Loïc Le Folgoc
YOU?
Author Swipe
View article: Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study
Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study Open
Multiple Instance Learning (MIL) has emerged as the best solution for Whole Slide Image (WSI) classification. It consists of dividing each slide into patches, which are treated as a bag of instances labeled with a global label. MIL include…
View article: Dense Self-Supervised Learning for Medical Image Segmentation
Dense Self-Supervised Learning for Medical Image Segmentation Open
Deep learning has revolutionized medical image segmentation, but it relies heavily on high-quality annotations. The time, cost and expertise required to label images at the pixel-level for each new task has slowed down widespread adoption …
View article: Evaluation of 3D GANs for Lung Tissue Modelling in Pulmonary CT
Evaluation of 3D GANs for Lung Tissue Modelling in Pulmonary CT Open
Generative adversarial networks (GANs) are able to model accurately the distribution of complex, high-dimensional datasets, for example images. This characteristic makes high-quality GANs useful for unsupervised anomaly detection in medica…
View article: Evaluation of 3D GANs for Lung Tissue Modelling in Pulmonary CT
Evaluation of 3D GANs for Lung Tissue Modelling in Pulmonary CT Open
GANs are able to model accurately the distribution of complex, high-dimensional datasets, e.g. images. This makes high-quality GANs useful for unsupervised anomaly detection in medical imaging. However, differences in training datasets suc…
View article: Uncertainty quantification in non-rigid image registration via stochastic gradient Markov chain Monte Carlo
Uncertainty quantification in non-rigid image registration via stochastic gradient Markov chain Monte Carlo Open
We develop a new Bayesian model for non-rigid registration of three-dimensional medical images, with a focus on uncertainty quantification. Probabilistic registration of large images with calibrated uncertainty estimates is difficult for b…
View article: Is MC Dropout Bayesian
Is MC Dropout Bayesian Open
MC Dropout is a mainstream free lunch method in medical imaging for approximate Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC and uncertainty quantification in Neural Networks (NNs); to fall wi…
View article: Is MC Dropout Bayesian?
Is MC Dropout Bayesian? Open
MC Dropout is a mainstream "free lunch" method in medical imaging for approximate Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC and uncertainty quantification in Neural Networks (NNs); to fall …
View article: Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data
Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data Open
Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for m…
View article: Bayesian Sampling Bias Correction: Training with the Right Loss Function
Bayesian Sampling Bias Correction: Training with the Right Loss Function Open
We derive a family of loss functions to train models in the presence of sampling bias. Examples are when the prevalence of a pathology differs from its sampling rate in the training dataset, or when a machine learning practioner rebalances…
View article: Stochastic segmentation networks: modelling spatially correlated aleatoric uncertainty
Stochastic segmentation networks: modelling spatially correlated aleatoric uncertainty Open
In image segmentation, there is often more than one plausible solution for a given input. In medical imaging, for example, experts will often disagree about the exact location of object boundaries. Estimating this inherent uncertainty and …
View article: Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty Open
In image segmentation, there is often more than one plausible solution for a given input. In medical imaging, for example, experts will often disagree about the exact location of object boundaries. Estimating this inherent uncertainty and …
View article: Explainable Anatomical Shape Analysis Through Deep Hierarchical Generative Models
Explainable Anatomical Shape Analysis Through Deep Hierarchical Generative Models Open
Quantification of anatomical shape changes currently relies on scalar global indexes which are largely insensitive to regional or asymmetric modifications. Accurate assessment of pathology-driven anatomical remodeling is a crucial step for…
View article: Explainable Anatomical Shape Analysis through Deep Hierarchical\n Generative Models
Explainable Anatomical Shape Analysis through Deep Hierarchical\n Generative Models Open
Quantification of anatomical shape changes currently relies on scalar global\nindexes which are largely insensitive to regional or asymmetric modifications.\nAccurate assessment of pathology-driven anatomical remodeling is a crucial step\n…
View article: FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms
FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms Open
We present an implementation of a new approach to diffeomorphic non-rigid registration of medical images. The method is based on optical flow and warps images via gradient flow with the standard $L^2$ inner product. To compute the transfor…
View article: FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the\n Manifold of Diffeomorphisms
FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the\n Manifold of Diffeomorphisms Open
We present an implementation of a new approach to diffeomorphic non-rigid\nregistration of medical images. The method is based on optical flow and warps\nimages via gradient flow with the standard $L^2$ inner product. To compute the\ntrans…
View article: Semi-Supervised Learning via Compact Latent Space Clustering
Semi-Supervised Learning via Compact Latent Space Clustering Open
We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation. The key idea is to dynamically create a graph over embeddings of labeled and …
View article: Attention U-Net: Learning Where to Look for the Pancreas
Attention U-Net: Learning Where to Look for the Pancreas Open
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implicitly learn to suppress irrelevant regions in an input image…
View article: Quantifying Registration Uncertainty With Sparse Bayesian Modelling
Quantifying Registration Uncertainty With Sparse Bayesian Modelling Open
We investigate uncertainty quantification under a sparse Bayesian model of medical image registration. Bayesian modelling has proven powerful to automate the tuning of registration hyperparameters, such as the trade-off between the data an…