The Pre-CT and Post-CT images of each pair are artifact-free CT and artifact-affected CT images, respectively. The cGAN is conditioned on the Post-CT images, includes a generator and a discriminator that operably compete with each other, and is characterized with a training objective that is a sum of an adversarial loss and a reconstruction loss. The method also includes training the cGAN with the dataset; inputting the post-operatively acquired CT image to the trained cGAN; and generating an artifact-corrected image by the trained cGAN, where metal artifacts are removed in the artifact-corrected image.

The present disclosure directs to a system and method for image processing. The method for image processing comprises acquiring a plurality of original computed tomography (CT) images of a spine of a subject; generating CT value images of the spine of the subject by processing the plurality of original CT images. The method further includes identifying an optimal sagittal image in which a centerline of the spine is located based on the CT value images. The method further includes identifying the centerline of the spine within the optimal sagittal image. The method further includes identifying a center point and a direction of at least one intervertebral disc along the centerline of the spine. The method still further includes reconstructing an image of the at least one intervertebral disc based on the center point and the direction of the at least one intervertebral disc.

The present disclosure describes methods for improving semi-automatic and/or fully automatic tooth segmentation in reconstructed images of X-ray scans using multi-energy X-ray spectra and/or a multi-energy X-ray scanner at more than one energy. Such improved segmentation of teeth in a reconstructed image of an X-ray scan is a critical first step in the utilization of the image for applications in orthodontics, endodontics, and implant planning In accordance with the methods, tooth segmentation may be performed semi-automatically or automatically for images which are reconstructed from a multi-energy X-ray scan. The results of the tooth segmentation may be represented as an image map which identifies voxels which are within a tooth or as a three-dimensional (3D) grid or any other representation of a three-dimensional (3D) spatial region.

A CPU acquires a radiographic image obtained by imaging an imaging region where a patient is present, with a radioscopy apparatus using radiation emitted from a radiation source and applied to an irradiation field adjusted by a collimator. The CPU specifies a structure image that is included in the radiographic image and represents a structure of a specific shape having transmittance of radiation lower than the patient, based on the specific shape. The CPU executes image processing corresponding to the structure image on a patient image region imaged by a radioscopy apparatus in a case where an irradiation field excluding a position of the structure is set as the irradiation field, in a region in the radiographic image.

The present disclosure directs to a system and method for image processing. The method for image processing comprises acquiring a plurality of original computed tomography (CT) images of a spine of a subject; generating CT value images of the spine of the subject by processing the plurality of original CT images. The method further includes identifying an optimal sagittal image in which a centerline of the spine is located based on the CT value images. The method further includes identifying the centerline of the spine within the optimal sagittal image. The method further includes identifying a center point and a direction of at least one intervertebral disc along the centerline of the spine. The method still further includes reconstructing an image of the at least one intervertebral disc based on the center point and the direction of the at least one intervertebral disc.