Name
Title | ||
|---|---|---|
Fully Automatic Planning Of Total Shoulder Arthroplasty Without Segmentation: A Deep Learning Based Approach |
Abstract | ||
|---|---|---|
We present a method for automatically determining the position and orientation of the articular marginal plane (AMP) of the proximal humerus in computed tomography (CT) images without segmentation or hand-crafted features. The process is broken down into 3 stages. Stage 1 determines a coarse estimation of the AMP center by sampling patches over the entire image and combining predictions with a novel kernel density estimation method. Stage 2 utilizes the estimate from stage 1 to focus on a smaller sampling region and operates at a higher images resolution to obtain a refined prediction of the AMP center. Stage 3 focuses patch sampling on the region around the center obtained at stage 2 and regresses the tip of a vector normal to the AMP which yields the orientation of the plane. The system was trained and evaluated on 27 upper arm CTs. In a 4-fold cross-validation the mean error in estimating the AMP center was 1.30 +/- 0.65mm and the angular error for estimating the normal vector was 4.68 +/- 2.84 degrees. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1007/978-3-030-11166-3_3 | COMPUTATIONAL METHODS AND CLINICAL APPLICATIONS IN MUSCULOSKELETAL IMAGING, MSKI 2018 |
Keywords | DocType | Volume |
Regression, Proximal humerus, Articular marginal plane, Deep learning, Total shoulder arthroplasty | Conference | 11404 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Paul Kulyk | 1 | 0 | 0.34 |
| Lazaros Vlachopoulos | 2 | 0 | 1.69 |
| Philipp Fürnstahl | 3 | 0 | 0.34 |
| Guoyan Zheng | 4 | 363 | 56.10 |