Statistical shape model of the spine fitting study: impact of clipping the latent representation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Statistical shape model of the spine fitting study: impact of clipping the latent representation

Résumé

Statistical shape models (SSMs) represent the distribution of labeled points across a training set of shapes. The standard practice for SSMs based on principal component analysis (PCA) is to use clipping, thresholding the latent representation so that all shapes lie within 3 standard deviations of the mean. This practice precludes the representation of shapes that are not well represented by the training set, constraining the model to realistic solutions, but making it impossible to work with shapes at the edges of the statistical population. In this study, we investigate the impact of clipping in a PCA-based SSM and whether using L2 regularization is a good replacement for clipping in the context of the automatic 2D to 3D reconstruction of the spine. We first show that using L2 regularization is equivalent to using a probabilistic PCA with two error variables, accounting for the suppression of the least important principal components and for the fact that the training set cannot perfectly represent all shapes at test time. Secondly, we use two data sets of 1746 and 768 patients with adolescent idiopathic scoliosis to study the effect of regularization, for different regularization weights and with or without clipping, for removing landmark detection errors using a simulated noise or a reconstruction pipeline. In both sets of experiments, we show that regularization removes noise in a way similar to clipping without preventing the reconstruction of out-of-distribution shapes, leading to outputs closer to ground truth, demonstrating that using a regularized SSM should be preferred to clipping.
Fichier principal
Vignette du fichier
1203212.pdf (826.59 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03694285 , version 1 (13-06-2022)

Identifiants

Citer

Manon Ansart, Thierry Cresson, Benjamin Aubert, Jacques A de Guise, Carlos Vázquez. Statistical shape model of the spine fitting study: impact of clipping the latent representation. PROCEEDINGS VOLUME 12032 SPIE MEDICAL IMAGING, Feb 2022, San Diego, United States. ⟨10.1117/12.2606202⟩. ⟨hal-03694285⟩
86 Consultations
169 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More