Ultrasound system acoustic output control using image data

Abstract

The ultrasound system uses image recognition to characterize the anatomy being imaged and then considers the identified anatomical features when setting the acoustic output level or limit of the ultrasound probe. Alternatively, instead of automatically setting the acoustic output level or limit, the system can alert the clinician that a change in operating level or condition is advisable for the current exam. In this way, the clinician can maximize the signal-to-noise level in the image for clearer, more abundant images while maintaining a safe level of acoustic output for patient safety.

Description

[Technical Field]

[0001] The present invention relates to medical diagnostic ultrasound systems, and more particularly to controlling the acoustic output of an ultrasound probe using image data. [Background technology]

[0002] Ultrasound imaging is one of the safest medical imaging modalities because it uses non-ionizing radiation to generate propagating sound waves. Nevertheless, numerous studies have been conducted over the years to determine potential biological effects. These studies have focused on long-term exposure to ultrasound energy, which can have thermal and cavitational effects due to high peak pulse energies. Some of the more prominent studies and reports published on these effects include "Diagnostic Ultrasound Bioeffects and Safety" (AIUM Report, January 28, 1993) and "American Institute of Ultrasound in Medicine Bioeffects Consensus Report" (Journal of Ultrasound in Medicine, Vol. 27, April 4, 2008). The FDA has also issued guidance documents regarding the safety and energy limits of ultrasound used in FDA clearance processes, such as "Information for Manufacturers Seeking Market Clearance of Diagnostic Ultrasound Systems and Transducers" in September 2008. Manufacturers use all of this information and other sources when designing, testing, and setting the energy limits of their ultrasound systems and transducer probes.

[0003] Measuring acoustic power from a transducer probe is an integral part of the transducer design process. Measurements of the acoustic power of a probe under development can be made in a water bath and used to set limits for driving the probe transmitter within the ultrasound system. Currently, manufacturers use I as the peak mechanical index for peak pulse (cavitation) effect limiting, I for thermal effect limiting, and MI ≤ 1.9. spta.3We adhere to the acoustic limit for general imaging of ≦720 mW / cm 2. The current operating levels for these thermal and mechanical means are constantly displayed on the display screen along with the image during operation of the ultrasound probe.

[0004] However, while ultrasound systems have these designed bio-effect limits, it is the responsibility of the clinician performing the exam to ensure that the system is always operated safely, especially for exams where lower limits are recommended. An important consideration is that bio-effects are a function not only of output power but also of other operating parameters that can affect patient safety, such as imaging mode, pulse repetition frequency, focal depth, pulse length, and transducer type. There are some types of exams for which operating guidance recommends specific probe operation. For example, shear wave imaging is contraindicated for obstetric exams. Most ultrasound systems have some form of acoustic output controller, which constantly evaluates these parameters and continuously estimates acoustic output, making adjustments to maintain operation within predetermined safety limits. Summary of the Invention [Problem to be solved by the invention]

[0005] However, much more can be done than just measuring the operating parameters of an ultrasound system. It would be desirable to automatically evaluate the performance of an exam from the clinician's perspective and make adjustments or recommendations to the output control. For example, it would be desirable to characterize the anatomy being imaged and use image information in setting or recommending changes to acoustic output to improve patient safety. [Means for solving the problem]

[0006] In accordance with the principles of the present invention, an ultrasound system uses image recognition to characterize the anatomy being imaged and then sets the acoustic output level or limit of the ultrasound probe taking into account the identified anatomical features. Alternatively, instead of automatically setting the acoustic output level or limit, the system can alert the clinician that a change in operating level or condition is advisable for the current exam. In this way, the clinician can maximize the signal-to-noise level in the image for a clearer, more diagnostic image while maintaining a safe level of acoustic output for patient safety. [Brief explanation of the drawings]

