An ultrasound diagnostic apparatus 1 includes an image acquisition unit 3 that generates an ultrasound image, an image recognition unit 9 that performs image recognition for the ultrasound image to calculate recognition scores, an index value calculation unit 10 that calculates index values of a plurality of parts on the basis of the recognition scores calculated for a predetermined number of ultrasound images, an order decision unit 11 that decides a determination order in which part determination is performed for the plurality of parts on the basis of the index values, and a part determination unit 12 that determines an imaging part of a subject on the basis of the recognition scores calculated according to the determination order.

An ultrasound diagnosis apparatus including: an ultrasound probe; a processor configured to perform transmission of ultrasound beam from the ultrasound probe to a subject to acquire an ultrasound image; a camera configured to acquire a digital image of a state of the ultrasound probe being in contact with the subject; a touch panel including a display screen displaying the ultrasound image and the digital image; an interface to receive instruction to acquire the ultrasound image and/or the digital image from a user; and a memory configured to store the ultrasound image and the digital image, wherein the processor is further configured to: exclusively control between the acquisition of the ultrasound image and the acquisition of the digital image according to instruction received by the interface; and save the ultrasound image and the digital image of the same inspection in the memory in association with each other.

An image analysis unit has a reliability calculation unit that calculates the reliability indicating the possibility that a lesion candidate is a lesion. A mark display control unit displays a mark reporting the lesion candidate on an ultrasonic image. In a continuous detection state where the reliability continues to meet the candidate detection conditions, the mark is continued to be displayed. During the time, the form of the mark is fixed from the time point when the candidate detection conditions are first met until a fixed form period elapses. The form of the mark is then changed as the reliability varies.

In an ultrasound diagnostic apparatus and an operation method of the ultrasound diagnostic apparatus of the invention, a control circuit performs polarization processing on a plurality of ultrasound transducers in a non-diagnosis period, during which transmission of ultrasound waves and reception of reflected waves for performing ultrasound diagnosis are not performed, in a case where the cumulative driving time of the plurality of ultrasound transducers for performing the ultrasound diagnosis becomes equal to or longer than a specified time. A transmission circuit generates a first transmission signal having a driving voltage for performing ultrasound diagnosis using a pulse generation circuit in the case of performing the ultrasound diagnosis, and generates a second transmission signal having a polarization voltage for performing polarization processing using the same pulse generation circuit as in the case of generating the first transmission signal in the case of performing the polarization processing.

Aspects of the disclosed technology provide ways to detect the object of ultrasound scanning and to automatically, load system settings and image preferences necessary to generate high quality output images. In some aspects, an ultrasound system can be configured to perform steps including receiving a selection of a first transducer, identifying a body structure or organ based on a signal received in response to an activation of the first transducer, retrieving a first set of image parameters corresponding with the body structure, and configuring the first transducer based on the first set of image parameters. Methods and machine-readable media are also provided.

Machine learning trains to tune settings. For training, the user interactions with the image parameters (i.e., settings) as part of ongoing examination of patients are used to establish the ground truth positive and negative examples of settings instead of relying on an expert review of collected samples. Patient information, location information, and/or user information may also be included in the training data so that the network is trained to provide settings for different situations based on the included information. During application, the patient is imaged. The initial or subsequent image is input with other information (e.g., patient, user, and/or location information) to the machine-trained network to output settings to be used for improved imaging in the situation.

During acquisition of an ultrasound image feed, ultrasound control data frames are acquired that may be interspersed amongst the ultrasound data frames. The control data frames may use consistent reference scan parameters, irrespective of the scanner settings, and may not need to be converted to image frames. The control data frames can be passed to an artificial intelligence model, which predicts the suitable settings for scanning the anatomy that is being scanned. The artificial intelligence model can be trained with a dataset containing different classes of ultrasound control data frames for different settings, where substantially all the ultrasound control data frames in the dataset are consistently acquired using the reference scan parameters.

An ultrasonic image diagnostic apparatus includes: an ultrasonic image acquisitor that acquires an ultrasonic image generated on the basis of a reception signal obtained by an ultrasonic probe that transmits and receives ultrasonic waves to and from a subject; an identification result acquisitor that acquires, by inputting the ultrasonic image acquired to any of a plurality of identifiers that identifies an identification target object captured in an input ultrasonic image, an identification result output from the identifier; and a hardware processor that changes the identifier to which the ultrasonic image acquired is input.

The invention provides a method for identifying a characteristic of one or more ultrasound images, wherein each image is of a subject imaged by an ultrasound probe using an ultrasound imaging process. The method includes obtaining a manipulation signal indicative of a manipulation of the ultrasound probe during the imaging process. A portion of the manipulation signal, which indicates the manipulation of the probe during a time period, is obtained. The obtained portion is associated with one or more ultrasound images. A neural network system is then used to classify a characteristic of the one or more ultrasound images based on both the obtained portion of the manipulation signal and the one or more images themselves. Such classification comprises applying one or more convolution kernels on the obtained portion of the manipulation signal to generate a convolution output representative of the obtained portion of the manipulation signal, and classifying the convolution output to indicate the characteristic of the one or more ultrasound images associated with the obtained portion.

A guidance system is configured to detect a current pose of an ultrasound transducer and to determine a movement to achieve a desired pose associated with a desired view or imaging plane of a patients anatomy. In one embodiment, the guidance system includes a processor circuit in communication with the ultrasound transducer. The processor circuit is configured to: receive an input associated with a desired pose of the ultrasound transducer; receive ultrasound imaging data representative of a field of view of the ultrasound transducer in a current pose; determine a movement to align the current pose of the ultrasound transducer with the desired pose; and generate a graphical representation of the movement. The graphical representation shows both the current pose of the ultrasound transducer and the desired pose of the ultrasound transducer. The graphical representation is output to a display in communication with the processor circuit.