Systems and methods for platform agnostic whole body image segmentation

Inventors

Richter, Jens Filip Andreas • Johnsson, Kerstin Elsa Maria • Gjertsson, Erik Konrad • Anand, Aseem Undvall

Assignees

Exini Diagnostics AB

Abstract

Presented herein are systems and methods that provide for automated analysis of three-dimensional (3D) medical images of a subject in order to automatically identify specific 3D volumes within the 3D images that correspond to specific anatomical regions (e.g., organs and/or tissue). Notably, the image analysis approaches described herein are not limited to a single particular organ or portion of the body. Instead, they are robust and widely applicable, providing for consistent, efficient, and accurate detection of anatomical regions, including soft tissue organs, in the entire body. In certain embodiments, the accurate identification of one or more such volumes is used to automatically determine quantitative metrics that represent uptake of radiopharmaceuticals in particular organs and/or tissue regions. These uptake metrics can be used to assess disease state in a subject, determine a prognosis for a subject, and/or determine efficacy of a treatment modality.

Core Innovation

The invention automatically processes a 3D anatomical image of a subject to identify volumes of interest that correspond to particular target tissue regions. A processor receives the 3D anatomical image obtained using an anatomical imaging modality and automatically identifies, for each of a plurality of target tissue regions, a corresponding target VOI using one or more machine learning modules, then determines a 3D segmentation map representing a plurality of 3D segmentation masks.

The method links the anatomical segmentation to functional PSMA imaging. The processor receives a 3D functional image obtained using a functional imaging modality following administration to the subject of a radiopharmaceutical comprising a prostate-specific membrane antigen binding agent. Using the 3D segmentation map, the processor identifies one or more 3D volumes within the 3D functional image that correspond to the identified target VOIs, and determines one or more uptake metrics representing uptake of the radiopharmaceutical in particular organs and/or tissue regions.

The disclosed clinical context includes standardized quantitative assessment by using the segmentation-driven functional volume identification to compute uptake metrics and indices. The description states that these hotspot-related indices support evaluation of cancer status, prognosis, and treatment efficacy, including extraction of corresponding 3D volumes and functional hotspots.

Claims Coverage

The patent provides two independent claims covering a method workflow and a system implementing that workflow. Across the independent claims, the coverage centers on four inventive features: machine-learning identification of target VOIs in a 3D anatomical image, creation of a 3D segmentation map, application of that segmentation to a corresponding 3D PSMA functional image, and determination of uptake metrics from the mapped functional volumes.

Across the independent method and system claims, the core inventive coverage is the integration of machine learning-based 3D anatomical segmentation with PSMA radiopharmaceutical functional imaging, using the segmentation map to identify corresponding functional volumes and compute uptake metrics for particular organs and/or tissue regions.

Stated Advantages

Documented Applications