4.6k citations · 4.7k across the 17 of their papers we have counts for
18 papers
Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos
Luca Parolari, Pietro Gori, Lamberto Ballan +2
Learning robust representations of polyp tracklets is key to enabling multiple AI-assisted colonoscopy applications, from polyp characterization to automated reporting and retrieva…
Unsupervised Domain Adaptation with Target-Only Margin Disparity Discrepancy
Gauthier Miralles, Loïc Le Folgoc, Vincent Jugnon +1
In interventional radiology, Cone-Beam Computed Tomography (CBCT) is a helpful imaging modality that provides guidance to practicians during minimally invasive procedures. CBCT dif…
Reducing Variability of Multiple Instance Learning Methods for Digital Pathology
Ali Mammadov, Loïc Le Folgoc, Guillaume Hocquet +1
Digital pathology has revolutionized the field by enabling the digitization of tissue samples into whole slide images (WSIs). However, the high resolution and large size of WSIs pr…
Dense Self-Supervised Learning for Medical Image Segmentation
Maxime Seince, Loic Le Folgoc, Luiz Augusto Facury de Souza +1
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-l…
Evaluation of 3D GANs for Lung Tissue Modelling in Pulmonary CT
Sam Ellis, Octavio E. Martinez Manzanera, Vasileios Baltatzis +6
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 med…
Uncertainty quantification in non-rigid image registration via stochastic gradient Markov chain Monte Carlo
Daniel Grzech, Mohammad Farid Azampour, Huaqi Qiu +3
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 imag…
Is MC Dropout Bayesian?
Loic Le Folgoc, Vasileios Baltatzis, Sujal Desai +7
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 un…
The Pitfalls of Sample Selection: A Case Study on Lung Nodule Classification
Vasileios Baltatzis, Kyriaki-Margarita Bintsi, Loic Le Folgoc +6
Using publicly available data to determine the performance of methodological contributions is important as it facilitates reproducibility and allows scrutiny of the published resul…
The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data
Vasileios Baltatzis, Loic Le Folgoc, Sam Ellis +6
Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging. While most studies deploy cross-entropy as the loss…
Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data
Loic Le Folgoc, Vasileios Baltatzis, Amir Alansary +8
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…
Geometric Deep Learning for Post-Menstrual Age Prediction based on the Neonatal White Matter Cortical Surface
Vitalis Vosylius, Andy Wang, Cemlyn Waters +8
Accurate estimation of the age in neonates is essential for measuring neurodevelopmental, medical, and growth outcomes. In this paper, we propose a novel approach to predict the po…
Bayesian Sampling Bias Correction: Training with the Right Loss Function
L. Le Folgoc, V. Baltatzis, A. Alansary +8
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 trainin…
Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
Miguel Monteiro, Loïc Le Folgoc, Daniel Coelho de Castro +5
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 o…
FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms
Daniel Grzech, Loïc le Folgoc, Mattias P. Heinrich +5
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 wit…
Controlling Meshes via Curvature: Spin Transformations for Pose-Invariant Shape Processing
Loic Le Folgoc, Daniel C. Castro, Jeremy Tan +5
We investigate discrete spin transformations, a geometric framework to manipulate surface meshes by controlling mean curvature. Applications include surface fairing -- flowing a me…
Semi-Supervised Learning via Compact Latent Space Clustering
Konstantinos Kamnitsas, Daniel C. Castro, Loic Le Folgoc +6
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…
Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents
Amir Alansary, Loic Le Folgoc, Ghislain Vaillant +11
We propose a fully automatic method to find standardized view planes in 3D image acquisitions. Standard view images are important in clinical practice as they provide a means to pe…
Attention U-Net: Learning Where to Look for the Pancreas
Ozan Oktay, Jo Schlemper, Loic Le Folgoc +9
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 implic…