Methods for color enhanced detection of bone density from CT images and methods for opportunistic screening using same

Inventors

Smith, Andrew Dennis

Assignees

AI Metrics LLC

Abstract

Embodiments describe an accurate and rapid method for assessing spinal bone density on chest or abdominal CT images using post-processed colored images. Post-processing of CT images for the purposes of displaying the spine is followed by color enhancement of routine unenhanced or contrast enhanced CT images to improve diagnostic accuracy, inter-observer agreement, reader confidence and/or time of interpretation as it relates to assessing bone density of the spine. CT images are post-processed (without changes to the standard-of-care CT imaging protocol and without additional cost or radiation for the patient) to straighten the spine for improved visualization of multiple segments. The color-enhanced images can be displayable simultaneously with the grayscale images. Methods and systems are provided for performing opportunistic bone density screening.

Core Innovation

The invention provides a color-enhanced detection approach for opportunistic bone density screening using digital computed tomography (CT) image data. The method receives one or more portions of CT image data obtained during a CT scan of a clinical indication unrelated to bone density, where the image data includes an image of at least a portion of a patient’s body comprising a bone. The CT image data is processed to obtain a specified type of image relevant for the portion of the patient’s body.

After processing, the invention identifies an attenuation value for one or more pixels in the processed image associated with the bone. A color palette comprises one or more colors, where each color is related to a specific range of attenuation values and each attenuation range corresponds to one or more different bone density conditions. The mapping applies the provided color palette to the processed image according to the identified attenuation values to opportunistically screen for abnormal bone density conditions.

In embodiments focused on the spine, the invention processes the digital CT image data to obtain a straightened sagittal image of the midline spine by removing spinal curvature by aligning vertebrae in a co-localized plane. The mapping uses a straightened thick slab sagittal image of the spine for screening, with optional segmentation and optional noise reduction and/or smoothing before the attenuation-to-color mapping.

Claims Coverage

The partial content shows three independent claims. Across them, the inventive coverage centers on opportunistic bone density screening from CT data using attenuation-value identification and mapping of attenuation ranges to a color palette linked to bone density conditions; system-level claims add spine straightening and alignment and modules for attenuation determination and palette mapping.

The independent claims collectively cover opportunistic bone density screening by identifying bone attenuation values in a processed CT-derived image and mapping those attenuation ranges to a color palette tied to bone density conditions. System claims further specify a straightened sagittal midline spine image via vertebra alignment and implement the pipeline using an attenuation determining module, color palette provider, and mapping module.

Stated Advantages

Documented Applications