×

System for predicting the recurrence of cancer in a cancer patient

  • US 10,579,935 B2
  • Filed: 08/11/2019
  • Issued: 03/03/2020
  • Est. Priority Date: 03/20/2016
  • Status: Active Grant
First Claim
Patent Images

1. A method involving a system for predicting a risk of cancer recurrence in a patient, the method comprising:

  • (a) reading a portion of a digital image from a storage device, wherein the digital image was acquired by a digital camera imaging a tissue section removed from the patient, wherein the tissue section was immunohistochemically stained with a first stain marking M1 macrophages with a first color so that the digital image includes first color information, and with a second stain marking M2 macrophages a second color so that the digital image includes second color information;

    (b) using geometric region information to identify a region of the portion of the digital image;

    (c) detecting first and second objects in the portion of the digital image, wherein the detecting involves using the first color information, the second color information, a predefined object size lower threshold, and a predefined object size upper threshold;

    (d) counting those first objects that are not located in the region identified in (b) but rather are disposed within a predetermined distance of the region, wherein the counting of (d) results in a first object count;

    (e) counting those second objects that are not located in the region identified in (b) but rather are disposed within the predetermined distance of the region, wherein the counting of (e) results in a second object count;

    (f) computing a score using the first object count and using the second object count, wherein the score predicts the risk of cancer recurrence in the patient; and

    (g) storing the score to a storage device, wherein (a) through (g) are performed by the system.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×