COMPUTERIZED SYSTEMS AND METHODS FOR DETECTING FEATURES IN ELECTRONIC IMAGES
Disclosed herein, inter alia, are systems and methods for extracting features from sequencing images using machine learning, involving the construction of a kernel bank to handle variations in imaging conditions, compressing extracted vector intensities into super intensity vectors, and improving basecalling accuracy and robustness to misfocus and aberrations.
1 . A computer-implemented method for extracting features of sequencing images, comprising:
extracting vector intensities, using at least a machine learning model trained on a set of sequencing images generated from a plurality of imaging systems, of an image patch of the sequencing images; and
compressing, using at least the machine learning model, the vector intensities into a plurality of super intensity vectors.
2 . The method of claim 1 , further comprising inputting the super intensity vectors into a base caller.
3 . The method of claim 1 , wherein the sequencing images of the image patch are aligned across successive cycles and spectral channels.
4 . The method of claim 1 , wherein the image patch is arranged around each extracted feature.
5 . The method of claim 1 , wherein the plurality of super intensity vector represents optimally-extracted signals of a wavelength channel of the image patch.
6 . The method of claim 5 , further comprising generating the plurality of super intensity vectors for each wavelength channel by convolving the aligned image patches with a bank of kernels.
7 . The method of claim 6 , wherein each kernel mimics an expected optical point-spread function.
8 . The method of claim 6 , further comprising:
constructing a different kernel bank for each wavelength channel, wherein each different kernel bank corresponds to a predominant wavelength of the wavelength channel; and
expanding the different kernel banks to include copies with different subpixel translations based on a previously calculated feature location.
9 . The method of claim 6 , wherein each of the kernels are constructed based on an assumed optical numerical aperture.
10 . The method of claim 9 , wherein the assumed optical numerical aperture is at least one of 0.4, 0.6, 0.8, and 1.0.
11 . The method of claim 9 , further comprising: creating a high-resolution Airy disk for each numerical aperture thereby creating a series of Airy disks of different widths.
12 . The method of claim 11 , further comprising surrounding each Airy disk by a hexagonal ring.
13 . The method of claim 11 , further comprising calculating a pseudo-inverse of a pattern created by each Airy disk; and
downsampling the pseudo-inverse to a true pixel pitch, resulting in a kernel that mimics a point spread function with depressions for nearest neighbor crosstalk suppression.
14 . The method of claim 1 , wherein the compressing the extracted vector intensities comprises:
projecting, using at least a linear transformation, the extracted vector intensities of the image patch into an embedding; and
passing the embedding through a plurality of activation functions and a plurality of linear transformations into the plurality of super intensity vectors.
15 . The method of claim 14 , further comprising: analyzing, using at least the machine learning model, each extracted feature of the image patch independent of other features of the image patch.
16 . A computer-implemented method for extracting features of an image, comprising:
constructing a kernel bank comprising learned linear combinations of a set of precomputed two-dimensional basis vectors trained simultaneously with a machine learning nonlinear extraction network that is trained on a set of sequencing images generated from a plurality of imaging systems; and
pre-computing, using at least the machine learning nonlinear extraction network, a set of optimal linear combinations.
17 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, perform a method for analyzing a tissue sample, the method comprising:
extracting vector intensities, using at least a machine learning model trained on a set of sequencing images generated from a plurality of imaging systems, of an image patch of the sequencing images; and
compressing, using at least the machine learning model, the vector intensities into a plurality of super intensity vectors.
18 . A system for analyzing a tissue sample, the system comprising:
(a) a memory storing instructions;
(b) a processor configured to execute the instructions to:
extracting vector intensities, using at least a machine learning model trained on a set of sequencing images generated from a plurality of imaging systems, of an image patch of the sequencing images; and
compressing, using at least the machine learning model, the vector intensities into a plurality of super intensity vectors.