Ultrasound imaging system parameter optimization via fuzzy logic

An ultrasound system comprising:

• a plurality of ultrasound image generating subsystems configured to generate an ultrasound image, the plurality of ultrasound image generating subsystems including a transmitter subsystem, a receiver subsystem, and an image processing subsystem;
• and
• a fuzzy logic controller communicatively coupled with at least one of the plurality of ultrasound imaging generating subsystems, wherein the fuzzy logic controller is configured to adaptively adjust parameters for at least B-mode imaging wherein the system parameters include receiver gain control parameters for the receiver subsystem;
• the fuzzy logic controller including a fuzzy logic program stored in a computer readable storage medium;
• wherein the fuzzy logic program includes:
• code for receiving, from at least one of the plurality of ultrasound imaging generating subsystems, input data including at least one of pixel image data and data for generating pixel image data;
• code for processing the input data using a set of inference rules to produce fuzzy output;
• and code for converting the fuzzy output into numerical values or system states for controlling at least one of the transmit subsystem and the receiver subsystem that generate the pixel image data;
• and
• code for adaptively adjusting the receiver gain control parameters for the receiver subsystem to adjust the gain for different regions within the B-mode imaging;
• wherein the code for adaptively adjusting the receiver gain control parameters comprises:
• code for analyzing a pixel intensity distribution in different pre-defined regions (ROI) of a detected image received by the receiver subsystem, based on a most recently processed series of one or more image frames that have been processed by the image processing subsystem;
• code for computing, for each ROI, a mean pixel intensity level and classifying the mean pixel intensity level based on a set of two or more predefined fuzzy membership functions for pixel intensity level;
• code for computing, for each ROI, a percentage of pixels that have exceeded a pre-determined system noise threshold and classifying the result based on a set of two or more predefined fuzzy membership functions for ROI composition;
• code for applying a set of inference rules to evaluate gain change membership values of a set of predefined gain change membership functions;
• code for defuzzifying the gain change membership values, by converting the gain change membership values into a numeric gain adjustment via a set of predefined equations that utilize the gain change membership values as weight factors, to obtain prescribed gain changes;
• and
• code for applying the prescribed gain changes to corresponding data segments for at least one or a current B-mode image frame and a future B-mode image frame.

A method of processing data for generating an ultrasound image, the method comprising:

• receiving, from at least one of a plurality of ultrasound imaging generating subsystems which include a transmitter subsystem, a receiver subsystem, and an image processing subsystem, input data including at least one of pixel image data and data for generating pixel image data;
• adaptively adjusting system parameters for at least one imaging mode wherein the system parameters include receiver gain control parameters for the receiver subsystem wherein:
• adaptively adjusting parameters comprises adaptively adjusting the receiver gain control parameters for the receiver subsystem to adjust the gain for different regions within B-mode imaging, wherein adaptively adjusting the receiver gain control parameter for the receiver subsystem comprises:
• analyzing a pixel intensity distribution in different pre-defined regions (ROI) of a detected image received by the receiver subsystem, based on a most recently processed series of one or more image frames that have been processed by the image processing subsystem;
• for each ROI, computing a mean pixel intensity level and classifying the mean pixel intensity level based on a set of two or more predefined fuzzy membership functions for pixel intensity level;
• for each ROI, computing a percentage of pixels that have exceeded a pre-determined system noise threshold and classifying the result based on a set of two or more predefined fuzzy membership functions for ROI composition;
• applying a set of inference rules to evaluate gain change membership values of a set of predefined gain change membership functions;
• defuzzifying the gain change membership values, by converting the gain change membership values into a numeric gain adjustment via a set of predefined equations that utilize the gain change membership values as weight factors, to obtain prescribed gain changes;
• and
• applying the prescribed gain changes to corresponding data segments for at least one of a current B-mode image frame and a future B-mode image frame.