Name
Abstract | ||
|---|---|---|
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i>
Statistical shape models have been successfully used in numerous biomedical image analysis applications where prior shape information is helpful such as organ segmentation or data augmentation when training deep learning models. However, training such models requires large data sets, which are often not available and, hence, shape models frequently fail to represent local details of unseen shapes. This work introduces a kernel-based method to alleviate this problem via so-called model localization. It is specifically designed to be used in large-scale shape modeling scenarios like deep learning data augmentation and fits seamlessly into the classical shape modeling framework.
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Method:</i>
Relying on recent advances in multi-level shape model localization via distance-based covariance matrix manipulations and Grassmannian-based level fusion, this work proposes a novel and computationally efficient kernel-based localization technique. Moreover, a novel way to improve the specificity of such models via normalizing flow-based density estimation is presented.
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i>
The method is evaluated on the publicly available JSRT/SCR chest X-ray and IXI brain data sets. The results confirm the effectiveness of the kernelized formulation and also highlight the models’ improved specificity when utilizing the proposed density estimation method.
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Conclusion:</i>
This work shows that flexible and specific shape models from few training samples can be generated in a computationally efficient way by combining ideas from kernel theory and normalizing flows.
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Significance:</i>
The proposed method together with its publicly available implementation allows to build shape models from few training samples directly usable for applications like data augmentation. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/TBME.2022.3158278 | IEEE Transactions on Biomedical Engineering |
Keywords | DocType | Volume |
Algorithms,Brain,Image Processing, Computer-Assisted,Models, Statistical,Radiography | Journal | 69 |
Issue | ISSN | Citations |
9 | 0018-9294 | 0 |
PageRank | References | Authors |
0.34 | 31 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Matthias Wilms | 1 | 2 | 2.06 |
| Jan Ehrhardt | 2 | 387 | 54.33 |
| Nils D Forkert | 3 | 0 | 0.34 |