An ultrasound imaging system (102) includes a touch screen user interface (122) and a touch screen controller (148). The touch screen user interface includes a touch panel (124). The touch panel includes a plurality of different clusters (510-522) of controls including a first cluster (512) in first sub-region and with a tactile control and one or more other cluster (510 and 514-522) in one or more other different sub-regions and with soft controls. The touch screen controller visually renders the one or more other clusters in the one or more different sub-regions spatially arranged with respect to each other based on a predetermined control cluster configuration for the touch screen user interface. The one or more other clusters include controls that correspond to different groupings of ultrasound imaging operations of the ultrasound imaging system.

A surgical implant planning computer positions an implant device relative to a bone of a patient. An initial image of a bone is obtained. An initial location data structure is obtained that contains data defining mapping between locations on the implant device and corresponding locations relative to the bone in the initial image. A target image of the bone of the patient is obtained. A transformation matrix is generated that transforms a contour of a portion of the bone in the initial image to satisfy a defined rule for conforming to a contour of a corresponding portion of the bone in the target image. A transformed location data structure is generated based on applying the transformation matrix to the initial location data structure. A graphical representation of the implant device is displayed overlaid at locations on the target image of the bone determined based on the transformed location data structure.

A method for displaying a target object, an electronic device, and a non-transitory storage medium are provided. The method includes: displaying at least one to-be-analyzed object in response to a first operation for the target object; obtaining an anchor point for determining one of the at least one to-be-analyzed object, in response to a second operation for the target object; determining, according to acquired object distribution images and the anchor point, a range of area where the current to-be-analyzed object corresponding to the anchor point is located in the target object.

A dynamic analysis system includes a hardware processor and an output device. The hardware processor obtains a cycle of temporal change in a feature amount relevant to a function to be diagnosed from each of dynamic images obtained by imaging of a dynamic state of a living body with radiation. The hardware processor further adjusts the obtained cycle, thereby generating a plurality of cycle-adjusted data having cycles of the temporal change in the feature amount being equal to one another. The hardware processor further generates difference information at each phase in the plurality of cycle-adjusted data. The output device outputs the difference information.

A method and system for creating a dynamic self-learning medical image network system, wherein the method includes receiving, from a first node initial user interaction data pertaining to one or more user interactions with the one or more initially obtained medical images; training a deep learning algorithm based at least in part on the initial user interaction data received from the node; and transmitting an instance of the trained deep learning algorithm to the first node and/or to one or more additional nodes, wherein at each respective node to which the instance of the trained deep learning algorithm is transmitted, the trained deep learning algorithm is applied to respective one or more subsequently obtained medical images in order to obtain a result.

A medical scan diagnosing system is operable to receive a medical scan. Diagnosis data of the medical scan is generated by performing a medical scan inference function on the medical scan. The first medical scan is transmitted to a first client device associated with a user of the medical scan diagnosing system in response to the diagnosis data indicating that the medical scan corresponds to a non-normal diagnosis. The medical scan is displayed to the user via an interactive interface displayed by a display device corresponding to the first client device. Review data is received from the first client device, where the review data is generated by the first client device in response to a prompt via the interactive interface. Updated diagnosis data is generated based on the review data. The updated diagnosis data is transmitted to a second client device associated with a requesting entity.

Various methods and systems are provided for breast positioning assistance during mammography and image guided interventional procedures. In one example, a vision system is utilized to evaluate one or more of a patient position, a breast position, and breast anatomy to determine if the patient and breast are adjusted to desired positions preferred for a desired view and imaging procedure. Further, based on the evaluation, prior to acquiring x-ray images, real-time feedback may be provided to guide the user to position the breast and/or the patient.

Provided is an image processing device that includes a hardware processor. The hardware processor calculates a feature amount relevant to a breast shape from a mammography image. The hardware processor selects a schema image corresponding to the breast shape of the mammography image from a plurality of types of predetermined schema images based on the feature amount relevant to the breast shape calculated by the hardware processor.

A method for determining one or more of selection, positioning or placement of a surgical implant, the method includes: predicting function of an impaired anatomical structure in an unimpaired condition; predicting post-operative function of the structure for one or more implants; selecting one or more of the implant, the implant position, or the implant location to improve the predicted post-operative function.

Not only is annotating medical images tedious and time consuming, but it also demands costly, specialty-oriented expertise, which is not easily accessible. To address this challenge, a new self-supervised framework is introduced: TransVW (transferable visual words), exploiting the prowess of transfer learning with convolutional neural networks and the unsupervised nature of visual word extraction with bags of visual words, resulting in an annotation-efficient solution to medical image analysis. TransVW was evaluated using NIH ChestX-ray14 to demonstrate its annotation efficiency. When compared with training from scratch and ImageNet-based transfer learning, TransVW reduces the annotation efforts by 75% and 12%, respectively, in addition to significantly accelerating the convergence speed. More importantly, TransVW sets new records: achieving the best average AUC on all 14 diseases, the best individual AUC scores on 10 diseases, and the second best individual AUC scores on 3 diseases. This performance is unprecedented, because heretofore no self-supervised learning method has outperformed ImageNet-based transfer learning and no annotation reduction has been reported for self-supervised learning. These achievements are contributable to a simple yet powerful observation: The complex and recurring anatomical structures in medical images are natural visual words, which can be automatically extracted, serving as strong yet free supervision signals for CNNs to learn generalizable and transferable image representation via self-supervision.