Dynamic adjustment of image compression for high resolution live medical image sharing

Abstract

A video stream of live medical images is generated at a local site having a medical image scanner. A live video stream is transmitted to at least one remote site via a network, which may include wired or wireless Internet connections. Network conditions are monitored during a network session and predictions are made on a predicted bit rate for transmission. The compression parameters for the live video stream are selected based on the predicted bit rate.

What is claimed is: 
     
         1 . A method of transmitting over the Internet a live video stream of ultrasound imaging data, comprising:
 monitoring a set of quality of service metrics for a network communication session between a local site having an ultrasound imaging scanner and a remote site;   predicting, based on the set of quality of service metrics, a minimum expected bit rate to transmit a compressed video stream including a live ultrasound video stream;   selecting, in response to the expected bit rate, video compression parameters to compress the video stream including the live ultrasound video stream; and   transmitting the compressed video stream to the remote site.   
     
     
         2 . The method of  claim 1 , wherein the at least one quality of service metric comprises a bandwidth metric, a packet loss metric, a packet latency, and a packet corruption metric. 
     
     
         3 . The method of  claim 1 , wherein the predicting comprises a prediction technique selected from the group consisting of a linear predication algorithm and a nonlinear prediction algorithm. 
     
     
         4 . The method of  claim 1 , wherein the predicting comprises a prediction technique selected from the group consisting of a linear prediction algorithm, Kalman prediction, and hidden Markov model prediction. 
     
     
         5 . The method of  claim 1 , wherein the live medical image video stream comprises one of an ultrasound video stream, an angiography video stream, and an endoscopy video stream. 
     
     
         6 . The method of  claim 1 , wherein the selecting comprises selecting from at least two different video compression protocols. 
     
     
         7 . The method of  claim 6 , wherein the at least two different video compression protocol include a MJPEG2000 compression protocol and at least one of MPEG-4, H.264, H.265, VP8, and VP9. 
     
     
         8 . The method of  claim 1 , wherein the selecting comprises selecting a subset of features of a particular video compression protocol. 
     
     
         9 . The method of  claim 8 , wherein the selecting a subset of features includes selecting at least one of:
 turning on or off the MVC encoding;   varying the block sizes of frames;   varying the quantization tables for intra-frame discrete cosine transform (DCT) compression;   varying motion vector compensation (MVC) for inter-frame compression, and reducing the stream frame rate by dropping frames ahead of the compression engine.   
     
     
         10 . The method of  claim 1 , further comprising selecting a transmission protocol based on the expected bit rate. 
     
     
         11 . The method of  claim 1 , further comprising analyzing quality of service metrics for a plurality of sessions and providing a network service recommendation. 
     
     
         12 . A method of tuning video compression parameters for a live video stream of medical images in a networked telemedicine environment having variable network quality, comprising:
 monitoring at least one quality of service metric for a network session between a local site having a medical imaging scanner and a remote site;   predicting, based on the at least one quality of service metric, a minimum expected bit rate to transmit a compressed live video stream of high resolution medical images from the medical imaging scanner;   selecting, in response to the expected bit rate, video compression parameters for the live video stream of medical images;   compressing the live video stream of high resolution medical image, using the selected video compression parameters; and   transmitting the compressed live video stream to the remote site.   
     
     
         13 . The method of  claim 12 , wherein the at least one quality of service metric is monitored in at least a local site and remote site. 
     
     
         14 . The method of  claim 12 , wherein the at least one quality of service metric comprises a bandwidth metric, a packet loss metric, a packet latency, and a packet corruption metric. 
     
     
         15 . The method of  claim 12 , wherein the predicting comprises a prediction technique selected from the group consisting of a linear predication algorithm and a nonlinear prediction algorithm. 
     
     
         16 . The method of  claim 12 , wherein the predicting comprises a prediction technique selected from the group consisting of a set of linear prediction algorithms, Kalman prediction, and hidden Markov model prediction. 
     
     
         17 . The method of  claim 12 , wherein the live medical image video stream comprises one of an ultrasound video stream, an angiography video stream, and an endoscopy video stream. 
     
     
         18 . The method of  claim 12 , wherein the selecting comprises selecting from at least two different video compression protocols. 
     
     
         19 . The method of  claim 18 , wherein the at least two different video compression protocol include a MJPEG2000 compression protocol and at least one of MPEG-4, H.264, H.265, VP8, and VP9. 
     
     
         20 . The method of  claim 12 , wherein the selecting comprises selecting a subset of features of a particular video compression protocol. 
     
     
         21 . The method of  claim 20 , wherein the selecting a subset of features includes selecting at least one of:
 turning on or off the MVC encoding;   varying the block sizes of frames;   varying the quantization tables for intra-frame discrete cosine transform (DCT) compression;   varying motion vector compensation (MVC) for inter-frame compression, and reducing the stream frame rate by dropping frames ahead of the compression engine.   
     
     
         22 . The method of  claim 21 , further comprising selecting a transmission protocol based on the expected bit rate. 
     
     
         23 . The method of  claim 12 , further comprising analyzing quality of service metrics for a plurality of sessions and providing a network service recommendation. 
     
     
         24 . A non-transitory computer readable medium including instructions which when executed on a processor implement any one of the methods of  claim 12 ,  13 ,  14 ,  15 ,  16 ,  17 ,  18 ,  19 ,  20 ,  21 ,  22 , or  23 . 
     
     
         25 . A system, comprising:
 an ultrasound image scanner to generate a live video stream of ultrasonic medical images; and   a computer system to monitor network conditions in a network session to a remote site, predict a minimum bit rate, and select compression parameters to compress the live video stream prior to transmission to the remote site.