Find heart rate using ecg imaage

I want to calculate heart rate & QRS vales using ecg image. This is my ecg image.

First i convert this photo to black and white using this code.This my Black & White photo.

Then i plot this black & white photo to extract values.This is code for plot.

---------------------------------------------------------------------------------------------

IM = imread('bin_ecgm.png'); %IM = rgb2gray(IM); IM = double(IM);

% Over sample 8 times in horizontal direction % Amount to oversample is determined by maximum slope, e.g. if max slope is % 16, oversample by 16. IM2 = interp2(IM,linspace(1,size(IM,2),size(IM,2)*8),linspace(1,size(IM,1),size(IM,1))');

% Calculate shortest path using 255 - image intensity as energy function [spath,senergy,slastindex,im] = shortestPath(255-IM2',255,0,1,100);

% Down sample path to account for original oversampling p_x = 1:size(IM2,2); p_x = p_x ./ 8; p_y = spath(:,2);

% Plot on top of original image imagesc(IM); colormap gray; hold on; plot(p_x,p_y,'r'); hold off;

-----------------------------------------------------------------------------------

    function [ p, e, l, im ] = shortestPath( m, opt, a, ax, bx  )
%SHORTESTPATH Summary of this function goes here
%   Detailed explanation goes here

%Get size of matrix [sy, sx] = size(m); im = zeros(sy,sx);

%Convert to value different from optimal value = abs(opt - m);

%Preallocate index matrix and energy matrix lastindex = zeros(sy, sx); energy = zeros(sy, sx);

%Initialise first rows energy(1,:) = value(1,:); lastindex(1,:) = 1:sx;

%Initialise temp matrix t = zeros(1,3);

%Loop through remaining rows for row = 2:sy for col = ax:bx %Get the last energies and current values if col == ax t = [inf energy(row-1,col:(col+1))]; cv = [inf value(row,col:(col+1))]; elseif col == bx t = [energy(row-1,(col-1):col) inf]; cv = [value(row,(col-1):col) inf]; else t = energy(row-1,(col-1):(col+1)); cv = value(row,(col-1):(col+1)); end

        %Add energy for moving
        t = t + [a 0 a];

        %Add energy from difference from optimum
        t = t + cv;

        %Find minimum
        [v,i] = min(t);

        %Save new values
        energy(row,col) = v;
        lastindex(row,col) = col + i - 2;

    end
end

[v,li] = min(energy(sy,ax:bx)); li = ax + li - 1; p(sy,:) = [sy li]; im(sy,li) = 1; for row = (sy-1):-1:1 i = lastindex(row,li); p(row,:) = [row,i]; im(row,i) = 1; li = i; end

e = energy; l = lastindex;

end

 ----------------------------------------------------------------------------------

any one know how to do this.

Answer 1

[Image Analyst]

First of all, use a flatbed scanner instead of a camera so you don't get the specular reflection of the flash in the image, and you'll get a better image of the black line. Then simply draw a black line across, cutting across the peaks. Then call imfill(), bwconncomp(), and regionprops() to get the centroids.

binaryImage = grayImage < 200; % Or whatever you did.
binaryImage(150, :) = true; % Draw a line across at line 150 or whatever.
binaryImage = imfill(binaryImage, 'holes'); % Fill in the peaks to make solid triangles.
cc = bwconncomp(binaryImage);
measurements = regionprops(cc, 'Centroid');
centroids = [measurements.Centroid];
xCentroids = centroids(1:2:end);  % Location of the peak centers horizontally.

xCentroids is in units of pixels. Then convert that to seconds by your spatial calibration where you know how many pixels corresponds to how many seconds, which you can get by measuring the number of pixels between the brown grid lines.

[Anupa]

after these things how detect QRS values

Answer 2

[Star Strider]

Objective: (Probably) Lead II EKG rhythm strip. Normal sinus rhythm, Rate 75, PR = 0.16 s, QRS = 0.10 s, QT = 0.42 s (QTc = 0.47 s). QRS amplitude 9 mv.

Impression: Abnormal EKG: (1) Significant QT prolongation; (2) Low T-wave amplitude suggestive of hypokalemia. No evidence of infarct or ischaemia.

----------

If you’re going to calculate anything from a paper EKG tracing, you also have to segment the time and voltage gridlines, if not in the same EKG image, then a corresponding one. Without those references, any EKG tracing is just a squiggle. I did a PubMed search on this just now, and it seems no one has done this, likely because there is no need for it. Even computer-interpreted EKG tracings are all reviewed by someone with expertise in reading them.

[Image Analyst]

We get these kinds of questions often. What I can't figure out is why they need to go off the paper strip. Don't the ecg instruments make the signal available in a digital file?

[Star Strider]

They do, and now that most hospitals and physicians’ offices have Internet connections, are downloaded to a central database as electronic records. I found this article ‘Distilling Clinically Interpretable Information from Data Collected on Next-Generation Wearable Sensors’ interesting (if slightly unnerving, in light of Edward Snowden’s revelations). Paper strips are used primarily for backup and immediate reading. I suspect that with the proliferation of tablet computers, paper will become progressively less relevant. There was an article in one of my professional newsletters mentioning that portable ultrasound (it didn’t mention the mode) would soon be used as frequently as the stethoscope. I assume this at least refers to Doppler units, but could also refer to imaging. If so, the software necessary to assist in interpreting it (segmentation by density, pseudocolor velocity depictions, etc.) are likely to become increasingly more important. A couple decades ago, I thought the Medical Tricorder and Warp Speed travel both about as improbable. I’m not so sure about the Tricorder now.

[Anupa]

is there any method to do this using ecg images.

[Image Analyst]

He just said that you should be able to get the signal and not have to work off the chart image. Can you get the signal in digital form? If not, why not?