Method and System for Acquisition of Fluorescence Images of Live-cell Biological Samples

A method for training a neural network to generate a two-dimensional projection image of a fluorescence image of a three-dimensional live-cell sample, comprising the steps of:

• (a) obtaining a training set in the form of a multitude of images, wherein the images comprise:
• (1) one or more long exposure images of the three-dimensional live-cell training sample obtained by moving a focal plane of a camera through the training sample in a Z direction, the camera thereby integrating fluorescence intensity from the training sample over a Z-dimension, and
• (2) a ground truth image, wherein the ground truth image is obtained from a set images obtained at a different Z focal plane position of the training sample and combined using a projection algorithm into a two-dimensional projection image;
• and
• (b) conducting a model training procedure using the training set to generate a trained neural network.

A live-cell imaging system for use in conjunction with a sample holding device adapted for holding a three-dimensional sample to generate a two-dimensional projection image of the sample, comprising:

• a fluorescence microscope having one or more excitation light sources, one or more objective lenses, and a camera operable to obtain one or more fluorescence images from the three-dimensional sample held within the sample holding device,
• wherein the fluorescence microscope includes a motor system configured to move the fluorescence microscope relative to the sample holding device in a Z direction such that the camera obtains one or more long exposure images of the sample, the images obtained by moving a focal plane of the camera through the sample in the Z direction;
• and
• a processing unit including a trained neural network model for generating the two-dimensional projection image of the three-dimensional sample from the one or more long exposure images.

A method for generating a training set for training a neural network, comprising the steps of:

• (a) with a camera, acquiring one or more long exposure fluorescence images of a three-dimensional training sample by moving a focal plane of the camera through the sample in a Z direction, the camera thereby integrating fluorescence intensity from the sample over a Z-dimension;
• (b) generating a ground truth image of the same training sample from one or more different images of the training sample obtained by the camera;
• (c) repeating steps (a) and (b) for a multitude of different training samples;
• and
• (d) supplying the images acquired by performing steps (a), (b) and (c) as a training set for training a neural network.