[0007] [Figure 1] 1 illustrates method steps for using acquired image data to advise or modify acoustic output in accordance with the present invention. [Figure 2] FIG. 1 is a block diagram of an ultrasound system constructed in accordance with a first embodiment of the present invention that uses an anatomical model to identify anatomical structures in ultrasound images. [Figure 3] 3 illustrates method steps for operating the ultrasound system of FIG. 2 in accordance with the principles of the present invention. [Figure 4] FIG. 1 is a block diagram of an ultrasound system configured in accordance with a second embodiment of the present invention, which uses a neural network model to identify anatomical structures in ultrasound images in accordance with the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0008] Referring first to FIG. 1 , a method for using image data in controlling acoustic output is shown. Image data is acquired in step 60 as a clinician scans a patient. In the example of FIG. 1 , the clinician is scanning the liver, as shown by acquired liver image 60a. The ultrasound system identifies this image as a liver image by recognizing known characteristics of the liver image, such as its depth within the body, the generally smooth texture of liver tissue, the depth to its distant boundaries, and the presence of bile ducts and blood vessels. The ultrasound system can also consider cues from the exam setup, such as the use of a deep abdominal probe and the extensive depth of the image. Using this information, the ultrasound system characterizes the image data in step 62 as an image of the liver acquired in an abdominal imaging exam. The ultrasound system then uses probe operating characteristics, such as drive voltage, thermal and MI settings, and other probe setup parameters described above, to identify the probe's current acoustic output. Next, in step 64, the calculated acoustic output is compared to recommended clinical limits for the abdominal exam.

[0009] An advisory or adjustment step 66 determines whether further action is indicated based on the comparison step 64. For example, if the current acoustic power is below the recommended acoustic power limit for the anatomy being imaged, a message may be issued to the clinician advising that the acoustic power be increased to produce echoes with a stronger signal-to-noise level and therefore a clearer, more distinct image. Other comparisons may indicate that the acoustic power is higher than the recommended limit for the anatomy being imaged, or that the operating mode is inappropriate for the anatomy being imaged.

[0010] The system then issues a message advising the clinician to adjust the acoustic power, if necessary, in step 66. The system can also automatically adjust the acoustic power limits in response to those recommended for the abdominal exam. If the current acoustic power is below the acoustic power limit recommended for the anatomy being imaged, a message can be issued to the clinician advising them to increase the acoustic power to produce echoes with a stronger signal-to-noise level, and therefore a clearer, sharper image.

[0011] FIG. 2 illustrates, in block diagram form, a first embodiment of an ultrasound system capable of operating according to the method of FIG. 1. A transducer array 112 is provided within the ultrasound probe 10 for transmitting ultrasound waves and receiving echo information from a region of the body. The transducer array 112 may be a two-dimensional array of transducer elements capable of electronically scanning in two or three dimensions, both in elevation (3D) and azimuth, as shown. Alternatively, the transducer may be a one-dimensional array capable of scanning a single image plane. The transducer array 112 is coupled to a microbeamformer 114 within the probe, which controls the transmission and reception of signals by the array elements. The microbeamformer is capable of at least partial beamforming of signals received by groups or "patches" of transducer elements, as described in U.S. Patent Nos. 5,997,479 (Savord et al.), 6,013,032 (Savord), and 6,623,432 (Powers et al.). One-dimensional array transducers can be operated directly by the system beamformer without the need for a microbeamformer. In the probe embodiment shown in FIG. 2, the microbeamformer is coupled by a probe cable to a transmit / receive (T / R) switch 16, which switches between transmit and receive, protecting the main system beamformer 20 from high-energy transmit signals. The transmission of ultrasound beams from the transducer array 112 under the control of the microbeamformer 114 is directed by a transmit controller 18 coupled to the T / R switch and the beamformer 20, which receives input from user operation of the system's user interface or control unit 24. Among the transmit characteristics controlled by the transmit controller are the spacing, amplitude, phase, frequency, repetition rate, and polarity of the transmit waveform. The beam formed in the direction of pulse transmission may be steered straight ahead from the transducer array or at different angles for a wider sector field of view.

[0012] Echoes received by successive groups of transducer elements are beamformed by appropriately delaying and then combining them. The partially beamformed signals generated by the microbeamformer 114 from each patch are coupled to the main beamformer 20, where the partially beamformed signals from individual patches of transducer elements are delayed and combined into a fully beamformed coherent echo signal. For example, the main beamformer 20 may have 128 channels, each of which receives partially beamformed signals from a patch of 12 transducer elements. In this way, signals received by 1500 or more transducer elements of a two-dimensional array transducer can efficiently contribute to a single beamformed signal. When the main beamformer is receiving signals from elements of a transducer array without a microbeamformer, the number of beamformer channels is typically equal to or greater than the number of elements providing signals for beamforming, and all beamforming is performed by the beamformer 20.

