A hierarchical method based on active shape models and directed Hough transform for segmentation of noisy biomedical images; application in segmentation of pelvic X-ray images

Abstract

Background: Traumatic pelvic injuries are often associated with severe, life-threatening hemorrhage, and immediate medical treatment is therefore vital. However, patient prognosis depends heavily on the type, location and severity of the bone fracture, and the complexity of the pelvic structure presents diagnostic challenges. Automated fracture detection from initial patient X-ray images can assist physicians in rapid diagnosis and treatment, and a first and crucial step of such a method is to segment key bone structures within the pelvis; these structures can then be analyzed for specific fracture characteristics. Active Shape Model has been applied for this task in other bone structures but requires manual initialization by the user. This paper describes a algorithm for automatic initialization and segmentation of key pelvic structures - the iliac crests, pelvic ring, left and right pubis and femurs - using a hierarchical approach that combines directed Hough transform and Active Shape Models.

Results: Performance of the automated algorithm is compared with results obtained via manual initialization. An error measures is calculated based on the shapes detected with each method and the gold standard shapes. ANOVA results on these error measures show that the automated algorithm performs at least as well as the manual method. Visual inspection by two radiologists and one trauma surgeon also indicates generally accurate performance.

Conclusion: The hierarchical algorithm described in this paper automatically detects and segments key structures from pelvic X-rays. Unlike various other x-ray segmentation methods, it does not require manual initialization or input. Moreover, it handles the inconsistencies between x-ray images in a clinical environment and performs successfully in the presence of fracture. This method and the segmentation results provide a valuable base for future work in fracture detection.

Figure 1

Flowchart of pelvic segmentation process. This flowchart illustrates the steps of the hierarchical initialization and segmentation algorithm.

Figure 2

Bones of the Pelvis. An x-ray showing key structures of interest located within the human pelvis.

Figure 3

Hough line detection of femoral shafts. Results of directed Hough Transform for detection of femoral shafts.

Figure 4

Hough circle detection of femoral heads. Results of directed Hough Transform for detection of femoral heads.

Figure 5

Example ASM detection of left femur. Example of left femur detection using ASM algorithm.

Figure 6

ANOVA boxplot for left iliac crest detection. Boxplot generated from ANOVA test for left femur detection results using manual ASM initialization and using our hierarchical automated algorithm.

Figure 7

ANOVA boxplot for left femur detection. Boxplot generated from ANOVA test for left iliac crest detection results using manual ASM initialization and using our hierarchical automated algorithm.

Figure 8

ANOVA boxplot for pelvic ring detection. Boxplot generated from ANOVA test for pelvic ring detection results using manual ASM initialization and using our hierarchical automated algorithm.

Figure 9

Automated detection results: first example. Example results for automated detection of all key pelvic structures. Results are accurate for all regions.

Figure 10

Automated detection results: second example. Example results for automated detection of all key pelvic structures. Results are accurate for all regions.

Figure 11

Automated detection results: third example. Example results for automated detection of all key pelvic structures. Results are good for pelvic ring, right crest and left pubis. Performance on other structures demonstrates some issues.

Figure 12

Automated detection results: fourth example. Example results for automated detection of all key pelvic structures. Results are good for pelvic ring, both crests and the right femur. Performance on other structures demonstrates some issues, particularly left and right pubis.