Automatic ultrasound titration of continuous positive airway pressure (CPAP) treatment for sleep apnea
View Patent ↗Techniques for automated titration of CPAP device for a subject include receiving multiple ultrasound images representing a cross section of an airway in a neck of the subject at corresponding different times. Multiple different positive pressure values imposed by a device on the airway of the subject are also received at each of the corresponding times. For each of the ultrasound images, a mask of pixels associated with an air-tissue interface is automatically formed, and a value of a statistic of pixels within the mask is automatically determined. A titration pressure for a continuous positive airway pressure (CPAP) device is automatically determined based on the positive pressures and the value of the statistic for each of the ultrasound images. Output data that indicates the titration pressure for the CPAP device is presented on a display device, such as by operating the CPAP device itself at the titration pressure.
1. A method implemented on a processor comprising:
automatically receiving a first plurality of ultrasound images representing a cross sections of an airway in a neck of a subject obtained by an ultrasound transducer array directed toward the subject at a corresponding plurality of different times;
determining a region of interest comprising a subset of pixels of each image of the first plurality of ultrasound images, wherein each region of interest encompasses an airway of the subject;
for each of the plurality of images, automatically forming a mask of pixels associated with an air-tissue interface based on both a morphological opening and a morphological closing with a structural element in the region of interest if the mask includes at least a minimum number of pixels;
for each of the plurality of images, automatically determining a value of a statistic of pixels within the mask;
presenting on an display device output data that indicates a degree of airway patency proportional to the value of the statistic at each of the corresponding plurality of different times.
2. A method as recited in claim 1 , wherein the statistic is mean intensity value within the mask.
3. A method as recited in claim 1 , wherein the statistic is a number of pixels within the mask.
4. A method as recited in claim 1 , wherein the statistic is a number of pixels having an intensity above a minimum intensity within the mask.
5. A method as recited in claim 1 , wherein the minimum number of pixels is 20.
6. A method as recited in claim 1 , wherein the structural element is diamond shaped.
7. A computer-readable medium carrying one or more sequences of instructions, wherein execution of the one or more sequences of instructions by one or more processors causes the one or more processors to perform the steps of:
automatically receiving a first plurality of ultrasound images representing a cross sections of an airway in a neck of a subject obtained by an ultrasound transducer array directed toward the subject at a corresponding plurality of different times;
determining a region of interest comprising a subset of pixels of each image of the first plurality of ultrasound images, wherein each region of interest encompasses an airway of the subject;
for each of the plurality of images, automatically forming a mask of pixels associated with an air-tissue interface based on both a morphological opening and a morphological closing with a structural element in the region of interest if the mask at least a minimum number of pixels;
for each of the plurality of images, automatically determining a value of a statistic of pixels within the mask;
presenting on an display device output data that indicates a degree of airway patency proportional to the value of the statistic at each of the corresponding plurality of different times.
8. A system comprising:
at least one processor; and
at least one computer-readable medium including one or more sequences of instructions,
the at least one computer-readable medium and the one or more sequences of instructions configured to, with the at least one processor, cause the system to perform at least the following,
automatically receiving a first plurality of ultrasound images representing a cross sections of an airway in a neck of a subject obtained by an ultrasound transducer array directed toward the subject at a corresponding plurality of different times;
determining a region of interest comprising a subset of pixels of each image of the first plurality of ultrasound images, wherein each region of interest encompasses an airway of the subject;
for each of the plurality of images, automatically forming a mask of pixels associated with an air-tissue interface based on both a morphological opening and a morphological closing with a structural element in the region of interest if the mask at least a minimum number of pixels;
for each of the plurality of images, automatically determining a value of a statistic of pixels within the mask;
presenting on an display device output data that indicates a degree of airway patency proportional to the value of the statistic at each of the corresponding plurality of different times.