Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

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

Publication

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

Mohammed, Aliya; Geppert, Carol; Hartmann, Arnd; u. a. (2022): Explaining and Evaluating Deep Tissue Classification by Visualizing Activations of Most Relevant Intermediate Layers, in: Current directions in biomedical engineering, Berlin: De Gruyter, Jg. 8, Nr. 2, S. 229–232, doi: 10.1515/cdbme-2022-1059.

Details

Faculty/Chair
Faculty/Professorship
Author
Mohammed, Aliya; Geppert, Carol; Hartmann, Arnd; Kuritcyn, Petr; Bruns, Volker; ORCID iDSchmid, Ute; Wittenberg, Thomas; Benz, Michaela; ORCID iDFinzel, Bettina
Title of the Journal
Current directions in biomedical engineering
ISSN
2364-5504
Publisher Information
De Gruyter : Berlin
Year of publication
2022
Volume
8
Issue
2
Language
English
DOI
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.

GND Keywords
Patholinguistik
Deep Learning
Explainable Artificial Intelligence
Evaluation
Maschinelles Lernen
Visualisierung
Benutzeroberfläche
Keywords
Digital Pathology
Deep Learning
XAI
Evaluation
Grad-CAM
Intelligent user interface
DDC Classification
004 Computer science
RVK Classification
ST 302
Type
Article
URI
Activation date
2024-01-24

Permalink: https://fis.uni-bamberg.de/handle/uniba/93000 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.