[0013] The coherent echo signals are subjected to signal processing by a signal processor 26, which includes digital filtering and noise reduction by spatial or frequency multiplexing. The digital filters of the signal processor 26 may be, for example, of the type disclosed in U.S. Pat. No. 5,833,613 (Averkiou et al.). The processed echo signals are demodulated into quadrature (I and Q) components by a quadrature demodulator 28, which provides signal phase information and can also shift the signal information to frequencies in the baseband range.

[0014] The beamformed and processed coherent echo signals are coupled to a B-mode processor 52 that generates a B-mode image of a body structure such as tissue. 2 +Q 2 ) 1 / 2Amplitude (envelope) detection of the quadrature-demodulated I and Q signal components is performed by calculating the echo signal amplitude in the form: The quadrature echo signal components are also coupled to a Doppler processor 46, which accumulates an ensemble of echo signals from discrete points within the image field, which is then used by a fast Fourier transform processor to estimate the Doppler shift at the point within the image. The Doppler shift is proportional to motion at the point within the image field, e.g., blood flow and tissue motion. For color Doppler images that can be generated for analysis of blood flow, the estimated Doppler flow values ​​at each point within the vessel are filtered using a lookup table and converted to a color value. Either the B-mode image or the Doppler image may be displayed alone, or together with a color Doppler overlay in anatomical registration showing blood flow within the tissue and vessels within the imaged region.

[0015] The B-mode image signals and, in the case of volumetric imaging, Doppler flow values ​​are coupled to a 3D image data memory 32, which stores image data in x, y, and z corresponding to the scanned volumetric region of the subject. For 2D images, a two-dimensional memory with addressable x,y memory locations can be used. The volume image data in the 3D data memory is coupled to a volume renderer 34, which converts the echo signals of the 3D data set into a 3D image projected from a given reference point, as described in U.S. Pat. No. 6,530,885 (Entrekin et al.). The reference point, which is the viewpoint from which the imaged volume is viewed, may be changed by controls on the user interface 24, allowing the volume to be tilted or rotated to examine the region from different perspectives. The rendered 3D image is coupled to an image processor 30, which processes the image data as needed for display on the image display 100. Ultrasound images are typically presented along with graphical data generated by a graphics processor 36, such as the patient's name, image depth markers, and scan information such as probe thermal output and mechanical index (MI). The volumetric image data is also coupled to a multi-planar reformatter 42 that is capable of extracting a single plane of image data from the volumetric data set for display of a single image plane.

[0016] In accordance with the principles of the present invention, the system of FIG. 2 includes an image recognition processor. In the embodiment of FIG. 2, the image recognition processor is a fetal bone model 86. The fetal model includes a memory that stores a library of mathematical models of different sizes and / or shapes in the form of data of typical fetal bone structures, and a processor that compares the models with structures in acquired ultrasound images. The library can include different sets of models, each representing a typical fetal structure at a particular age in fetal development, such as the first and second trimesters of development. The model is data representing a mesh of the fetal skeleton and the skin (surface) of the developing fetus. Because the bone mesh is interconnected like the actual bones of the skeleton, its range of relative movement and articulation is constrained in the same way as that of the actual skeletal structure. Similarly, the surface mesh is constrained to be within a certain range of distance from the bones it surrounds. When ultrasound images from an abdominal examination contain echoes that may be strong reflections from solid objects such as bones, the image information is combined with the fetal model and used to select a specific model from the library as a starting point for analysis. The model can be deformed within constraint limits, e.g., fetal age, by changing parameters of the model to distort the model, such as an adaptive mesh representing the approximate surface of a typical skull or femur, thereby fitting the model to structural landmarks in the image dataset through deformation. Adaptive mesh models are desirable because they can be warped, within the limits of their mesh continuity and other constraints, to fit the deformed model to structures in the image. The foregoing model deformation and fitting is described in further detail in International Patent Application No. WO 2015 / 019299 (Mollus et al.), entitled "Model-Based Segmentation of an Atomic Structure."See also International Patent Application No. WO 2010 / 150156 (Peters et al.), entitled "ESTABLISHING A CONTOUR OF A STRUCTURE BASED ON IMAGE INFORMATION," and U.S. Patent Application No. 2017 / 0128045 (Roundhill et al.), entitled "TRANSLATION OF ULTRASOUND ARRAY RESPONSIVE TO ANATOMICAL ORIENTATION." The process can be adapted by the model, and continues by the automatic shape processor until data is found within a plane or volume that can be identified as fetal bone structure. Planes within the volumetric image dataset may be selected by the fetal model operating on volumetric image data provided by the volume renderer 34, when the bone model is configured to do so. Alternatively, a series of differently oriented image planes that intersect the suspect location can be extracted from the volumetric data by the multiplanar reformatter 42 and provided to the fetal model 86 for analysis and fitting. When the image analysis identifies fetal bone structures in the image, this characterization of the image data is coupled to acoustic output controller 44, which compares the current acoustic output set by the controller with clinical limit data for the obstetric exam stored in clinical limit data memory 38. If the current acoustic output setting is found to exceed the limits recommended for the obstetric exam, the acoustic output controller can command a message to be displayed on display 100, informing the clinician that a lower acoustic output setting is recommended. Alternatively, the acoustic output controller can set a lower limit for the acoustic output of transmit controller 18.

