Segmenting lung nodules from Chest X-ray images

This is my code. It is almost accurately segmenting out the lung regions from chest x-ray images. But i need to write a logic that also segments out those blobs only that are candidate nodules. I also have ground truth for the nodule's size and location in the image.

clear; clc; close all;

%% Loading images

Threshold = 36;

raw_x_ray='JPCLN014.png';

I=imread(raw_x_ray);

figure(101);

imshow(I);

colormap(gray);

title('Grayscale X-Ray');

I=wiener2(I, [5 5]);

figure(102);

subplot(2,1,1);

imshow(I);

subplot(2,1,2);

imhist(I, 256);

a_thresh = I >= Threshold; % set this threshold

[labelImage, numberOfBlobs] = bwlabel(a_thresh);

props = regionprops(a_thresh,'all');

sortedSolidity = sort([props.Solidity], 'descend');

SB = sortedSolidity(1);

if SB == 1

binaryImage = a_thresh; figure(103);

imshow(binaryImage); colormap(gray);

The image needs to be flipped first. Nodule's size is 20mm for this image, (569,717) are the coordinates, the nodule is in the right upper lobe (S3) and is malignant (lung cancer diagnosed).

Answer 1

[Image Analyst]

Go here for published algorithms:

http://www.visionbib.com/bibliography/contentsmedical.html#Medical%20Applications,%20CAT,%20MRI,%20Ultrasound,%20Heart%20Models,%20Brain%20Models