Inhalt anspringen

Validating Automatic Concept-Based Explanations for AI-Based Digital Histopathology

Schnelle Fakten

  • Interne Autorenschaft

  • Weitere Publizierende

    Daniel Sauter, Georg Lodde, Felix Nensa, Dirk Schadendorf, Elisabeth Livingstone

  • Veröffentlichung

    • 2022
  • Zeitschrift/Zeitung

    Sensors (14)

  • Organisationseinheit

  • Fachgebiete

    • Informatik allgemein
  • Forschungsschwerpunkte

    • Medizinische Informatik (MI)
  • Format

    Journalartikel (Artikel)

Zitat

D. Sauter, G. Lodde, F. Nensa, D. Schadendorf, E. Livingstone, and M. Kukuk, “Validating Automatic Concept-Based Explanations for AI-Based Digital Histopathology,” Sensors, vol. 22, no. 14, 2022 [Online]. Available: https://www.mdpi.com/1424-8220/22/14/5346

Abstract

Digital histopathology poses several challenges such as label noise, class imbalance, limited availability of labelled data, and several latent biases to deep learning, negatively influencing transparency, reproducibility, and classification performance. In particular, biases are well known to cause poor generalization. Proposed tools from explainable artificial intelligence (XAI), bias detection, and bias discovery suffer from technical challenges, complexity, unintuitive usage, inherent biases, or a semantic gap. A promising XAI method, not studied in the context of digital histopathology is automated concept-based explanation (ACE). It automatically extracts visual concepts from image data. Our objective is to evaluate ACE’s technical validity following design science principals and to compare it to Guided Gradient-weighted Class Activation Mapping (Grad-CAM), a conventional pixel-wise explanation method. To that extent, we created and studied five convolutional neural networks (CNNs) in four different skin cancer settings. Our results demonstrate that ACE is a valid tool for gaining insights into the decision process of histopathological CNNs that can go beyond explanations from the control method. ACE validly visualized a class sampling ratio bias, measurement bias, sampling bias, and class-correlated bias. Furthermore, the complementary use with Guided Grad-CAM offers several benefits. Finally, we propose practical solutions for several technical challenges. In contradiction to results from the literature, we noticed lower intuitiveness in some dermatopathology scenarios as compared to concept-based explanations on real-world images.

Erläuterungen und Hinweise

Diese Seite verwendet Cookies, um die Funktionalität der Webseite zu gewährleisten und statistische Daten zu erheben. Sie können der statistischen Erhebung über die Datenschutzeinstellungen widersprechen (Opt-Out).

Einstellungen (Öffnet in einem neuen Tab)