Supervised novelty detection in brain tissue classification with an application to white matter hyperintensities

Hugo J. Kuijf, Pim Moeskops, Bob D. de Vos, Willem H. Bouvy, Jeroen de Bresser, Geert Jan Biessels, Max A. Viergever, Koen L. Vincken

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

6 Citations (Scopus)
2 Downloads (Pure)


Novelty detection is concerned with identifying test data that differs from the training data of a classifier. In the case of brain MR images, pathology or imaging artefacts are examples of untrained data. In this proof-of-principle study, we measure the behaviour of a classifier during the classification of trained labels (i.e. normal brain tissue). Next, we devise a measure that distinguishes normal classifier behaviour from abnormal behavior that occurs in the case of a novelty. This will be evaluated by training a kNN classifier on normal brain tissue, applying it to images with an untrained pathology (white matter hyperintensities (WMH)), and determine if our measure is able to identify abnormal classifier behaviour at WMH locations. For our kNN classifier, behaviour is modelled as the mean, median, or q1 distance to the k nearest points. Healthy tissue was trained on 15 images; classifier behaviour was trained/tested on 5 images with leave-one-out cross-validation. For each trained class, we measure the distribution of mean/median/q1 distances to the k nearest point. Next, for each test voxel, we compute its Z-score with respect to the measured distribution of its predicted label. We consider a Z-score ≥4 abnormal behaviour of the classifier, having a probability due to chance of 0.000032. Our measure identified >90% of WMH volume and also highlighted other non-trained findings. The latter being predominantly vessels, cerebral falx, brain mask errors, choroid plexus. This measure is generalizable to other classifiers and might help in detecting unexpected findings or novelties by measuring classifier behaviour.
Original languageEnglish
Title of host publicationMedical Imaging 2016 : Image Processing. 1-3 March 2016, San Diego, California, United States
EditorsA. Styner, E.D. Angelini
Place of PublicationBellingham
Number of pages7
ISBN (Electronic)9781510600195
Publication statusPublished - Feb 2016
Externally publishedYes
EventSPIE Medical Imaging 2016 - San Diego, United States
Duration: 27 Feb 20163 Mar 2016

Publication series

NameProceedings of SPIE
ISSN (Electronic)0277-786X


ConferenceSPIE Medical Imaging 2016
Country/TerritoryUnited States
CitySan Diego
OtherComputer-Aided Diagnosis

Cite this