Novelty Detection for Breast Cancer Image Classification

Using classification learning algorithms for medical diagnosis may
require not only refined model creation techniques and careful
unbiased model evaluation, but also detecting the risk of
misclassification at the time of model application. This is
addressed by novelty detection, which identifies instances for which
the training set is not sufficiently representative and for which it
may be safer to restrain from classification and request a human
expert diagnosis. The paper presents two techniques for isolated
instance identification, based on clustering and one-class support
vector machines, which represent two different approaches to
multidimensional outlier detection. The prediction quality for
isolated instances is evaluated using a random forest algorithm
applied to breast cancer diagnosis image data and found to be substantially
inferior to the prediction quality for non-isolated instances. Each of
the two techniques is then used to create a novelty detection model which
can be combined with a classification model and used at the time of
prediction to detect instances for which the latter cannot be
reliably applied. Novelty detection is demonstrated to improve
random forest prediction quality and argued to deserve further
investigation in medical diagnosis applications.

Author: Pawel Cichosz
Conference: Title