17522196. CLASSIFICATION OF MEDICAL IMAGES USING MACHINE LEARNING TO ACCOUNT FOR BODY ORIENTATION simplified abstract (International Business Machines Corporation)

CLASSIFICATION OF MEDICAL IMAGES USING MACHINE LEARNING TO ACCOUNT FOR BODY ORIENTATION

Organization Name

International Business Machines Corporation

Inventor(s)

Sun Young Park of San Diego CA (US)

Dustin Michael Sargent of San Diego CA (US)

CLASSIFICATION OF MEDICAL IMAGES USING MACHINE LEARNING TO ACCOUNT FOR BODY ORIENTATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17522196 titled 'CLASSIFICATION OF MEDICAL IMAGES USING MACHINE LEARNING TO ACCOUNT FOR BODY ORIENTATION

Simplified Explanation

The patent application describes a computer system that can identify a medical condition in a patient using machine learning techniques.

• Trained machine learning image generator creates a set of training images based on patient imaging data.
• Each training image is labeled with a projection angle of the corresponding two-dimensional projection.
• Machine learning image classifier model is trained using the set of training images to identify patient rotation angles in x-ray images.
• X-ray images are processed with the machine learning image classifier model to identify patient rotation angles.
• Machine learning medical condition classifier model is trained to identify a medical condition using the labeled x-ray images.
• The machine learning medical condition classifier model determines an indication of the medical condition in a patient's x-ray image.

Potential applications of this technology:

• Medical diagnosis: The system can assist doctors in identifying medical conditions in patients by analyzing x-ray images.
• Automation: The system can automate the process of analyzing x-ray images, reducing the workload on medical professionals.
• Training tool: The system can be used as a training tool for medical students to learn how to identify medical conditions in x-ray images.

Problems solved by this technology:

• Accuracy: The system can improve the accuracy of medical condition identification by using machine learning algorithms.
• Efficiency: The system can analyze x-ray images quickly, allowing for faster diagnosis and treatment.
• Standardization: The system can provide standardized analysis of x-ray images, reducing variability in diagnosis.

Benefits of this technology:

• Improved diagnosis: The system can assist doctors in making more accurate and timely diagnoses.
• Time-saving: The system can analyze x-ray images quickly, saving time for both doctors and patients.
• Training enhancement: The system can be used as a training tool to improve the skills of medical professionals in diagnosing medical conditions.

Original Abstract Submitted

A computer system identifies a medical condition in a patient. A trained machine learning image generator is used to generate a set of training images based on three-dimensional patient imaging data, wherein each training image is labeled with a projection angle of the corresponding two-dimensional projection. Using the set of training images, a machine learning image classifier model is trained to identify patient rotation angles in x-ray images. X-ray images are processed with the machine learning image classifier model to identify patient rotation angles. A machine learning medical condition classifier model is trained to identify a medical condition using the labeled x-ray images. The machine learning medical condition classifier model determines an indication of the medical condition in a patient's x-ray image. Embodiments of the present invention further include a method and program product for identifying a medical condition in a patient in substantially the same manner described above.