TY - JOUR
T1 - Localized Statistical Shape Models for Large-scale Problems With Few Training Data
AU - Wilms, Matthias
AU - Ehrhardt, Jan
AU - Forkert, Nils Daniel
N1 - Publisher Copyright:
© 1964-2012 IEEE.
PY - 2022/9/1
Y1 - 2022/9/1
N2 - Objective: 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. Method: 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. Results: 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. Conclusion: 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. Significance: 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.
AB - Objective: 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. Method: 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. Results: 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. Conclusion: 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. Significance: 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.
UR - http://www.scopus.com/inward/record.url?scp=85126336732&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/16aac0bb-a0bf-3f80-bf20-73c4ca3b10a0/
U2 - 10.1109/TBME.2022.3158278
DO - 10.1109/TBME.2022.3158278
M3 - Journal articles
C2 - 35271438
AN - SCOPUS:85126336732
SN - 0018-9294
VL - 69
SP - 2947
EP - 2957
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 9
M1 - 9
ER -