# US 2026/0063622 A1 · Method, system, and device for analyzing cellular properties with machine learning to identify states of senescence

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0063622 A1
- Document ID: US20260063622A1
- Status: Published application
- Kind: A1
- Application number: 19/270,119
- Filed: 2025-07-15
- Published: 2026-03-05
- Earliest claimed: 2024-07-15
- Assignees: New York University
- Applicants: New York University
- Inventors: Michael N. Wosczyna; Sahil Mapkar
- Web page: https://patentgrep.com/patent/US20260063622A1

## CPC

- G01N 33/5023: {on expression patterns}
- G01N 33/5061: {Muscle cells}
- G06V 10/273: {removing elements interfering with the pattern to be recognised}
- G06V 10/30: Noise filtering
- G06V 10/72: Data preparation, e.g. statistical preprocessing of image or video features
- G06V 10/763: {Non-hierarchical techniques, e.g. based on statistics of modelling distributions}
- G06V 20/695: {Preprocessing, e.g. image segmentation}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/776: Validation; Performance evaluation
- G06V 20/698: {Matching; Classification}
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A system, product, and method for analyzing cellular properties and nuclear geometries with machine learning such as unsupervised learning to identify senescence is described. The system, product, and method may include steps or operations including processing images comprising one or more animal cells; determining altered cellular properties associated with senescence of the one or more animal cells of the processed images by extracting: nuclear properties, non-nuclear properties, and functional properties of the animal cells; and determining senescence of the one or more cells by scoring the respective nuclei using unsupervised learning.

## Claims

### Claim 1

A nontransitory computer readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
obtaining at least one image comprising at least one animal cell;
pre-processing the at least one image;
segmenting the at least one pre-processed image to identify a region of the at least one image corresponding to a nucleus of the animal cell;
calculating at least one nuclear morphometric parameter of the animal cell from the region of the image;
providing the at least one nuclear morphometric parameter as an input to an unsupervised machine learning algorithm; and
calculating a senescence parameter of the at least one animal cell with the unsupervised machine learning algorithm.

### Claim 2 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the at least one animal cell comprises a cell of the group consisting of: a stem cell, a muscle stem cell, a mesenchymal stem cell, a mesenchymal stromal cell, a fibroadipogenic progenitor, a endothelial cell, a skeletal muscle cell, a cartilage cell, a chondrocyte, an immune cell, a myoblast, an adipocyte, a preadipocyte, an epithelial cell, and a hepatocyte.

### Claim 3 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the unsupervised machine learning algorithm comprises dimensional reduction.

### Claim 4 (depends on 3)

The nontransitory computer readable medium of claim 3, wherein the dimensional reduction comprises UMAP.

### Claim 5 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the unsupervised learning algorithm comprises cluster analysis.

### Claim 6 (depends on 5)

The nontransitory computer readable medium of claim 5, wherein the cluster analysis is based on a value k, wherein k is greater than 2 and k defines the number of groups, wherein the number of groups comprise at least a senescence cluster and non-senescence cluster corresponding to the one or more animal cells.

### Claim 7 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the at least one nuclear morphometric parameter is selected from the group consisting of: nuclear size, intensity of a nuclear stain, nuclear circularity, and dense foci.

### Claim 8 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the at least one nuclear morphometric parameter comprises nuclear size, intensity of a nuclear stain, nuclear circularity, and heterochromatic foci.

### Claim 9 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the pre-processing step comprises removing noise from the images using 3D deconvolution.

### Claim 10 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the pre-processing step comprises generating a binary image from the at least one image.

### Claim 11 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the senescence parameter comprises a senescence score.

### Claim 12 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the senescence parameter comprises assigning the at least one animal cell to one of a set of discrete groups.

### Claim 13 (depends on 12)

The nontransitory computer readable medium of claim 12, wherein the discrete groups are calculated based on k-means cluster analysis.

### Claim 14 (depends on 1)

The nontransitory computer readable medium of claim 1 wherein the at least one animal cell was treated with a nucleic acid marker.

### Claim 15 (depends on 14)

The nontransitory computer readable medium of claim 14, wherein the nucleic acid marker comprises DAPI.

### Claim 16 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the step of segmenting the at least one pre-processed image to identify the region of the at least one image corresponding to the nucleus of the animal cell comprises calculating a size, a circularity, or a blebbing of at least one segment of the pre-processed image.

### Claim 17 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the image is of a cell culture or a tissue sample.

### Claim 18 (depends on 1)

The nontransitory computer readable medium of claim 1, wherein the image is of a tissue section.

### Claim 19

A method of calculating a senescence score of at least one animal cell, comprising:
obtaining at least one image comprising at least one animal cell;
identifying a region of the at least one image corresponding to a nucleus of the animal cell;
calculating at least one nuclear morphometric parameter of the animal cell from the region of the image;
providing the at least one nuclear morphometric parameter as an input to an unsupervised machine learning algorithm; and
calculating a senescence parameter of the at least one animal cell with the unsupervised machine learning algorithm.

### Claim 20 (depends on 19)

A method of screening a drug candidate comprising the steps of:
providing a culture comprising one or more animal cells;
calculating a first set of senescence parameters of at least one animal cell of the one or more animal cells of the culture via the method of claim 19;
contacting a drug candidate to the culture;
calculating a second set of senescence parameters of at least one animal cell of the one or more animal cells of the culture via the method of claim 19; and
comparing the first set of senescence parameters to the second set of senescence parameters.
