Comparing images

Análisis de imágenes biomédicas en Python

Stephen Bailey

Instructor

Comparing images

both-images-and-stacked

Summary metrics

Goal: define a metric of similarity between two images.

Cost functions produce metrics to be minimized.

Objective functions produce metrics to be maximized.

Mean absolute error

import imageio.v2 as imageio
import numpy as np
i1=imageio.imread('OAS1035-v1.dcm')
i2=imageio.imread('OAS1035-v2.dcm')

err = i1 - i2

plt.imshow(err)

mask-error

abs_err = np.abs(err)
plt.imshow(abs_err)

mae = np.mean(abs_err)
mae

29.8570

mask-abs-error

Mean absolute error

Goal: minimize the cost function

# Improve im1 alignment to im2
xfm=ndi.shift(im1, shift=(-8, -8))
xfm=ndi.rotate(xfm, -18,
                 reshape=False)

# Calculate cost
abs_err = np.abs(im1 - im2)
mean_abs_err = np.mean(abs_err)

mean_abs_err

13.0376

adjusted-overlay

Intersection of the union

$$ IOU = \frac{I_1 \cap I_2 }{I_1 \cup I_2}$$

mask1 = im1 > 0
mask2 = im2 > 0

intsxn = mask1 & mask2
plt.imshow(intsxn)

mask-intersection

union = mask1 | mask2
plt.imshow(union)

iou = intsxn.sum() / union.sum()
iou

0.68392

mask-union

Let's practice!

Análisis de imágenes biomédicas en Python