Unsupervised cell segmentation by fast Gaussian Processes
This provides an unsupervised solution for biologists analyzing cell behaviors from noisy microscopy images, addressing limitations of supervised tools that rely on labeled data.
The paper tackles the problem of cell segmentation in microscopy images without requiring labeled data or parameter tuning, using fast Gaussian processes and adaptive thresholding to achieve scalable and accurate results compared to existing methods.
Cell boundary information is crucial for analyzing cell behaviors from time-lapse microscopy videos. Existing supervised cell segmentation tools, such as ImageJ, require tuning various parameters and rely on restrictive assumptions about the shape of the objects. While recent supervised segmentation tools based on convolutional neural networks enhance accuracy, they depend on high-quality labeled images, making them unsuitable for segmenting new types of objects not in the database. We developed a novel unsupervised cell segmentation algorithm based on fast Gaussian processes for noisy microscopy images without the need for parameter tuning or restrictive assumptions about the shape of the object. We derived robust thresholding criteria adaptive for heterogeneous images containing distinct brightness at different parts to separate objects from the background, and employed watershed segmentation to distinguish touching cell objects. Both simulated studies and real-data analysis of large microscopy images demonstrate the scalability and accuracy of our approach compared with the alternatives.