PuSH - Publication Server of Helmholtz Zentrum München

Sadafi, A. ; Koehler, N. ; Makhro, A.* ; Bogdanova, A.* ; Navab, N.* ; Marr, C. ; Peng, T.

Multiclass deep active learning for detecting red blood cell subtypes in brightfield microscopy.

Lect. Notes Comput. Sc. 11764 LNCS, 685-693 (2019)
Postprint DOI Order publishers version
Open Access Green
The recent success of deep learning approaches relies partly on large amounts of well annotated training data. For natural images object annotation is easy and cheap. For biomedical images however, annotation crucially depends on the availability of a trained expert whose time is typically expensive and scarce. To ensure efficient annotation, only the most relevant objects should be presented to the expert. Currently, no approach exists that allows to select those for a multiclass detection problem. Here, we present an active learning framework that identifies the most relevant samples from a large set of not annotated data for further expert annotation. Applied to brightfield images of red blood cells with seven subtypes, we train a faster R-CNN for single cell identification and classification, calculate a novel confidence score using dropout variational inference and select relevant images for annotation based on (i) the confidence of the single cell detection and (ii) the rareness of the classes contained in the image. We show that our approach leads to a drastic increase of prediction accuracy with already few annotated images. Our original approach improves classification of red blood cell subtypes and speeds up the annotation. This important step in diagnosing blood diseases will profit from our framework as well as many other clinical challenges that suffer from the lack of annotated training data.
Additional Metrics?
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords Active Learning ; Multiclass Annotation ; Single Cell Microscopy
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Quellenangaben Volume: 11764 LNCS, Issue: , Pages: 685-693 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]