[0017] FIG. 3 illustrates a method for controlling acoustic power using the ultrasound system of FIG. 2 just described. Image data is acquired at step 60, in this example fetal image 60b. The image data is analyzed with a fetal bone model that identifies fetal bone structure, thus characterizing the image as a fetal image at step 62. At step 64, acoustic power controller 44 compares the current acoustic power performance and / or settings with limits appropriate for fetal examination. If any of these limits are exceeded by the current acoustic power, at step 66, the user is advised to reduce the acoustic power, or the acoustic power is automatically changed by the acoustic power controller. Alternatively, imaging modes not recommended for obstetric examinations, such as shear wave imaging, can be automatically prohibited from operation.

[0018] A second embodiment of an ultrasound system of the present invention is shown in block diagram form in Figure 4. In the system of Figure 4, the system elements shown and described in Figure 2 are used for similar functions and operations and will not be described again. In the system of Figure 4, the image recognition processor includes a neural network model 80. The neural network model utilizes a development in artificial intelligence called "deep learning," a rapidly developing field of machine learning algorithms that mimics the way the human brain functions when analyzing problems. The human brain recalls what it has learned from solving similar problems in the past and applies that knowledge to solve new problems. Exploration is ongoing to identify possible uses of this technology in many fields, including pattern recognition, natural language processing, and computer vision. Deep learning algorithms have a distinct advantage over traditional forms of computer programming algorithms in that they can be generalized and trained to recognize image features by analyzing image samples rather than writing custom computer code. However, the anatomical structures visualized in ultrasound systems do not appear to readily lend themselves to automated image recognition. Every person is different, and anatomical shapes, sizes, locations, and functions vary from person to person. Furthermore, the quality and clarity of ultrasound images vary even when using the same ultrasound system because the body's environment affects the ultrasound signals returned from inside the body that are used to form the image. For example, scanning a fetus through the pregnant mother's abdomen often results in significant attenuation of the ultrasound signal, obscuring anatomical structures in the fetal image. Nevertheless, the system described in this implementation demonstrated the ability to use deep learning techniques to recognize anatomy in fetal ultrasound images through processing with a neural network model. The neural network model is first trained by presenting it with multiple images of known anatomical structures, for example, fetal images with known fetal structures that are identified against the model.Once trained, live images acquired by a clinician during an ultrasound examination are analyzed in real time by the neural network model, which identifies fetal anatomical structures in the images.

