A
Athanasios Vlontzos
Researcher at Imperial College London
Publications - 32
Citations - 328
Athanasios Vlontzos is an academic researcher from Imperial College London. The author has contributed to research in topics: Computer science & Reinforcement learning. The author has an hindex of 5, co-authored 25 publications receiving 174 citations.
Papers
More filters
Journal ArticleDOI
Evaluating reinforcement learning agents for anatomical landmark detection.
Amir Alansary,Ozan Oktay,Yuanwei Li,Loic Le Folgoc,Benjamin Hou,Ghislain Vaillant,Konstantinos Kamnitsas,Athanasios Vlontzos,Ben Glocker,Bernhard Kainz,Daniel Rueckert +10 more
TL;DR: Novel deep reinforcement learning (RL) strategies to train agents that can precisely and robustly localize target landmarks in medical scans are evaluated and the performance of these agents surpasses state‐of‐the‐art supervised and RL methods.
Book ChapterDOI
Multiple Landmark Detection Using Multi-agent Reinforcement Learning
TL;DR: In this article, a multi-agent reinforcement learning (MARL) approach is proposed to detect anatomical landmarks in medical images, where agents collaborate by sharing their accumulated knowledge for a collective gain.
Posted Content
Multiple Landmark Detection using Multi-Agent Reinforcement Learning
TL;DR: A new detection approach for multiple landmarks based on multi-agent reinforcement learning based on the hypothesis that the position of all anatomical landmarks is interdependent and non-random within the human anatomy, thus finding one landmark can help to deduce the location of others.
Proceedings ArticleDOI
Unsupervised Human Pose Estimation through Transforming Shape Templates
TL;DR: In this paper, a learnable template matching problem facilitated by deep feature extractors is proposed to estimate human-interpretable landmarks by transforming a template consisting of predefined body parts that are characterized by 2D Gaussian distributions.
Book ChapterDOI
Ultrasound Video Summarization using Deep Reinforcement Learning
TL;DR: This paper introduces a novel, fully automatic video summarization method that is tailored to the needs of medical video data, framed as reinforcement learning problem and produces agents focusing on the preservation of important diagnostic information.