Comparison of deep learning approaches for multi-label chest X-ray classification

Gespeichert in:

Veröffentlicht in:	Scientific reports Vol. 9.2019, Article number 6381, insgesamt 10 Seiten
Personen und Körperschaften:	Baltruschat, Ivo M. (VerfasserIn), Nickisch, Hannes (VerfasserIn), Graß, Michael (VerfasserIn), Knopp, Tobias (VerfasserIn), Saalbach, Axel (VerfasserIn), Technische Universität Hamburg (Sonstige), Institute for Biomedical Imaging (Sonstige)
Titel:	Comparison of deep learning approaches for multi-label chest X-ray classification/ Ivo M. Baltruschat, Hannes Nickisch, Michael Grass, Tobias Knopp & Axel Saalbach
Format:	E-Book-Kapitel
Sprache:	Englisch
veröffentlicht:	2019
Gesamtaufnahme:	: Scientific reports, Vol. 9.2019, Article number 6381, insgesamt 10 Seiten , volume:9
Quelle:	Verbunddaten SWB Lizenzfreie Online-Ressourcen

Details
Zusammenfassung:	The increased availability of labeled X-ray image archives (e.g. ChestX-ray14 dataset) has triggered a growing interest in deep learning techniques. To provide better insight into the different approaches, and their applications to chest X-ray classification, we investigate a powerful network architecture in detail: the ResNet-50. Building on prior work in this domain, we consider transfer learning with and without fine-tuning as well as the training of a dedicated X-ray network from scratch. To leverage the high spatial resolution of X-ray data, we also include an extended ResNet-50 architecture, and a network integrating non-image data (patient age, gender and acquisition type) in the classification process. In a concluding experiment, we also investigate multiple ResNet depths (i.e. ResNet-38 and ResNet-101). In a systematic evaluation, using 5-fold re-sampling and a multi-label loss function, we compare the performance of the different approaches for pathology classification by ROC statistics and analyze differences between the classifiers using rank correlation. Overall, we observe a considerable spread in the achieved performance and conclude that the X-ray-specific ResNet-38, integrating non-image data yields the best overall results. Furthermore, class activation maps are used to understand the classification process, and a detailed analysis of the impact of non-image features is provided.
Beschreibung:	Sonstige Körperschaft: Technische Universität Hamburg Sonstige Körperschaft: Technische Universität Hamburg, Institute for Biomedical Imaging
Umfang:	Illustrationen, Diagramme 10
ISSN:	2045-2322
DOI:	10.1038/s41598-019-42294-8