@article{DBLP:journals/mia/AlansaryOLFHVKV19,
  author    = {Amir Alansary and
               Ozan Oktay and
               Yuanwei Li and
               Lo{\"{\i}}c Le Folgoc and
               Benjamin Hou and
               Ghislain Vaillant and
               Konstantinos Kamnitsas and
               Athanasios Vlontzos and
               Ben Glocker and
               Bernhard Kainz and
               Daniel Rueckert},
  title     = {Evaluating reinforcement learning agents for anatomical landmark detection},
  journal   = {Medical Image Anal.},
  volume    = {53},
  pages     = {156--164},
  year      = {2019},
  doi = {10.1016/j.media.2019.02.007},
  url = {https://doi.org/10.1016/j.media.2019.02.007},
  code = {https://github.com/amiralansary/rl-medical},
  abstract = {Automatic anatomical-landmark detection is important for many medical-image-analysis applications, but manual annotation is time-consuming and prone to observer error. This study evaluates deep reinforcement-learning strategies that train agents to localize landmarks in three-dimensional scans. It compares fixed- and multiscale search, hierarchical coarse-to-fine actions and several deep Q-network architectures across fetal ultrasound, adult brain MRI and cardiac MRI. The proposed agents outperform supervised and reinforcement-learning baselines, while hierarchical steps accelerate search by a factor of four to five.},
}