Figure 1
Confocal fluorescence image of Iba-1 labelled microglial cells in APPswe/PS1dE9 mouse brain tissue (a) and segmented image (b). ImageJ sample image leaf.jpeg (c) and segmented image (d).
Figure 2
Confocal fluorescence image of MOAB2 labelled amyloid-β pathology in APPswe/PS1dE9 mouse brain tissue with sparse annotations for signal (red) and background (blue) (a) and resulting segmentation (b).
Figure 3
Confocal fluorescence image of MOAB2 labelled amyloid-β pathology in APPswe/PS1dE9 mouse brain tissue with image filters applied. Maximum (a), mean (b), median (c), minimum (d), range (e), standard deviation (f), locally scaled intensity (g), Gaussian (h), entropy (i), difference from mean (j), difference from median (k) and difference from Gaussian (l) filters at radii 3, 17 and 65 pixels. Difference-of-Gaussians at 3/17, 17/65, and 33/65 pixels (j). Difference-of-entropy for 3/17, 17/65, and 33/65 pixels (k).
Figure 4
ImageSURF menu options.
Figure 5
ImageSURF classifier settings dialog with default options.
Figure 6
ImageSURF filter selection dialog with example filters selected.
Figure 7
ImageSURF classifier training dialog with example settings.
Figure 8
ImageSURF training examples. Confocal fluorescence images of MOAB2 labelled amyloid-β pathology in APPswe/PS1dE9 mouse brain tissue (a). Segmented training images (b) and merged image (c) using the ImageJ Merge Channels tool to display the segmented signal pixels as transparent red and background as transparent blue.
Figure 9
ImageSURF pixel classifier training workflow. A representative set of sub-images are selected and cropped from the full image set and sparsely annotated as signal or background using a bitmap image software package. The sub-images and annotations are used as the input to train an ImageSURF classifier which is them applied back to the input sub-images. The accuracy of the sub-image segmentations is manually verified and the annotation training and verification processes repeated until the sub-image segmentation is accurate. Once the trained classifier has been verified as accurate, it can be applied to any image set of which the training set is representative.