Ultrasound imaging system with automatic image saving

An ultrasound system for imaging a region of interest of a subject during a needle injection into the region of interest, comprising:

• a transducer configured to transmit ultrasound signals to and receive echo signals from the region of interest;
• a receive circuitry configured to convert the echo signals into image frames of ultrasound data;
• a buffer memory configured to store the image frames;
• and
• a processor configured to:
• obtain a first subset of the image frames from the buffer memory;
• compare the first subset of the image frames to each other;
• identify, from the first subset, a first image frame indicating that a needle used for a needle injection procedure is approaching to a target and a second image frame indicating that the needle has stopped moving at the target based on the comparing;
• obtain a second subset of the image frames from the buffer memory, wherein the second subset of the image frames have been generated and stored subsequent to the first subset in the buffer memory;
• identify, from the second subset, a third image frame indicating a tip of the needle using a machine learning algorithm;
• obtain a third subset of the image frames depicting a region around the tip of the needle from the buffer memory, wherein the third subset of the image frames have been generated and stored subsequent to the second subset in the buffer memory;
• identify, from the third subset, a fourth image frame indicating an injection of a fluid from the tip of the needle using a color flow imaging;
• and
• store at least three of the first image frame, the second image frame, the third image frame and the fourth image frame that depict the needle injection in a first memory for archival purposes.

A method performed by a processor in an ultrasound system, the method comprising:

• receiving ultrasound signals from a region of interest during a needle injection procedure;
• converting the ultrasound signals into image frames of ultrasound data;
• storing the image frames in a buffer memory;
• obtaining a first subset of the image frames from the buffer memory;
• comparing the first subset of the image frames to each other;
• indentifying, from the first subset, a first image frame indicating that a needle used for a needle injection procedure is approaching to a target and a second image frame indicating that the needle has stopped moving at the target based on the comparing,
• obtaining a second subset of the imgage frames from the buffer memory, wherein the second subset of the image frames have been generated and stored subsequent to the first subset in the buffer memory;
• identifying, from the second subset, a third image frame indicating a tip of the needle using a machine learning algorithm;
• obtaining a third subset of the image frames depicting a region around the tip of the needle from the buffer memory, wherein the third subset of the image frames have been generated and stored subsequent to the second subset in the buffer memory,
• identifying, from the third subset, a fourth image frame indicating an injection of a fluid from the tip of the needle using a color flow imaging;
• and
• saving at least three of the first image frame, the second image frame, the third image frame and the fourth image frame that depict the injection event in a first memory.