2.7k citations · 9.2k across the 86 of their papers we have counts for
14 papers · 1 filter
Partial supervision for the FeTA challenge 2021
Lucas Fidon, Michael Aertsen, Suprosanna Shit +4
This paper describes our method for our participation in the FeTA challenge2021 (team name: TRABIT). The performance of convolutional neural networks for medical image segmentation…
Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction
Martin Huber, Sébastien Ourselin, Christos Bergeles +1
Current laparoscopic camera motion automation relies on rule-based approaches or only focuses on surgical tools. Imitation Learning (IL) methods could alleviate these shortcomings,…
Homography-based Visual Servoing with Remote Center of Motion for Semi-autonomous Robotic Endoscope Manipulation
Martin Huber, John Bason Mitchell, Ross Henry +3
The dominant visual servoing approaches in Minimally Invasive Surgery (MIS) follow single points or adapt the endoscope's field of view based on the surgical tools' distance. These…
Interactive Segmentation via Deep Learning and B-Spline Explicit Active Surfaces
Helena Williams, João Pedrosa, Laura Cattani +4
Automatic medical image segmentation via convolutional neural networks (CNNs) has shown promising results. However, they may not always be robust enough for clinical use. Sub-optim…
Deep Learning Approach for Hyperspectral Image Demosaicking, Spectral Correction and High-resolution RGB Reconstruction
Peichao Li, Michael Ebner, Philip Noonan +5
Hyperspectral imaging is one of the most promising techniques for intraoperative tissue characterisation. Snapshot mosaic cameras, which can capture hyperspectral data in a single…
Distributionally Robust Segmentation of Abnormal Fetal Brain 3D MRI
Lucas Fidon, Michael Aertsen, Nada Mufti +13
The performance of deep neural networks typically increases with the number of training images. However, not all images have the same importance towards improved performance and ro…
Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation
Lucas Fidon, Michael Aertsen, Doaa Emam +9
Deep neural networks have increased the accuracy of automatic segmentation, however, their accuracy depends on the availability of a large number of fully segmented images. Methods…
Methodology development and evaluation of optical properties characterisation of small size tissue samples
Yijing Xie, Jonathan Shapey, Eli Nabavi +4
Integrating sphere (IS) techniques combined with an inverse adding doubling (IAD) algorithm have been widely used for determination of optical properties of ex vivo tissues. Semi-i…
Robotic Endoscope Control via Autonomous Instrument Tracking
Caspar Gruijthuijsen, Luis C. Garcia-Peraza-Herrera, Gianni Borghesan +5
Many keyhole interventions rely on bi-manual handling of surgical instruments, forcing the main surgeon to rely on a second surgeon to act as a camera assistant. In addition to the…
Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation
Reuben Dorent, Samuel Joutard, Jonathan Shapey +4
We introduce , a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks…
Video-rate dual-modal forward-viewing photoacoustic and fluorescence endo-microscopy through a multimode fibre
Tianrui Zhao, Michelle T. Ma, Sebastien Ourselin +2
Multimode fibres are becoming increasingly attractive in optical endoscopy as they promise to enable unparalleled miniaturisation, spatial resolution and cost as compared to conven…
MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning
Xiangde Luo, Guotai Wang, Tao Song +6
Segmentation of organs or lesions from medical images plays an essential role in many clinical applications such as diagnosis and treatment planning. Though Convolutional Neural Ne…
Intrapapillary Capillary Loop Classification in Magnification Endoscopy: Open Dataset and Baseline Methodology
Luis C. Garcia-Peraza-Herrera, Martin Everson, Laurence Lovat +6
Purpose. Early squamous cell neoplasia (ESCN) in the oesophagus is a highly treatable condition. Lesions confined to the mucosal layer can be curatively treated endoscopically. We…
Scale factor point spread function matching: Beyond aliasing in image resampling
M. Jorge Cardoso, Marc Modat, Tom Vercauteren +1
Imaging devices exploit the Nyquist-Shannon sampling theorem to avoid both aliasing and redundant oversampling by design. Conversely, in medical image resampling, images are consid…