Method and apparatus for tumor purity based on pathological slide image
Provided is a computing apparatus including: at least one memory; and at least one processor, wherein the at least one processor is configured to: perform a first classification on a plurality of tissues expressed in a pathological slide image by analyzing the pathological slide image, perform a second classification on a plurality of cells expressed in a pathological slide image by analyzing the pathological slide image, and calculate tumor purity including information on noise included in the pathological slide image by combining a first classification result and a second classification result.
1 . A computing apparatus comprising:
memory storing instructions; and
at least one processor, wherein the instructions cause the at least one processor to:
perform a first classification on a plurality of tissues expressed in a pathological slide image by analyzing the pathological slide image;
perform a second classification on a plurality of cells expressed in the pathological slide image by analyzing the pathological slide image;
classify tumor cells among cells included in a cancer area in the pathological slide image by combining the first classification result and the second classification result;
determine a total number of cells corresponding to a number of the tumor cells, a number of lymphocyte cells, and a number of other cells included in the cancer area, a cancer stroma area, and a background area in the pathological slide image, wherein the background area includes an area representing biological noise; and
calculate tumor purity including information about a first ratio of the number of the tumor cells included in the cancer area with respect to the total number of cells, and information on technical noise included in the pathological slide image,
wherein the information on the technical noise is calculated based on a size of a degraded area included in the pathological slide image.
2 . The computing apparatus of claim 1 , wherein
the instructions further cause the at least one processor to perform the first classification by classifying the pathological slide image into the cancer area and at least one of the cancer stroma area, a necrosis area, or the background area.
3 . The computing apparatus of claim 2 , wherein
the instructions further cause the at least one processor to calculate a second ratio of the cancer area with respect to the total area included in the pathological slide image by combining the first classification result and the second classification result.
4 . The computing apparatus of claim 1 , wherein
the instructions further cause the at least one processor to perform the second classification by classifying the plurality of cells expressed in the pathological slide image into the tumor cells and at least one of a lymphocyte cell, or other cells.
5 . The computing apparatus of claim 1 , wherein
the instructions further cause the at least one processor to calculate at least one index representing an expected cancer signal by using the first classification result and the second classification result.
6 . The computing apparatus of claim 5 , wherein
the instructions further cause the at least one processor to control a display device to output the tumor purity and the at least one index.
7 . The computing apparatus of claim 5 , wherein
the instructions further cause the at least one processor to provide a guide on whether to perform an additional experiment by comparing the at least one index with a preset threshold.
8 . The computing apparatus of claim 1 , wherein
the instructions further cause the at least one processor to calculate at least one of an expected DNA yield for all cells and an expected tumor DNA yield for tumor cells using the calculated tumor purity.
9 . The computing apparatus of claim 1 , wherein the information on the technical noise comprises a second ratio of the size of the degraded area to a size of a total area included in the pathological slide image comprising a size of the cancer area, a size of the cancer stroma area, and a size of the background area.
10 . A method of interpreting a pathological slide image, the method comprising:
performing a first classification on a plurality of tissues expressed in the pathological slide image by analyzing the pathological slide image;
performing a second classification on a plurality of cells expressed in the pathological slide image by analyzing the pathological slide image; and
classifying tumor cells among cells included in a cancer area in the pathological slide image by combining the first classification result and the second classification result;
determine a total number of cells corresponding to a number of the tumor cells, a number of lymphocyte cells, and a number of other cells included in the cancer area, a cancer stroma area, and a background area in the pathological slide image, wherein the background area includes an area representing biological noise; and
calculating tumor purity including information about a first ratio of the number of the tumor cells included in the cancer area with respect to the total number of cells, and information on technical noise included in the pathological slide image,
wherein the information on the technical noise is calculated based on a size of a degraded area included in the pathological slide image.
11 . The method of claim 10 , wherein
the performing the first classification comprises classifying the pathological slide image into the cancer area and at least one of the cancer stroma area, a necrosis area, or the background area.
12 . The method of claim 11 , wherein
the calculating the tumor purity comprises calculating a second ratio of the cancer area with respect to the total area included in the pathological slide image by combining the first classification result and the second classification result.
13 . The method of claim 10 , wherein
the performing the second classification comprises classifying the plurality of cells expressed in the pathological slide image into the tumor cells and at least one of a lymphocyte cell, or other cells.
14 . The method of claim 10 , further comprising:
calculating at least one index representing an expected cancer signal by using the first classification result and the second classification result.
15 . The method of claim 14 , wherein
the calculating the at least one index comprises calculating at least one of an expected DNA yield for all cells and an expected tumor DNA yield for tumor cells using the calculated tumor purity.
16 . The method of claim 14 , further comprising outputting the tumor purity and the at least one index.
17 . The method of claim 14 , further comprising providing a guide on whether to perform an additional experiment by comparing the at least one index with a preset threshold.
18 . A non-transitory computer-readable recording medium having recorded thereon a program for executing the method of claim 10 in a computer.