299 citations
- King's College LondonGB86 papers
- King's College - North CarolinaUS13 papers
- Imperial College LondonGB6 papers
- University College LondonGB6 papers
- European Organization for Nuclear ResearchCH5 papers
- Queen Mary University of LondonGB5 papers
- University of CambridgeGB5 papers
- University of OxfordGB5 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Guy's and St Thomas' NHS Foundation TrustGB4 papers
- King's College Hospital NHS Foundation TrustGB4 papers
- St Thomas' HospitalGB4 papers
7 papers · 1 filter
Long-term Dependency for 3D Reconstruction of Freehand Ultrasound Without External Tracker
Qi Li, Ziyi Shen, Qian Li +5
Objective: Reconstructing freehand ultrasound in 3D without any external tracker has been a long-standing challenge in ultrasound-assisted procedures. We aim to define new ways of…
An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
Minkyung Kim, Jongmin Yu, Junsik Kim +2
Most deep anomaly detection models are based on learning normality from datasets due to the difficulty of defining abnormality by its diverse and inconsistent nature. Therefore, it…
Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images
Tareen Dawood, Chen Chen, Baldeep S. Sidhua +9
Quantifying uncertainty of predictions has been identified as one way to develop more trustworthy artificial intelligence (AI) models beyond conventional reporting of performance m…
Deep Homography Prediction for Endoscopic Camera Motion Imitation Learning
Martin Huber, Sebastien Ourselin, Christos Bergeles +1
In this work, we investigate laparoscopic camera motion automation through imitation learning from retrospective videos of laparoscopic interventions. A novel method is introduced…
Spatial gradient consistency for unsupervised learning of hyperspectral demosaicking: Application to surgical imaging
Peichao Li, Muhammad Asad, Conor Horgan +3
Hyperspectral imaging has the potential to improve intraoperative decision making if tissue characterisation is performed in real-time and with high-resolution. Hyperspectral snaps…
Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics
Minkyung Kim, Junsik Kim, Jongmin Yu +1
One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In pr…