[0019] Deep learning neural network models include software that can be written by software designers and are publicly available from many sources. In the ultrasound system of FIG. 4, the neural network model software is stored in digital memory. An application that can be used to build neural network models, called “NVidia Digits,” is available at https: / / developer.nvidia.com / digits. NVidia Digits is an advanced user interface centered around a deep learning framework called “Caffe,” developed by the Berkeley Vision and Learning Center (http: / / caffe.berkeleyvision.org / ). A list of popular deep learning frameworks suitable for use in implementing the present invention can be found at https: / / developer.nvidia.com / deep-learning-frameworks. Coupled to the neural network model 80 is a training image memory 82, in which ultrasound images of known fetal anatomy, including fetal bony structures, are stored and used to train the neural network model to identify that anatomical structure in the ultrasound image dataset. Once the neural network model has been trained with a large number of known fetal images, the neural network model receives image data from the volume renderer 34. The neural network model can receive other cues in the form of anatomical information, such as the fact that an abdominal examination is being performed, as described above. The neural network model then analyzes regions of the image until fetal bony structures are identified in the image data. As previously described, the ultrasound system then characterizes the acquired ultrasound image as a fetal image and forwards this characterization to the acoustic output controller 44. The acoustic output controller compares the currently controlled acoustic output with recommended clinical limits for fetal images and either alerts the user of excessive acoustic output or automatically resets the acoustic output limit setting as described above for the first embodiment. Variations of the above-described system and method will be readily apparent to those skilled in the art. Other image recognition algorithms may be used if desired.Other devices and techniques may or may alternatively be used to characterize the anatomical structures in the images, such as the data entered into the ultrasound system by the clinician.

[0020] The techniques of the present invention can be used in other diagnostic fields besides abdominal imaging. For example, many ultrasound examinations require standard views of anatomical structures for diagnosis, which are amenable to relatively easy identification in images. In renal diagnosis, the standard view is a coronal image plane of the kidney. In cardiology, two-, three-, and four-chamber views of the heart are standard views. Models of other anatomical structures, such as cardiac models, are now commercially available. Neural network models can be trained to recognize such views and anatomical structures in cardiac image datasets and then used to characterize cardiac use of an ultrasound probe. Other applications will be readily apparent to those skilled in the art.

[0021] It should be noted that the component structures of ultrasound systems suitable for use in implementing the present invention, particularly those of FIGS. 2 and 4 , can be implemented in hardware, software, or a combination thereof. Various embodiments and / or components of the ultrasound system, such as the fetal bone model and deep learning software module, or components therein, processors, and controllers, may be implemented as part of one or more computers or microprocessors. The computer or processor may include a computing device, an input device, a display unit, and an interface, for example, for accessing the Internet. The computer or processor may include a microprocessor. The microprocessor may be connected to a communication bus, for example, for accessing a PACS system or a data network for importing training images. The computer or processor may also include memory. Memory devices, such as the 3D image data memory 32, the training image memory, the clinical data memory, and the memory storing the fetal bone model library, may include random access memory (RAM) and read-only memory (ROM). The computer or processor may further include a storage medium, which may be a hard disk drive or a removable storage drive, such as a floppy disk drive, an optical disk drive, or a solid-state thumb drive. The storage device may also be any other similar means for loading computer programs or other instructions into a computer or processor.

[0022] As used herein, the terms "computer" or "module" or "processing device" or "workstation" may include any microprocessor-based or microprocessor-based system, including systems using microprocessor controllers, reduced instruction set computers (RISC), ASICs, logic circuits, and any other circuitry or processing device capable of performing the functions described herein. The above examples are illustrative only and are thus not intended to limit in any way the definition and / or meaning of these terms.

[0023] A computer or processor executes a set of instructions stored in one or more memory devices to process input data. The memory devices may also store data or other information as desired or needed. The memory devices may be in the form of information sources or physical memory devices within a processing machine.

[0024] A set of instructions for an ultrasound system, including instructions for controlling the acquisition, processing, and transmission of ultrasound images as described above, may include various commands that instruct a computer or processor as a processing machine to perform specific operations, such as the methods and processes of various embodiments of the present invention. The set of instructions may form a software program. The software may be in various forms, such as system software or application software, and may be embodied as a tangible, non-transitory computer-readable medium. Furthermore, the software may form a collection of separate programs or modules, such as a neural network model module, a program module within a larger program, or portions of a program module. This software may also include modular programming in the form of object-oriented programming. The processing of input data by a processing device may be in response to operator commands, results of previous processing, or requests by other processing devices.

[0025] Moreover, the following claim limitations are not written in means-plus-function format and are not intended to be construed under 35 U.S.C. § 112, sixth paragraph, except where such claim limitations expressly use the phrase "means" followed by a functional statement lacking further structure.

