Universität zu Köln

Hekler, Achim, Utikal, Jochen S., Enk, Alexander H., Solass, Wiebke ORCID: 0000-0002-6639-1935, Schmitt, Max, Klode, Joachim, Schadendorf, Dirk ORCID: 0000-0003-3524-7858, Sondermann, Wiebke, Franklin, Cindy, Bestvater, Felix, Flaig, Michael J., Krahl, Dieter, von Kalle, Christof, Froehling, Stefan and Brinker, Titus J. (2019). Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images. Eur. J. Cancer, 118. S. 91 - 97. OXFORD: ELSEVIER SCI LTD. ISSN 1879-0852

Full text not available from this repository.

Abstract

Background: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports on 25-26% of discordance for classifying a benign nevus versus malignant melanoma. A recent study indicated the potential of deep learning to lower these discordances. However, the performance of deep learning in classifying histopathologic melanoma images was never compared directly to human experts. The aim of this study is to perform such a first direct comparison. Methods: A total of 695 lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi/345 melanoma). Only the haematoxylin & eosin (H&E) slides of these lesions were digitalised via a slide scanner and then randomly cropped. A total of 595 of the resulting images were used to train a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison to 11 histopathologists. Three combined McNemar tests comparing the results of the CNNs test runs in terms of sensitivity, specificity and accuracy were predefined to test for significance (p < 0.05). Findings: The CNN achieved a mean sensitivity/specificity/accuracy of 76%/60%/68% over 11 test runs. In comparison, the 11 pathologists achieved a mean sensitivity/specificity/accuracy of 51.8%/66.5%/59.2%. Thus, the CNN was significantly (p = 0.016) superior in classifying the cropped images. Interpretation: With limited image information available, a CNN was able to outperform 11 histopathologists in the classification of histopathological melanoma images and thus shows promise to assist human melanoma diagnoses. (C) 2019 The Author(s). Published by Elsevier Ltd.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Hekler, Achim UNSPECIFIED UNSPECIFIED UNSPECIFIED Utikal, Jochen S. UNSPECIFIED UNSPECIFIED UNSPECIFIED Enk, Alexander H. UNSPECIFIED UNSPECIFIED UNSPECIFIED Solass, Wiebke UNSPECIFIED orcid.org/0000-0002-6639-1935 UNSPECIFIED Schmitt, Max UNSPECIFIED UNSPECIFIED UNSPECIFIED Klode, Joachim UNSPECIFIED UNSPECIFIED UNSPECIFIED Schadendorf, Dirk UNSPECIFIED orcid.org/0000-0003-3524-7858 UNSPECIFIED Sondermann, Wiebke UNSPECIFIED UNSPECIFIED UNSPECIFIED Franklin, Cindy UNSPECIFIED UNSPECIFIED UNSPECIFIED Bestvater, Felix UNSPECIFIED UNSPECIFIED UNSPECIFIED Flaig, Michael J. UNSPECIFIED UNSPECIFIED UNSPECIFIED Krahl, Dieter UNSPECIFIED UNSPECIFIED UNSPECIFIED von Kalle, Christof UNSPECIFIED UNSPECIFIED UNSPECIFIED Froehling, Stefan UNSPECIFIED UNSPECIFIED UNSPECIFIED Brinker, Titus J. UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-143591
DOI:	10.1016/j.ejca.2019.06.012
Journal or Publication Title:	Eur. J. Cancer
Volume:	118
Page Range:	S. 91 - 97
Date:	2019
Publisher:	ELSEVIER SCI LTD
Place of Publication:	OXFORD
ISSN:	1879-0852
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language DIGITAL PATHOLOGY; DERMATOLOGISTS; DIAGNOSIS; ALGORITHMS Multiple languages Oncology Multiple languages
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/14359