Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Enzo Ferrante

Enzo Ferrante

Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis



Nicolás Gaggion , Lucas Mansilla , Candelaria Mosquera , Diego H. Milone , Enzo Ferrante

Figure 1 for Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis
Figure 2 for Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis
Figure 3 for Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis
Figure 4 for Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis
* Source code at https://github.com/ngaggion/HybridGNet 
   Access Paper or Ask Questions

SUD: Supervision by Denoising for Medical Image Segmentation



Sean I. Young , Adrian V. Dalca , Enzo Ferrante , Polina Golland , Bruce Fischl , Juan Eugenio Iglesias

* Author's manuscript for IEEE Trans. Pattern Anal. Mach. Intell 
   Access Paper or Ask Questions

Understanding the impact of class imbalance on the performance of chest x-ray image classifiers



Candelaria Mosquera , Luciana Ferrer , Diego Milone , Daniel Luna , Enzo Ferrante

Figure 1 for Understanding the impact of class imbalance on the performance of chest x-ray image classifiers
Figure 2 for Understanding the impact of class imbalance on the performance of chest x-ray image classifiers
Figure 3 for Understanding the impact of class imbalance on the performance of chest x-ray image classifiers
Figure 4 for Understanding the impact of class imbalance on the performance of chest x-ray image classifiers

   Access Paper or Ask Questions

Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation



Agostina Larrazabal , Cesar Martinez , Jose Dolz , Enzo Ferrante

Figure 1 for Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation
Figure 2 for Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation
Figure 3 for Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation
Figure 4 for Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation

   Access Paper or Ask Questions

Domain Generalization via Gradient Surgery



Lucas Mansilla , Rodrigo Echeveste , Diego H. Milone , Enzo Ferrante

Figure 1 for Domain Generalization via Gradient Surgery
Figure 2 for Domain Generalization via Gradient Surgery
Figure 3 for Domain Generalization via Gradient Surgery
Figure 4 for Domain Generalization via Gradient Surgery
* Accepted for publication at ICCV 2021 
   Access Paper or Ask Questions

Hybrid graph convolutional neural networks for landmark-based anatomical segmentation



Nicolás Gaggion , Lucas Mansilla , Diego Milone , Enzo Ferrante

Figure 1 for Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
Figure 2 for Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
Figure 3 for Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
Figure 4 for Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
* Accepted for publication at MICCAI 2021 
   Access Paper or Ask Questions

Orthogonal Ensemble Networks for Biomedical Image Segmentation



Agostina J. Larrazabal , CĂ©sar MartĂ­nez , Jose Dolz , Enzo Ferrante

Figure 1 for Orthogonal Ensemble Networks for Biomedical Image Segmentation
Figure 2 for Orthogonal Ensemble Networks for Biomedical Image Segmentation
Figure 3 for Orthogonal Ensemble Networks for Biomedical Image Segmentation
* Accepted for publication at MICCAI 2021 
   Access Paper or Ask Questions

Cranial Implant Design via Virtual Craniectomy with Shape Priors



Franco Matzkin , Virginia Newcombe , Ben Glocker , Enzo Ferrante

Figure 1 for Cranial Implant Design via Virtual Craniectomy with Shape Priors
Figure 2 for Cranial Implant Design via Virtual Craniectomy with Shape Priors
Figure 3 for Cranial Implant Design via Virtual Craniectomy with Shape Priors
Figure 4 for Cranial Implant Design via Virtual Craniectomy with Shape Priors

   Access Paper or Ask Questions

Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images



Julian Alberto Palladino , Diego Fernandez Slezak , Enzo Ferrante

Figure 1 for Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images
Figure 2 for Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images
Figure 3 for Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images
Figure 4 for Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images
* Accepted for publication in the International Seminar on Medical Information Processing and Analysis (SIPAIM 2020) 
   Access Paper or Ask Questions

Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy



Franco Matzkin , Virginia Newcombe , Susan Stevenson , Aneesh Khetani , Tom Newman , Richard Digby , Andrew Stevens , Ben Glocker , Enzo Ferrante

Figure 1 for Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy
Figure 2 for Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy
Figure 3 for Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy
Figure 4 for Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy
* Accepted for publication in MICCAI 2020. Update: Figure 1 corrected to match description 
   Access Paper or Ask Questions
1
2
3
>>