Patient signal analysis based on affine template matching

• US 10,588,577 B2
• Filed: 01/29/2015
• Issued: 03/17/2020
• Est. Priority Date: 01/29/2015
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens Healthcare GMBH (Siemens AG)
• Inventors: Zhang, Hongxuan
• Primary Examiner(s): Wilson, Kaylee R
• Assistant Examiner(s): Shah, Jay B
• Application Number:
  US14/609,083
• Publication Number:
  US 20160220190A1
• Time in Patent Office: 1,874 Days
• Field of Search: None
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/02108 from analysis of pulse wave characteristics
• CPC Class Codes: A61B 5/026 Measuring blood flow A61B3/1233, A61B3/1241 take precedence
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/4836 Diagnosis combined with treatment in closed-loop systems or methods A61B5/0036 takes precedence
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7253 characterised by using transforms
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence

Abstract

Disclosed herein is a framework for facilitating patient signal analysis. In accordance with one aspect, the framework performs affine template matching of a region of interest from patient signal data with a baseline signal portion by performing an affine waveform transformation of the region of interest. One or more affine ratios may be determined based on the matched region of interest and the baseline signal portion for generating a report or diagnosis of a cardiac event.

Claims

1. A system for patient signal analysis, comprising:

a non-transitory memory device;

a processor device in communication with the memory device; and

a signal analysis unit stored in the memory device and operative with the processor device to perform steps including

receiving hemodynamic patient signal data acquired from a patient,

extracting a region of interest from the hemodynamic patient signal data,

performing affine template matching of the region of interest with a baseline signal portion by performing an affine waveform transformation of the region of interest,

determining one or more affine ratios based on the matched region of interest and the baseline signal portion, wherein each of the one or more affine ratios quantitatively characterizes a difference between the matched region of interest and the baseline signal portion, wherein the difference quantifies a cardiac pathology,

wherein determining the one or more affine ratios comprises determining an affine amplitude ratio in response to time durations of the matched region of interest and the baseline signal portion being similar,

wherein determining the one or more affine ratios comprises determining an affine timing ratio in response to amplitudes at a key point of the matched region of interest and the baseline signal portion being similar, and

controlling a medical treatment device based at least in part on the one or more affine ratios.

2. The system of claim 1 wherein the hemodynamic patient signal data comprises blood pressure data, blood flow sound data, oximetric signal data or cardiac sound data.

3. A method of patient signal analysis, comprising:

receiving, from a patient monitor, patient signal data;

extracting, by a processor device, a region of interest from the patient signal data;

performing, by the processor device, affine template matching of the region of interest with a baseline signal portion by performing an affine waveform transformation of the region of interest;

determining, by the processor device, one or more affine ratios based on the matched region of interest and the baseline signal portion, wherein each of the one or more affine ratios quantitatively characterizes a difference between the matched region of interest and the baseline signal portion, wherein the difference quantifies a cardiac pathology,

wherein determining the one or more affine ratios comprises determining an affine amplitude ratio in response to time durations of the matched region of interest and the baseline signal portion being similar,

wherein determining the one or more affine ratios comprises determining an affine timing ratio in response to amplitudes at a key point of the matched region of interest and the baseline signal portion being similar; and

controlling, by the processor device, a medical treatment device based at least in part on the one or more affine ratios.

4. The method of claim 3 further comprising selecting the baseline signal portion from the patient signal data.

5. The method of claim 3 wherein performing the affine waveform transformation comprises stretching or shrinking a first time duration of the region of interest.

6. The method of claim 3 wherein performing the affine waveform transformation further comprises stretching or shrinking amplitudes of the region of interest to synchronize a first key point of the region of interest with a second said key point of the baseline signal portion.

7. The method of claim 6 wherein the first and second key points comprise a maximum amplitude point, a minimum amplitude point, a mean amplitude point, a peak amplitude point, an end-of-diastolic phase point or an end-of-systolic phase point.

8. The method of claim 3 wherein performing the affine waveform transformation further comprises stretching or shrinking the region of interest until waveform areas under the region of interest and the baseline signal portion match.

9. The method of claim 3 wherein determining the affine amplitude ratio comprises determining a ratio of a sum of amplitudes extracted from the baseline signal portion and a sum of amplitudes extracted from the matched region of interest.

10. The method of claim 9 wherein the amplitudes are extracted from one or more waveform key points of the baseline signal portion and the matched region of interest.

11. The method of claim 10 wherein the one or more waveform key points comprise a maximum amplitude point, a mean amplitude point, a peak amplitude point, an end-of-diastolic phase point or an end-of-systolic phase point.

12. The method of claim 9 wherein the amplitudes are extracted from continuous waveform data points of the baseline signal portion and the matched region of interest.

13. The method of claim 3 wherein determining the affine timing ratio comprises determining a ratio of time durations extracted from the baseline signal portion and the matched region of interest.

14. The method of claim 3 wherein determining the one or more affine ratios comprises determining an affine shape morphology ratio based on time durations and amplitudes extracted from continuous data points of the baseline signal portion and the matched region of interest in response to the time durations and the amplitudes of the matched region of interest and the baseline signal portion being varying, wherein determining the affine shape morphology ratio comprises integrating the affine amplitude ratio and the affine timing ratio.

15. The method of claim 3 wherein determining the one or more affine ratios comprises determining an affine template key point based discrete summary ratio based on time durations and amplitudes extracted from key points of the baseline signal portion and matched region of interest.

16. The method of claim 3 wherein determining the one or more affine ratios comprises determining an affine template energy ratio based on areas covered by waveforms of the baseline signal portion and the matched region of interest.

17. The method of claim 3 further comprising determining a weighted summation of multiple affine ratios to generate a summary ratio and outputting a report based on the summary ratio.

18. The method of claim 3 further comprising determining one or more statistical parameters based on multiple affine ratios and outputting a report based on the one or more statistical parameters.

19. A non-transitory computer readable medium embodying a program of instructions executable by machine to perform steps for patient signal analysis, the steps comprising:

receiving, from a patient monitor, patient signal data;

extracting, by a processor device, a region of interest from the patient signal data;

performing, by the processor device, affine template matching of the region of interest with a baseline signal portion by performing an affine waveform transformation of the region of interest;

determining, by the processor device, one or more affine ratios based on the matched region of interest and the baseline signal portion, wherein each of the one or more affine ratios quantitatively characterizes a difference between the matched region of interest and the baseline signal portion, wherein the difference quantifies a cardiac pathology,

wherein determining the one or more affine ratios comprises determining an affine amplitude ratio in response to time durations of the matched region of interest and the baseline signal portion being similar,

wherein determining the one or more affine ratios comprises determining an affine timing ratio in response to amplitudes at a key point of the matched region of interest and the baseline signal portion being similar; and

controlling a medical treatment device based at least in part on the one or more affine ratios.