Lung Segmentation Bone Suppression Radiographic Image Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for lung segmentation and bone suppression in radiographic images face challenges in accurately removing spurious boundary pixels and obscuring features, leading to false positives and reduced diagnostic accuracy.
Innovation Solution
The method involves detecting and suppressing clavicle, posterior, and anterior rib bones by warping the images to straighten bone structures, performing edge detection, and using intensity projections to refine lung contours, thereby generating a bone-suppressed image that enhances lung segmentation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional bone suppression techniques are used, then some bone structures are removed, but false positives increase and diagnostic accuracy decreases
Solution Approach 1:
The patent segments the lung image into multiple regions based on anatomical landmarks (clavicles, ribs, diaphragm, heart) and processes each region with appropriate suppression techniques. This regional segmentation allows selective bone suppression while preserving lung tissue boundaries, thereby improving both diagnostic reliability and segmentation precision simultaneously
Solution Approach 2:
Different suppression strategies are applied to different anatomical regions: aggressive suppression for rib shadows in lung fields, conservative suppression for clavicle boundaries near apex, and selective suppression for anterior ribs. This local quality approach ensures high measurement precision in each region while maintaining overall diagnostic reliability
2Object-generated harmful factors
If aggressive bone suppression is applied, then bone structures are removed, but lung boundary pixels are incorrectly removed causing false positives
Solution Approach 1:
The patent performs preliminary detection and classification of bone structures (clavicles, posterior ribs, anterior ribs) before suppression. By pre-identifying bone boundaries and lung boundaries separately, the suppression operation can be precisely targeted at bone structures only, preventing loss of lung boundary information while effectively removing bone obscuration
Solution Approach 2:
The patent uses intermediate representations such as intensity projection profiles and boundary probability maps as mediators between the original image and the suppressed image. These intermediaries allow precise control of the suppression process, enabling bone removal while preserving lung boundary pixels through iterative refinement and boundary protection mechanisms
Data Source
Figure 1
Figure 2A~2B
Figure 3A~3B
AI summary
Lung segmentation and bone suppression techniques are helpful pre-processing steps prior to radiographic analyses of the human thorax, as may occur during cancer screenings and other medical examinations. Autonomous lung segmentation may remove spurious boundary pixels from a radiographic image, as well as identify and refine lung boundaries. Thereafter, autonomous bone suppression may identify clavicle, posterior rib, and anterior rib bones using various image processing techniques, including warping and edge detection. The identified clavicle, posterior rib, and anterior rib bones may then be supressed from the radiographic image to yield a segmented, bone suppressed radiographic image.