MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

A Statistically Characterized Reference Data Set for Image Registration of Pelvis Using Combinatorial Affine Registration Optimization

A Yorke1*, I Sala2 , D Solis3 , T Guerrero4 , (1) William Beaumont Hospital, Royal Oak, MI, (2) Beaumont Hospital, Royal Oak, MI, (3) William Beaumont Hospital, Warren, MI, (4) ,Royal Oak, MI

Presentations

(Tuesday, 7/16/2019) 10:30 AM - 11:00 AM

Room: Exhibit Hall | Forum 9

Purpose: selected landmark points on clinical image pairs provide a basis for rigid registration validation. Using combinatorial affine registration optimization (CARO) we provide a statistically characterized reference data set for image registration of the pelvis by estimating the underlying ground truth.

Methods: Landmark points for each CT/CBCT image pair for 60 pelvic cases were identified. From the identified landmark pairs, combination subsets of k-number of landmark pairs were generated without repeat, to form a k-set for k=4, 8, &12. An affine registration between the image pairs was calculated for each k-combination set (1,900-8,000,000). The mean and the standard deviation of the registration were used as the final registration for each image pair. Joint entropy was employed to measure and compare the quality of CARO to commercially available software.

Results: An average of 154 (range: 91-212) landmark pairs were selected for each CT/CBCT image pair. The mean standard deviation of the registration output decreased as the k-size increased for all cases. In general the joint entropy evaluated was found to be lower than results from commercially available software. Of all 60 cases 87% of the k=4, 75% of k=8 and 75% of k=12 resulted in better registration using CARO as compared to 60% from a commercial software. The minimum joint entropy determined for one case and found to exist at the estimated registration mean in agreement with CARO approach.

Conclusion: The results demonstrate that CARO is still a very good method for estimating the underlying truth of rigid registration. The estimated ground truth was found to be better than commercially available software. Additionally, the k-set of 4 resulted in overall best outcomes when compared to k=8 and 12, which is anticipated because k=8 and 12 are more likely to have mismatched points that would affect the accuracy of the registration.

Keywords

Not Applicable / None Entered.

Taxonomy

IM/TH- Image registration : CT

Contact Email