SYSTEMS AND METHODS OF ANALYZING MICROBIOMES USING ARTIFICIAL INTELLIGENCE
Disclosed systems and methods include executing a convolutional neural network to detect a level of microbiome in a whole slide image associated with a patient, based on an output of the convolutional neural network, categorize the whole slide image as one of microbiome-low and microbiome-high, and, based on the categorization of the whole slide image, determine a characteristic of a cancer associated with the patient.
1 . A computer system for assessing a patient's response to a cancer treatment wherein the patient has cancer, the system comprising:
a processor; and
a computer-readable storage medium storing computer-readable instructions which, when executed by a processor, cause the processor to:
execute a convolutional neural network to detect a level of microbiome in a whole slide image associated with the patient;
based on an output of the convolutional neural network, categorize the whole slide image as one of microbiome-low and microbiome-high; and
based on the categorization of the whole slide image, determine a characteristic of cancer associated with the patient.
2 . The system of claim 1 , wherein the whole slide image comprises hematoxylin and eosin (H&E)-stained pathology slides.
3 . The system of claim 1 , wherein the cancer is bladder cancer.
4 . The system of claim 3 , wherein the convolutional neural network is trained based on Formalin-Fixed Paraffin-Embedded (FFPE) diagnostic images sourced from a bladder cohort.
5 . The system of claim 1 , wherein the output of the convolutional neural network is used to determine a survival statistic of the patient.
6 . The system of claim 1 , wherein microbiome-low is associated with a microbiome level of less than a median microbiome level of a cohort and microbiome-high is associated with a microbiome level of greater than the median microbiome level of the cohort.
7 . The system of claim 1 , wherein the instructions further cause the processor to:
determine if the patient is responding to the cancer treatment based on the categorization of the whole slide image; and
continue treating the patient with the cancer treatment in response to determining the patient is responding to the cancer treatment.
8 . The system of claim 1 , wherein the instructions further cause the processor to determine a pathologic complete response (pCR) based on the output of the convolutional neural network.
9 . A method of assessing a patient's response to a cancer treatment wherein the patient has cancer, the method comprising:
executing a convolutional neural network to detect a level of microbiome in a whole slide image associated with the patient;
based on an output of the convolutional neural network, categorizing the whole slide image as one of microbiome-low and microbiome-high;
based on the categorization of the whole slide image, determining a characteristic of cancer associated with the patient;
determining the patient is responding to the cancer treatment based on the categorization of the whole slide image; and
continuing treating the patient with the cancer treatment in response to determining the patient is responding to the cancer treatment.
10 . The method of claim 9 , wherein the whole slide image comprises hematoxylin and eosin (H&E)-stained pathology slides.
11 . The method of claim 9 , wherein the cancer is bladder cancer.
12 . The method of claim 11 , wherein the convolutional neural network is trained based on Formalin-Fixed Paraffin-Embedded (FFPE) diagnostic images sourced from a bladder cohort.
13 . The method of claim 9 , wherein the output of the convolutional neural network is used to determine a patient survival statistic.
14 . The method of claim 9 , wherein microbiome-low is associated with a microbiome level of less than a median microbiome level of a cohort and microbiome-high is associated with a microbiome level of greater than the median microbiome level of the cohort.
15 . The method of claim 9 , further comprising determining a pathologic complete response (pCR) based on the output of the convolutional neural network.
16 . At least one machine-readable non-transitory medium comprising a plurality of instructions, executed on a computing device, to facilitate the computing device to:
execute a convolutional neural network to detect a level of microbiome in a whole slide image associated with a patient;
based on an output of the convolutional neural network, categorize the whole slide image as one of microbiome-low and microbiome-high; and
based on the categorization of the whole slide image, determine a characteristic of cancer associated with the patient.
17 . The machine-readable non-transitory medium of claim 16 , wherein the whole slide image comprises hematoxylin and eosin (H&E)-stained pathology slides.
18 . The machine-readable non-transitory medium of claim 16 , wherein the cancer is bladder cancer.
19 . The machine-readable non-transitory medium of claim 18 , wherein the convolutional neural network is trained based on Formalin-Fixed Paraffin-Embedded (FFPE) diagnostic images sourced from a bladder cohort.
20 . The machine-readable non-transitory medium of claim 16 , wherein the output of the convolutional neural network is used to determine a survival statistic of the patient.