UMassLMF.DEV

Image Operations

Generic selectors
Exact matches only
Search in title
Search in content
Post Type Selectors
Add (Image x Image)Added image’s own DAPI component. Might be useful for emphasizing nuclei/filaments while still showing other elements.
A close up of a purple and black background Description automatically generated with medium confidenceA purple and blue background Description automatically generated with medium confidence
Subtract (Image x Image)Subtracted image’s own DAPI component after splitting RGB into separate channels. DAPI was subtracted from blue (subtracting from RGB resulted in a black image).
A close up of a purple and black background Description automatically generated with medium confidenceA red and black background Description automatically generated
Multiply (Image x Image)Multiplied by image’s own DAPI component, resulted in a dimmed version of the DAPI channel with only blue in the histogram. May be useful for isolating components while also denoising.
A close up of a purple and black background Description automatically generated with medium confidenceBlue dots in the dark Description automatically generated
Divide (Image x Image)Divided image by its own DAPI channel, which resulted in an entire image of pixels with RGB (0,0,1). Applied Auto Contrast afterwards to emphasize the result. Not sure this option has many applications. Suppose you could divide by a grid to get gridlines? Images have to be the same size to use divide.
A close up of a purple and black background Description automatically generated with medium confidenceA blue square with small dots Description automatically generated
MinimumTakes the minimum of the input images. Used the FITC component of the original image, which resulted in the blue component being removed. May be useful for a timelapsed sequence of images to highlight changes between frames.
A close up of a purple and black background Description automatically generated with medium confidenceRed light on a black background Description automatically generated
MaximumTakes the maximum of the input images. Used a 20X portion of the original image, resulting in both 10X and 20X cells appearing.
A close up of a purple and black background Description automatically generated with medium confidenceA purple and black background Description automatically generated with medium confidence
CovarianceFinds covariance between images of each pixel. Probably best for grayscale images. Used the DAPI channel of the original image as the other input, which resulted in high FITC signal areas having lower covariance of red. Output is a float image with values for each color channel.
A close up of a purple and black background Description automatically generated with medium confidenceA yellow and green background Description automatically generated
Mask ImageRemoves parts of an image not covered by a binary. Detected background and operation removed cells.
Remove ShadingPerforms a shading correction on the first image specified by the second image. Worked like Divide but with higher resultant intensity (did not increase contrast here) when correcting original image by its own DAPI component.
A close up of a purple and black background Description automatically generated with medium confidenceA blue background with white lines Description automatically generated
Add (Image x Constant)Adds specified constant to R, G, and B values of each pixel. Used 50 here (meaning a pixel with 10/0/75 would become 60/50/125). It ended up desaturating the image, if higher values are used the image becomes closer to white.
A close-up of a cell Description automatically generatedA close-up of a purple background Description automatically generated
Subtract (Image x Constant)Subtracts specified constant from R, G, and B values of each pixel. This image had 0 for the green channel, so subtracting resulted in a negative value which showed up as a black screen. However, applying Abs to the result made the green values positive and the image visible. Subtracted 50 and then used Abs here.
­ A close-up of a cell Description automatically generatedA close up of a colorful pattern Description automatically generated with medium confidence
Multiply (Image x Constant)Multiplies R, G, and B values of each pixel by the specified constant. Used 5 here.
A close-up of a cell Description automatically generatedA purple and black background Description automatically generated
Divide (Image x Constant)Divides R, G, and B values of each pixel by the specified constant. Used 10 here.
A close-up of a cell Description automatically generatedA close up of a purple and black background Description automatically generated with medium confidence
ClipSets the R, G, and B values of each pixel to fall in between the specified bounds. Values within the bounds are unchanged, values lower than the min are set to the min, and values higher than the max are set to the max. Used bounds of 10 and 80, which would set a pixel with 113/0/61 to 80/10/61.
A close-up of a cell Description automatically generatedA purple and blue background Description automatically generated
Constant ValueSets R, G, and B values of each pixel to the specified constant, which just results in a uniform gray. Not sure this has many applications. Used a constant of 50.
A close-up of a cell Description automatically generatedA black rectangular object with white text Description automatically generated
AbsTakes the absolute value of each pixel’s RGB values. Useful if you have negative values after using something like Subtract (see above), has no effect if values are already all positive.
A close-up of a cell Description automatically generatedA close-up of a cell Description automatically generated
InvertSets RGB values to (max allowed intensity)-(original value), which inverts image colors.
A close-up of a cell Description automatically generatedA close-up of a white background Description automatically generated
ExpEach pixel’s RGB value is set to (specified base)^(original value). Results in very large RGB values. If original value causes result to exceed 32-bit float limit (on the order of 10^38), value is set to infinity and pixel is black. Used base 2 here-anything larger caused large parts of image to overflow.
A close-up of a cell Description automatically generatedA pink background with black spots Description automatically generated
InvEach pixel’s RGB value is set to its reciprocal (1/original value). Used auto contrast on the result to enhance visibility, but result is still quite dim.
A close-up of a cell Description automatically generatedA black and red background Description automatically generated
LogSets each pixel’s RGB value to log of specified base (original value). Used the default base of 10 here.
A close-up of a cell Description automatically generatedPurple and purple background with small flowers Description automatically generated with medium confidence
PowSets RGB value of each pixel to (original value)^(specified exponent). The default value of 2 did a good job at separating cells/sharpening the image, but noise reduction should still be used. Highly recommend this one!
A close-up of a cell Description automatically generatedA close up of a cell Description automatically generated
SignComputes the sign of each intensity value for each channel for every pixel (1 if positive, 0 if 0, -1 if negative). Since all R/B values were positive and all G values were 0, the result is a uniform magenta for the example image.
A close-up of a cell Description automatically generated
GreaterCompares intensity values from 2 channels and outputs a value of 1 if A > B or 0 if A ≤ B. Compared red to blue here. LUTs were adjusted to make result visible.
A close-up of a cell Description automatically generated
Greater or EqualCompares intensity values from 2 channels and outputs a value of 1 if A ≥ B or 0 if A < B. Compared blue to red here so it is approximately the inverse of the Greater example. LUTs were adjusted to make result visible.
A close-up of a cell Description automatically generated
EqualCompares intensity values from 2 channels and outputs a value of 1 if A == B or 0 if A != B. Compared red to blue here. LUTs were adjusted to make result visible. If input order is reversed, the same pixels are visible in the blue channel.
A close-up of a cell Description automatically generated
.Not E-qualCompares intensity values from 2 channels and outputs a value of 1 if A != B or 0 if A == B. Will probably make most of the image {1} values. Compared blue to red here. LUTs were adjusted to make result visible. If input order is reversed, the same pixels are visible in the blue channel. This node will produce the inverse of Equal.
A close-up of a cell Description automatically generated
BlendBlends a foreground image and a background image using a third image as weight. All images must have the same bit depth, pixel dimensions, and calibration. Used 3 images of cells here.
ConditionalTakes 3 channel inputs: a True layer, a False layer, and a Condition layer (shown). If the intensity value of the Condition layer is 0, the output of that pixel will be the corresponding pixel from the False layer. If the intensity value of the Condition layer is not 0, the output will be the corresponding pixel from the True layer (a brightfield image unlike the other 2 layers in this example so it is more visible). All inputs must have the same dimensions.