Authors:
Rune Wetteland
1
;
Kjersti Engan
1
;
Trygve Eftestøl
1
;
Vebjørn Kvikstad
2
and
Emilius A. M. Janssen
3
Affiliations:
1
Department of Electrical Engineering and Computer Science, University of Stavanger and Norway
;
2
Department of Pathology, Stavanger University Hospital and Norway
;
3
Department of Pathology, Stavanger University Hospital, Norway, Department of Mathematics and Natural Sciences, University of Stavanger and Norway
Keyword(s):
Histological Whole-Slide Images, Autoencoder, Deep Learning, Semi-supervised Learning, ROI Extraction.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Medical Imaging
;
Pattern Recognition
;
Software Engineering
Abstract:
Globally there has been an enormous increase in bladder cancer incidents the past decades. Correct prognosis of recurrence and progression is essential to avoid under- or over-treatment of the patient, as well as unnecessary suffering and cost. To diagnose the cancer grade and stage, pathologists study the histological images. However, this is a time-consuming process and reproducibility among pathologists is low. A first stage for an automated diagnosis system can be to identify the diagnostical relevant areas in the histological whole-slide images (WSI), segmenting cell tissue from damaged areas, blood, background, etc. In this work, a method for automatic classification of urothelial carcinoma into six different classes is proposed. The method is based on convolutional neural networks (CNN), firstly trained unsupervised using unlabelled images by utilising an autoencoder (AE). A smaller set of labelled images are used to train the final fully-connected layers from the low dimensio
nal latent vector of the AE, providing an output as a probability score for each of the six classes, suitable for automatically defining regions of interests in WSI. For evaluation, each tile is classified as the class with the highest probability score. The model achieved an average F1-score of 93.4% over all six classes.
(More)