Predicting total nucleic acid yield and dissection boundaries for histology slides

Patent metadata

Field	Value
Publication number	US-11348661-B2
Application number	US-202017139765-A
Country	US
Kind code	B2
Filing date	Dec 31, 2020
Priority date	May 14, 2018
Publication date	May 31, 2022
Grant date	May 31, 2022

Abstract

A method for qualifying a specimen prepared on one or more hematoxylin and eosin (H&E) slides by assessing an expected yield of nucleic acids for tumor cells and providing associated unstained slides for subsequent nucleic acid analysis is provided.

First claim

What is claimed:

1. A computer-implemented method for qualifying a specimen prepared on one or more hematoxylin and eosin (H&E) slides and for providing associated unstained slides for nucleic acid analysis, the method comprising:
generating a digital image of each of the one or more H&E slides prepared from the specimen at an image-based nucleic acid yield prediction system having one or more processors; and
for each digital image:
identifying, using the one or more processors, tumor cells of the H&E slide from the digital image;
generating a tumor area mask based at least in part on the identified tumor cells, wherein the tumor area mask defines a dissection boundary of the H&E slide associated with the digital image;
predicting an expected yield of nucleic acid for the tumor cells within the dissection boundary, by providing the digital image to a machine learning model trained on a plurality of H&E slides having labeled dissection boundaries and labeled total nucleic yield; and
providing one or more of the associated unstained slides for nucleic acid analysis when the summation of expected yield of nucleic acid predicted for each digital image exceeds a predetermined threshold.

2. The method of claim 1 , wherein only associated unstained slides with the H&E slides having predicted expected yield of nucleic acid exceeding a slide yield threshold are included in the summation.

3. The method of claim 1 , wherein providing the associated unstained slides for nucleic acid analysis comprises sending the associated unstained slides to a third party for sequencing.

4. The method of claim 1 , wherein providing the associated unstained slides for nucleic acid analysis comprises sequencing the nucleic acids extracted from within the dissection boundary identified from the H&E slides.

5. The method of claim 1 , wherein the predetermined threshold is based at least in part on one or more specification requirements.

6. The method of claim 5 , wherein specification requirements are based on a minimum surface area within the dissection boundary.

7. The method of claim 5 , wherein specification requirements are based on a minimum cell count within the dissection boundary.

8. The method of claim 5 , wherein specification requirements are based on a minimum cell density within the dissection boundary.

9. The method of claim 5 , wherein specification requirements are set by an entity.

10. The method of claim 1 , wherein the predetermined threshold is within a range between and including 50 ng-2000 ng.

11. The method of claim 1 , wherein predicting the expected yield of nucleic acid for the tumor cells within the dissection boundary further comprises:
counting the number of tumor cells identified within the dissection boundary and multiplying the count by a tumor cell average nucleic acid yield.

12. The method of claim 1 , wherein predicting the expected yield of nucleic acid for the tumor cells within the dissection boundary further comprises:
calculating the surface area of the dissection boundary and multiplying the surface area by a dissection boundary average nucleic acid yield.

13. The method of claim 1 , wherein the dissection boundary is a microdissection boundary.

14. The method of claim 1 , wherein the dissection boundary is a macrodissection boundary.

15. The method of claim 1 , wherein the dissection boundary is a whole slide boundary.

16. The method of claim 1 , wherein identifying the tumor cells of the H&E slide from the digital image comprises identifying the tumor cells using a trained cell segmentation model.

17. The method of claim 16 , wherein identifying the tumor using the trained cell segmentation model comprises:
applying, using the one or more processors, a plurality of tile images formed from the digital image to the trained cell segmentation model and, for each tile, assigning a cell classification to one or more pixels within the tile image.

18. The method of claim 17 , wherein assigning the cell classification to one or more pixels within the tile image comprises:
identifying, using the one or more processors, the one or more pixels as a cell interior, a cell border, or a cell exterior and classifying the one or more pixels as the cell interior, the cell border, or the cell exterior.

19. The method of claim 16 , wherein the trained cell segmentation model is a pixel-resolution three-dimensional UNet classification model trained to classify a cell interior, a cell border, and a cell exterior.

20. The method of claim 16 , wherein identifying the tumor cells using the trained cell segmentation model comprises:
applying, using the one or more processors, each of a plurality of tile images formed from the digital image to the trained cell segmentation model; and
performing, using the one or more processors, a registration on segmented cells in each of the tile images by determining a cell border of each cell, determining a centroid of each cell, and shifting coordinates of centroids to a universal coordinate space for the digital image.

21. The method of claim 16 , wherein the trained cell segmentation model is trained using a set of H&E slide training images annotated with identified cell borders, identified cell interiors, and identified cell exteriors.

22. The method of claim 1 , further comprising superimposing, using a viewer, the tumor area mask over the digital image to visually indicate to a user which tumor cells to scrape.

23. The method of claim 1 , wherein generating the tumor area mask further comprises providing the digital image of the H&E slide to a model trained on a plurality of H&E slides having dissection labels.

24. A system comprising a pathology slide scanner system configured to perform the method of claim 1 .

25. The system of claim 24 , wherein the pathology slide scanner system is communicatively coupled to an image-based tumor cells prediction system through a communication network for providing the one or more of the associated unstained slides for nucleic acid analysis when the summation of expected yield of nucleic acid predicted for each digital image exceeds the predetermined threshold.

26. The method of claim 1 , wherein the one or more processors are one or more graphics processing units (GPUs), tensor processing units (TPUs), and/or central processing units (CPUs).

27. The method of claim 1 , wherein the expected yield of nucleic acid is confirmed through sequencing the tumor cells within the dissection boundary.

28. The method of claim 27 , where sequencing is next-generation sequencing.

29. The method of claim 27 , where sequencing is short-read sequencing.

Assignees

• Tempus Labs Inc

Inventors

• Yip Stephen
• Ho Irvin
• Sha Lingdao
• Osinski Boleslaw
• Khan Aly Azeem
• Kruger Andrew J
• Carlson Michael
• Greenwald Abel
• Willis Caleb
• Westley Andrew
• Jones Ryan
• Mahon Brett

Classifications

• G06T1/20 Primary

  Processor architectures; Processor configuration, e.g. pipelining · CPC title

• G06V10/774

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06V20/698

  Matching; Classification · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06V10/82

  using neural networks · CPC title