Incorporating Shape Variability in Image Segmentation via Implicit Template Deformation

Prevost, Raphaël; Cuingnet, Rémi; Mory, Benoît; Cohen, Laurent D.; Ardon, Roberto

doi:10.1007/978-3-642-40760-4_11

Cited by 9 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Briefly, automatic liver segmentation was performed by using an anatomic liver model derived from an independent dataset of 50 T1-weighted contrast-enhanced abdominal MR images. Probability maps of the liver’s location were determined by the random forest algorithm and weighted by organ atlases (26–29). The liver model then underwent implicit template deformation with a classic principal components analysis.…”

Section: Methodsmentioning

confidence: 99%

“…The control point editing was based on non-Euclidean geometry and the theory of radial functions (30), and the liver contour editing relied on voxel signal intensities and an edge-detection algorithm (31). The theories underlying the prototype software (eg, regression forests for organ localization, computed organ probability maps, and implicit template deformation for segmentation) have been previously validated in multiple large imaging databases of diverse organs (26–29). …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Imaging Biomarkers of Tumor Response in Neuroendocrine Liver Metastases Treated with Transarterial Chemoembolization: Can Enhancing Tumor Burden of the Whole Liver Help Predict Patient Survival?

et al. 2017

Self Cite

View full text Add to dashboard Cite

Purpose To investigate whether whole-liver enhancing tumor burden [ETB] can serve as an imaging biomarker and help predict survival better than World Health Organization (WHO), Response Evaluation Criteria in Solid Tumors (RECIST), modified RECIST (mRECIST), and European Association for the Study of the Liver (EASL) methods in patients with multifocal, bilobar neuroendocrine liver metastases (NELM) after the first transarterial chemoembolization (TACE) procedure. Materials and Methods This HIPAA-compliant, institutional review board–approved retrospective study included 51 patients (mean age, 57.8 years ± 13.2; range, 13.5–85.8 years) with multifocal, bilobar NELM treated with TACE. The largest area (WHO), longest diameter (RECIST), longest enhancing diameter (mRECIST), largest enhancing area (EASL), and largest enhancing volume (ETB) were measured at baseline and after the first TACE on contrast material–enhanced magnetic resonance images. With three-dimensional software, ETB was measured as more than 2 standard deviations the signal intensity of a region of interest in normal liver. Response was assessed with WHO, RECIST, mRECIST, and EASL methods according to their respective criteria. For ETB response, a decrease in enhancement of at least 30%, 50%, and 65% was analyzed by using the Akaike information criterion. Survival analysis included Kaplan-Meier curves and Cox regressions. Results Treatment response occurred in 5.9% (WHO criteria), 2.0% (RECIST), 25.5% (mRECIST), and 23.5% (EASL criteria) of patients. With 30%, 50%, and 65% cutoffs, ETB response was seen in 60.8%, 39.2%, and 21.6% of patients, respectively, and was the only biomarker associated with a survival difference between responders and nonresponders (45.0 months vs 10.0 months, 84.3 months vs 16.7 months, and 85.2 months vs 21.2 months, respectively; P < .01 for all). The 50% cutoff provided the best survival model (hazard ratio [HR]: 0.2; 95% confidence interval [CI]: 0.1, 0.4). At multivariate analysis, ETB response was an independent predictor of survival (HR: 0.2; 95% CI: 0.1, 0.6). Conclusion Volumetric ETB is an early treatment response biomarker and surrogate for survival in patients with multifocal, bilobar NELM after the first TACE procedure.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Imaging Biomarkers of Tumor Response in Neuroendocrine Liver Metastases Treated with Transarterial Chemoembolization: Can Enhancing Tumor Burden of the Whole Liver Help Predict Patient Survival?

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Active surface models operate on the same principle [38,39] but replace the contours by triangulated meshes to model 3D surfaces. They have proved very successful for medical [28,16] and cartographic applications [13], among others, and are still being improved [23,35,18].…”

Section: Active Contour and Surface Modelsmentioning

confidence: 99%

Deep Active Surface Models

Wickramasinghe¹,

Knott²,

Fua³

2020

Preprint

View full text Add to dashboard Cite

Active Surface Models have a long history of being useful to model complex 3D surfaces but only Active Contours have been used in conjunction with deep networks, and then only to produce the data term as well as meta-parameter maps controlling them. In this paper, we advocate a much tighter integration. We introduce layers that implement them that can be integrated seamlessly into Graph Convolutional Networks to enforce sophisticated smoothness priors at an acceptable computational cost.We will show that the resulting Deep Active Surface Models outperform equivalent architectures that use traditional regularization loss terms to impose smoothness priors for 3D surface reconstruction from 2D images and for 3D volume segmentation.

show abstract

“…A second set of methods uses the shape model S(θ S ) as a shape prior instead of a shape space. Several shape constraints have been introduced within several image segmentation frameworks including level-sets (Chan and Zhu, 2005;Cremers, 2003), free-form deformation space (Rueckert et al, 2003b) or implicit template deformation (Prevost et al, 2013). While those methods have greater shape flexibility for delineating structures, it is often difficult to set the coefficients weighting the shape constraint with other image terms.…”

Section: Introductionmentioning

confidence: 99%

Bayesian logistic shape model inference: Application to cochlear image segmentation

Wang

Demarcy²,

Vandersteen

et al. 2022

Medical Image Analysis

View full text Add to dashboard Cite

Incorporating shape information is essential for the delineation of many organs and anatomical structures in medical images. While previous work has mainly focused on parametric spatial transformations applied on reference template shapes, in this paper, we address the Bayesian inference of parametric shape models for segmenting medical images with the objective to provide interpretable results. The proposed framework defines a likelihood appearance probability and a prior label probability based on a generic shape function through a logistic function. A reference length parameter defined in the sigmoid controls the trade-off between shape and appearance information. The inference of shape parameters is performed within an Expectation-Maximisation approach where a Gauss-Newton optimization stage allows to provide an approximation of the posterior probability of shape parameters. This framework is applied to the segmentation of cochlea structures from clinical CT images constrained by a 10 parameter shape model. It is evaluated on three different datasets, one of which includes more than 200 patient images. The results show performances comparable to supervised methods and better than previously proposed unsupervised ones. It also enables an analysis of parameter distributions and the quantification of segmentation uncertainty including the effect of the shape model.

show abstract

Incorporating Shape Variability in Image Segmentation via Implicit Template Deformation

Cited by 9 publications

References 14 publications

Imaging Biomarkers of Tumor Response in Neuroendocrine Liver Metastases Treated with Transarterial Chemoembolization: Can Enhancing Tumor Burden of the Whole Liver Help Predict Patient Survival?

Imaging Biomarkers of Tumor Response in Neuroendocrine Liver Metastases Treated with Transarterial Chemoembolization: Can Enhancing Tumor Burden of the Whole Liver Help Predict Patient Survival?

Deep Active Surface Models

Bayesian logistic shape model inference: Application to cochlear image segmentation

Contact Info

Product

Resources

About