activity
20222024
most citedLong-term Dependency for 3D Reconstruction of Freehand Ultrasound Without External Tracker

20 citations · 49 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images

Martynas Pocius, Wen Yan, Dean C. Barratt +4

In this paper we propose a reinforcement learning based weakly supervised system for localisation. We train a controller function to localise regions of interest within an image by…

cs.CV2023

Boundary-RL: Reinforcement Learning for Weakly-Supervised Prostate Segmentation in TRUS Images

Weixi Yi, Vasilis Stavrinides, Zachary M. C. Baum +5

We propose Boundary-RL, a novel weakly supervised segmentation method that utilises only patch-level labels for training. We envision the segmentation as a boundary detection probl…

cs.CV20231 cited

Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction

Qi Li, Ziyi Shen, Qian Li +5

Three-dimensional (3D) freehand ultrasound (US) reconstruction without using any additional external tracking device has seen recent advances with deep neural networks (DNNs). In t…

cs.CV202215 cited

Cross-Modality Image Registration using a Training-Time Privileged Third Modality

Qianye Yang, David Atkinson, Yunguan Fu +7

In this work, we consider the task of pairwise cross-modality image registration, which may benefit from exploiting additional images available only at training time from an additi…

cs.CV2022

Meta-Registration: Learning Test-Time Optimization for Single-Pair Image Registration

Zachary MC Baum, Yipeng Hu, Dean C Barratt

Neural networks have been proposed for medical image registration by learning, with a substantial amount of training data, the optimal transformations between image pairs. These tr…

cs.CV2022

Learning Generalized Non-Rigid Multimodal Biomedical Image Registration from Generic Point Set Data

Zachary MC Baum, Tamas Ungi, Christopher Schlenger +2

Free Point Transformer (FPT) has been proposed as a data-driven, non-rigid point set registration approach using deep neural networks. As FPT does not assume constraints based on p…