Claims

1. 1. An ultrasound imaging system that sets or recommends acoustic output levels or limits in consideration of image data, comprising: an ultrasound probe configured to acquire image data of an anatomical structure, the ultrasound probe further comprising a transducer array configured to transmit acoustic waves of controllable acoustic power; a display configured to display an ultrasound image of the anatomical structure from the acquired image data; an image recognition processor configured, in response to the acquired image data, to process the image data and identify particular anatomical structures depicted in the ultrasound images of the image data based on deriving features of the ultrasound images; an acoustic output controller configured to recommend or set an acoustic output level or limit for the transducer array taking into account the identified anatomical structure; and the acoustic output controller is further configured to cause an acoustic output message to be displayed on the display when operating below a recommended acoustic output limit, the acoustic output message indicating that the acoustic output can be increased; the acoustic output controller is further configured to inhibit an image capture mode in response to a characterization of the image. Ultrasound imaging system.

2. The ultrasound imaging system of claim 1 , wherein the image recognition processor further comprises an anatomical model.

3. The ultrasound imaging system of claim 2 , wherein the image recognition processor is further configured to compare the image data to an anatomical model.

4. The ultrasound imaging system of claim 3 , wherein the image recognition processor is configured to characterize the ultrasound image in response to a comparison of the image data to an anatomical model.

5. The ultrasound imaging system of claim 4 , wherein the acoustic power controller is configured to recommend or set the acoustic power level or limit in consideration of the characterization of the ultrasound image.

6. The ultrasound imaging system of claim 1 , wherein the image recognition processor comprises a neural network model.

7. The ultrasound imaging system of claim 6 , wherein the image recognition processor further comprises a training image memory.

8. 7. The ultrasound imaging system of claim 6, wherein the image recognition processor is configured to characterize the ultrasound image in response to deep learning analysis of the ultrasound image by the neural network model.

9. 9. The ultrasound imaging system of claim 8, wherein the acoustic output controller is configured to recommend or set the acoustic output level or limit in consideration of the characterization of the ultrasound image by the neural network model.

10. a memory in communication with the acoustic power controller configured to store clinical acoustic power limit data; the acoustic output controller is further configured to recommend or set an acoustic output level or limit for the transducer array in consideration of the data.

10. The ultrasound imaging system of claim 1.

11. The ultrasound imaging system of claim 1 , wherein the acoustic output controller is further configured to cause an acoustic output message to be displayed on the display.

12. a transmit controller coupled to the transducer array and configured to control acoustic transmission by the transducer array; the transmit controller is responsive to an acoustic power limit set by the acoustic power controller; 10. The ultrasound imaging system of claim 1.

13. 13. The ultrasound imaging system of claim 12, wherein the acoustic output controller is further responsive to one or more of a transducer drive voltage, an imaging mode, a pulse repetition frequency, a focal depth, a pulse length, and a transducer type when recommending or setting an acoustic output level or limit.

14. A method for setting or recommending acoustic output levels or limits taking into account image data, comprising: identifying a characteristic of an acoustic output level from an ultrasound probe in an ultrasound system; acquiring ultrasound image data from the ultrasound system; characterizing the image data to identify an anatomical structure being imaged; providing at least one of output guidance to adjust the acoustic output level or automatically adjusting the acoustic output level based on the identified anatomical structure; displaying an acoustic power message that the acoustic power can be increased when operating below a recommended acoustic power limit; inhibiting an image capture mode in response to the image characterization; having method.

15. The method of claim 1, further comprising: comparing the acoustic output level characteristic signature with predetermined clinical limits for the imaged anatomical structure; adjusting the acoustic output level or providing output guidance based on the comparison; and 15. The method of claim 14, comprising:

16. A computer program product embodied in a non-volatile computer-readable medium that, when coupled to a processor in an ultrasound system having an ultrasound probe, provides instructions to the processor for setting or recommending acoustic output levels or limits in view of image data, the instructions comprising: identifying a characteristic signature of acoustic output levels from the ultrasound probe in the ultrasound system; acquiring ultrasound image data from the ultrasound system; characterizing the image data to identify an anatomical structure being imaged; automatically adjusting the acoustic output level based on the identified anatomical structure; displaying an acoustic power message that the acoustic power can be increased when operating below a recommended acoustic power limit; inhibiting an image capture mode in response to the image characterization; 1. A computer program product comprising:

Images