System and methods for characterizing and monitoring inter-anatomical reference relationships in medical imaging

WO2026136371A1PCT designated stage Publication Date: 2026-06-25GE PRECISION HEALTHCARE LLC
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
GE PRECISION HEALTHCARE LLC
Filing Date
2025-12-16
Publication Date
2026-06-25

AI Technical Summary

Technical Problem

Monitoring the performance of machine learning models in medical imaging deployments is challenging due to patient privacy concerns and regulatory requirements, which prevent the transmission of clinical imaging data, leading to difficulties in evaluating model reliability and identifying biases across different sites and patient populations.

Method used

A system and method that analyze spatial relationships between anatomical landmarks detected by machine learning models, transmitting these relationships rather than the medical images, allowing for performance characterization and anomaly detection without accessing protected health information, using statistical thresholds derived from reference datasets to identify deviations and provide alerts.

Benefits of technology

Enables systematic evaluation of model performance across different deployment sites and patient populations while maintaining privacy and compliance, reducing computational overhead, and facilitating real-time monitoring of potential anomalies and biases.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000048_0000
    Figure 00000048_0000
  • Figure 00000049_0000
    Figure 00000049_0000
  • Figure 00000050_0000
    Figure 00000050_0000
Patent Text Reader

Abstract

A method for monitoring performance of a deployed machine learning model includes receiving a medical image at a clinical site, detecting anatomical landmarks as geometric objects in the medical image using the deployed model, determining spatial relationships between pairs of the detected geometric objects, transmitting the spatial relationships to a remote monitoring system without transmitting the medical image, comparing the spatial relationships against previously determined spatial relationships to identify outliers, generating a performance characterization based on the identified outliers, and responding to deviations from expected model performance by transmitting alerts. The geometric objects include organ masks, segmentation masks, landmark masks, derived planes, and bounding boxes. The spatial relationships include normalized distances between object centers and angles between object orientation vectors. Statistical thresholds enable identification of anomalous relationships while maintaining patient privacy.
Need to check novelty before this filing date? Find Prior Art