Systems and methods for automated and interactive analysis of bone scan images for detection of metastases

Inventors

Sjöstrand, Karl Vilhelm • Richter, Jens Filip Andreas • Edenbrandt, Lars

Assignees

Exini Diagnostics AB • Progenics Pharmaceuticals Inc

Abstract

Presented herein are systems and methods that provide for improved computer aided display and analysis of nuclear medicine images. In particular, in certain embodiments, the systems and methods described herein provide improvements to several image processing steps used for automated analysis of bone scan images for assessing cancer status of a patient. For example, improved approaches for image segmentation, hotspot detection, automated classification of hotspots as representing metastases, and computation of risk indices such as bone scan index (BSI) values are provided.

Core Innovation

The invention provides a processor-based method for lesion marking and quantitative analysis of nuclear medicine images of a human subject. The method accesses a bone scan image set obtained following administration of an agent to the human subject and automatically segments each image to identify skeletal regions of interest corresponding to anatomical regions of a skeleton, including a femur region and a humerus region, thereby generating an annotated set of images for downstream hotspot processing.

The method automatically detects an initial set of one or more hotspots, where each hotspot corresponds to an area of elevated intensity in the annotated set of images. Hotspot detection uses intensities of pixels in the annotated set of images and one or more region-dependent threshold values, including values associated with the femur region and/or the humerus region that provide enhanced hotspot detection sensitivity to compensate for reduced uptake of the agent therein, including a first reduced intensity threshold value for the femur/humerus that is lower than a second threshold value for one or more other skeletal regions of interest.

For each hotspot in the initial set, the method extracts a set of hotspot features and calculates a metastasis likelihood value corresponding to a likelihood of the hotspot representing a metastasis based on the hotspot features. The method then causes rendering of a graphical representation of at least a portion of the initial set of hotspots for display within a graphical user interface (GUI). The invention is also embodied as a system and a computer aided image analysis device that implement the same lesion marking and quantitative analysis workflow.

Claims Coverage

The independent claims cover a processor-implemented method and corresponding system/device for lesion marking and quantitative analysis, with three core inventive feature areas: skeletal region segmentation including femur/humerus, region-dependent hotspot detection using a reduced threshold for femur/humerus, and metastasis likelihood calculation with GUI rendering. Additional claim coverage adds an intended-use label for the computer aided device.

Collectively, the independent claims cover automatic segmentation of skeletal regions of interest including femur and/or humerus, automatic detection of hotspots using region-dependent pixel-intensity thresholds with a reduced threshold for femur/humerus, extraction of hotspot features, calculation of a metastasis likelihood value per hotspot, and GUI rendering of hotspot representations, with additional scope requiring a label specifying intended use by trained healthcare professionals and/or researchers for the computer aided device.

Stated Advantages

Documented Applications