# US 12,217,851 B2 · Identification of candidate signs indicative of an NTRK oncogenic fusion

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

- Number: US 12,217,851 B2
- Document ID: US12217851B2
- Status: Granted
- Kind: B2
- Application number: 17/595,191
- Filed: 2020-04-28
- Published: 2022-07-14
- Granted: 2025-02-04
- Earliest claimed: 2019-05-10
- Applicants: Bayer Consumer Care AG
- Inventors: Arndt Schmitz; Eren Metin Elci; Faidra Stavropoulou; Mikhail Kachala; Antti Karlsson; Mikko Tukiainen
- Web page: https://patentgrep.com/patent/US12217851B2

## CPC

- G16H 30/40: for processing medical images, e.g. editing
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06T 7/0012: {Biomedical image inspection}
- G06V 20/698: {Matching; Classification}
- G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06T 2207/30004: Biomedical image processing
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The present invention relates to the identification of one or more candidate signs indicative of an NTRK oncogenic fusion within patient data. Subject matter of the present invention are a computer-implemented method, a system, and a non-transitory computer-readable storage medium for determining a probability value from patient data associated with a subject patient, the probability value indicating the probability of the subject patient suffering from cancer caused by a mutation of a neurotrophic receptor tyrosine kinase (NTRK) gene.

## Claims

### Claim 1

A computer-implemented method for identifying one or more candidate signs indicative of an NTRK oncogenic fusion within patient data associated with a subject patient, the method comprising:
receiving historical patient data for which one or more candidate signs indicative of an NTRK oncogenic fusion have been verified or excluded, the historical patient data comprising a plurality of histopathological images of tumor tissue;
training a prediction model via machine learning to predict a probability of cancer caused by the NTRK oncogenic fusion for each histological image of the plurality of histopathological images, thereby obtaining a trained prediction model;
receiving patient data of a subject patient suffering from cancer, the patient data comprising at least one histopathological image of tumor tissue of the subject patient;
inputting the patient data into the trained prediction model, the trained prediction model being configured for identifying within the patient data one or more characteristics of an NTRK oncogenic fusion;
receiving as an output from the trained prediction model a probability value, the probability value indicating the probability of the subject patient suffering from cancer caused by an NTRK oncogenic fusion;
comparing the probability value with a predefined threshold value; and
in the event that the probability value is equal to or greater than the threshold value: initiating further investigations for verification of the indication that the subject patient suffers from cancer caused by an NTRK oncogenic fusion.

### Claim 2

A system, comprising:
a processor; and
a memory storing an application program configured to perform, when executed by the processor, an operation for identifying one or more candidate signs indicative of an NTRK oncogenic fusion within patient data associated with a subject patient, the operation comprising:
receiving historical patient data for which the one or more candidate signs indicative of the NTRK oncogenic fusion have been verified or excluded, the historical patient data comprising a plurality of histopathological images of tumor tissue;
training a prediction model via machine learning to predict a probability of cancer caused by the NTRK oncogenic fusion for each histological image of the plurality of histopathological images, thereby obtaining a trained prediction model;
receiving patient data of a subject patient suffering from cancer, the patient data comprising at least one histopathological image of tumor tissue of the subject patient;
inputting the patient data into the trained prediction model, the trained prediction model being configured for identifying within the patient data one or more characteristics of an NTRK oncogenic fusion;
receiving as an output from the trained prediction model a probability value, the probability value indicating the probability of the subject patient suffering from cancer caused by an NTRK oncogenic fusion;
comparing the probability value with a predefined threshold value; and
in the event that the probability value is equal to or greater than the threshold value: initiating further investigations for verification of the indication that the subject patient suffers from cancer caused by an NTRK oncogenic fusion.

### Claim 3

A non-transitory computer-readable storage medium comprising processor-executable instructions with which to perform an operation for identifying one or more candidate signs indicative of an NTRK oncogenic fusion within patient data associated with a subject patient, the operation comprising:
receiving historical patient data for which one or more candidate signs indicative of an NTRK oncogenic fusion have been verified or excluded, the historical patient data comprising a plurality of histopathological images of tumor tissue;
training a prediction model via machine learning to predict a probability of cancer caused by the NTRK oncogenic fusion for each histological image of the plurality of histopathological images, thereby obtaining a trained prediction model;
receiving patient data of a subject patient suffering from cancer, the patient data comprising at least one histopathological image of tumor tissue of the subject patient;
inputting the patient data into the trained prediction model, the trained prediction model being configured for identifying within the patient data one or more characteristics of an NTRK oncogenic fusion;
receiving as an output from the trained prediction model a probability value, the probability value indicating the probability of the subject patient suffering from cancer caused by an NTRK oncogenic fusion;
comparing the probability value with a predefined threshold value; and
in the event that the probability value is equal to or greater than the threshold value: initiating further investigations for verification of the indication that the subject patient suffers from cancer caused by an NTRK oncogenic fusion.