Deep Reinforcement Learning for Detection of Abnormal Anatomies

Paula López Diez*, Kristine Aavild Juhl , Josefine Vilsbøll Sundgaard, Hassan Diab, Jan Margeta, Francois Patou, Rasmus Reinhold Paulsen

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

56 Downloads (Pure)


Automatic detection of abnormal anatomies or malformations of different structures of the human body is a challenging task that could provide support for clinicians in their daily practice. Compared to normative anatomies, there is a low presence of anatomical abnormalities in patients, and the great variation within malformations make it challenging to design deep learning frameworks for automatic detection. We propose a framework for anatomical abnormality detection, which benefits from using a deep reinforcement learning model for landmark detection trained in normative data. We detect the abnormalities using the variability between the predicted landmarks configurations in a subspace based on a point distribution model of landmarks using Procrustes shape alignment and principal component analysis projection from normative data. We demonstrate the performance of this implementation on clinical CT scans of the inner ear, and show how synthetically created abnormal cochlea anatomy can be detected using the prediction of five landmarks around the cochlea. Our approach shows a Receiver Operating Characteristics (ROC) Area Under The Curve (AUC) of 0.97, and 96% accuracy for the detection of abnormal anatomy on synthetic data.
Original languageEnglish
JournalProceedings of the Northern Lights Deep Learning Workshop
Number of pages8
Publication statusPublished - 2022
EventNorthern Lights Deep Learning Workshop 2022 - Tromsø, Norway
Duration: 10 Jan 202212 Jan 2022


ConferenceNorthern Lights Deep Learning Workshop 2022


  • Deep reinforcement learning
  • Landmarks
  • Anomaly detection
  • Medical image
  • Inner ear
  • PCA
  • Procrustes
  • C-MARL
  • CT


Dive into the research topics of 'Deep Reinforcement Learning for Detection of Abnormal Anatomies'. Together they form a unique fingerprint.

Cite this