Data
The data itself are grayscale 8-bit images taken with DIC optics of cilia biopsies published in this 2015 study. For each video, you are provided 100 subsequent frames, which is roughly equal to about 0.5 seconds of real-time video (the framerate of each video is 200 fps). Since the videos are grayscale, if you read a single frame in and notice its data structure contains three color channels, you can safely pick one and drop the other two. Same goes for the masks. Speaking of the masks: each mask is the same spatial dimensions (height, width) as the corresponding video. Each pixel, however, is colored according to what it contains in the video:
- 2 corresponds to cilia (what you want to predict!)
- 1 corresponds to a cell
- 0 corresponds to background (neither a cell nor cilia)
- On the Left is single frame from the grayscale video.
- On the Right is the 3-label segmentation of the video (0: background, 1: cell, 2: cilia). The “cilia” label is what we’re interested in for this project and will be the label
- Below is the gif version of the cilia movement if you look closely you will find the hair like things moving
