Automated qualitative description of anatomical changes in radiotherapy

Inventors

BONDAR, Maria Luiza • Bal, Matthieu Frederic • Isola, Alfonso Agatino

Assignees

Elekta Inc

Abstract

A system and a method for monitoring anatomical changes in a subject in radiation therapy are provided, as well as an arrangement for medical imaging and analysis and a computer program product for carrying out the method. For monitoring anatomical changes in a subject in radiation therapy, the following steps are performed. First anatomical image data and subsequent anatomical image data of the subject are received. The first anatomical image data and the subsequent anatomical image data are analyzed. This analysis comprises registering the subsequent anatomical data to the first anatomical data. Changes between the first anatomical image data and the subsequent anatomical image data are identified as change states, and the identified change states are matched to corresponding qualitative descriptions. A monitoring report is provided, which comprises the qualitative descriptions of the identified changes.

Core Innovation

The invention concerns monitoring anatomical changes in a subject receiving radiation therapy. A system, method, or computer-readable medium receives and analyzes first and subsequent anatomical image data, identifies changes as respective change states using a trained learning algorithm, matches those states to corresponding qualitative descriptions, and provides a monitoring report containing the descriptions.

The disclosure describes spatial reasoning approaches, including RCC-8 and Cardinal reasoning, optional dose-plan comparisons, quantitative region-of-interest measurements, risk indicators, pictograms, and interactive report views. The system supports faster and more consistent assessment and flags cases for clinical review. Background problem details are not explicitly described in patent.

Claims Coverage

The provided claims identify three independent claims: a system claim, a method claim, and a non-transitory computer-readable-medium claim. Their central claim elements cover analyzing anatomical image data from different times, identifying change states with a trained learning algorithm, matching the states to qualitative descriptions, and providing a monitoring report.

The three independent claims cover system, method, and computer-readable-medium forms of the same image-based monitoring approach. Across them, the central claim elements are change-state identification using a trained learning algorithm, translation into qualitative descriptions, and reporting; dependent claims specify additional analyses and report features.

Stated Advantages

Documented Applications