Skip to main content
[Preprint]. 2024 Sep 24:2024.05.15.594372. [Version 2] doi: 10.1101/2024.05.15.594372

Figure 2. NFT point-to-mask pipeline detail.

Figure 2.

A) We convert ROIs with human NFT point annotations to detailed segmentation masks. We do so by B) generating 400×400 pixel tiles centered on the label, C) applying color deconvolution, otsu thresholding, and morphological cleaning operations, and D) performing blob detection with center-biasing and size filtering to obtain a mask. E) We then stitch each mask into its corresponding location in the ROI via union operations.