Explaining and Evaluating Deep Tissue Classification by Visualizing Activations of Most Relevant Intermediate Layers

Mohammed A, Geppert CI, Hartmann A, Kuritcyn P, Bruns V, Schmid U, Wittenberg T, Benz M, Finzel B (2022)

Publication Type: Journal article

Publication year: 2022

Journal

Current Directions in Biomedical Engineering De Gruyter

Book Volume: 8

Pages Range: 229-232

Journal Issue: 2

DOI: 10.1515/cdbme-2022-1059

Abstract

Deep Learning-based tissue classification may support pathologists in analyzing digitized whole slide images. However, in such critical tasks, only approaches that can be validated by medical experts in advance to deployment, are suitable. We present an approach that contributes to making automated tissue classification more transparent. We step beyond broadly used visualizations for last layers of a convolutional neural network by identifying most relevant intermediate layers applying Grad-CAM. A visual evaluation by a pathologist shows that these layers assign relevance, where important morphological structures are present in case of correct class decisions. We introduce a tool that can be easily used by medical experts for such validation purposes for any convolutional neural network and any layer. Visual explanations for intermediate layers provide insights into a neural network's decision for histopathological tissue classification. In future research also the context of the input data must be considered.

Authors with CRIS profile

Carol-Immanuel Geppert Institute of Pathology Arndt Hartmann Lehrstuhl für Allgemeine Pathologie und Pathologische Anatomie Thomas Wittenberg

Involved external institutions

Otto-Friedrich-Universität Bamberg DE Germany (DE) Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Mohammed, A., Geppert, C.-I., Hartmann, A., Kuritcyn, P., Bruns, V., Schmid, U.,... Finzel, B. (2022). Explaining and Evaluating Deep Tissue Classification by Visualizing Activations of Most Relevant Intermediate Layers. Current Directions in Biomedical Engineering, 8(2), 229-232. https://doi.org/10.1515/cdbme-2022-1059

MLA:

Mohammed, Aliya, et al. "Explaining and Evaluating Deep Tissue Classification by Visualizing Activations of Most Relevant Intermediate Layers." Current Directions in Biomedical Engineering 8.2 (2022): 229-232.

BibTeX: Download