Biomedicinsk bildanalys i Python
Stephen Bailey
Instructor
Mål: definiera ett likhetsmått mellan två bilder.
Kostnadsfunktioner ger mått som ska minimeras.
Målfunktioner ger mått som ska maximeras.
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)
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)
abs_err = np.abs(err) plt.imshow(abs_err) mae = np.mean(abs_err) mae
abs_err = np.abs(err) plt.imshow(abs_err)
mae = np.mean(abs_err) mae
29.8570
Mål: minimera kostnadsfunktionen
# 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
# 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
$$ IOU = \frac{I_1 \cap I_2 }{I_1 \cup I_2}$$
mask1 = im1 > 0 mask2 = im2 > 0 intsxn = mask1 & mask2 plt.imshow(intsxn)
mask1 = im1 > 0 mask2 = im2 > 0
intsxn = mask1 & mask2 plt.imshow(intsxn)
union = mask1 | mask2 plt.imshow(union) iou = intsxn.sum() / union.sum() iou
union = mask1 | mask2 plt.imshow(union)
iou = intsxn.sum() / union.sum() iou
0.68392
Preparing Video For Download...
