mlsanityData to 7 Oct 2026

Interpretability of a Deep Learning Model in the Application of Cardiac MRI Segmentation with an ACDC Challenge Dataset

arXiv 2103.08590 ↗First posted 15 Mar 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Cardiac Magnetic Resonance (CMR) is the most effective tool for the assessment and diagnosis of a heart condition, which malfunction is the world's leading cause of death. Software tools leveraging Artificial Intelligence already enhance radiologists and cardiologists in heart condition assessment but their lack of transparency is a problem. This project investigates if it is possible to discover concepts representative for different cardiac conditions from the deep network trained to segment crdiac structures: Left Ventricle (LV), Right Ventricle (RV) and Myocardium (MYO), using explainability methods that enhances classification system by providing the score-based values of qualitative concepts, along with the key performance metrics. With introduction of a need of explanations in GDPR explainability of AI systems is necessary. This study applies Discovering and Testing with Concept Activation Vectors (D-TCAV), an interpretaibilty method to extract underlying features important for cardiac disease diagnosis from MRI data. The method provides a quantitative notion of concept importance for disease classified. In previous studies, the base method is applied to the classification of cardiac disease and provides clinically meaningful explanations for the predictions of a black-box deep learning classifier. This study applies a method extending TCAV with a Discovering phase (D-TCAV) to cardiac MRI analysis. The advantage of the D-TCAV method over the base method is that it is user-independent. The contribution of this study is a novel application of the explainability method D-TCAV for cardiac MRI anlysis. D-TCAV provides a shorter pre-processing time for clinicians than the base method.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 11 of its 22 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

11 of 22 references.

References · 11

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  5. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  6. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  7. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  9. 2017An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentationcited by 36
  10. 2019Global and Local Interpretability for Cardiac MRI Classificationcited by 29
  11. 2019Towards Automatic Concept-based Explanationscited by 10

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 2; 2023: 0; 2024: 1; 2025: 1.

8 papers.

  1. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  2. 2021Explainable Medical Imaging AI Needs Human-Centered Design: Guidelines and Evidence from a Systematic Reviewcited by 30
  3. 2022ClaSP -- Parameter-free Time Series Segmentationcited by 21
  4. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  5. 2021Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Toolscited by 9
  6. 2021Optimising Knee Injury Detection with Spatial Attention and Validating Localisation Abilitycited by 3
  7. 2022Automated Diagnosis of Cardiovascular Diseases from Cardiac Magnetic Resonance Imaging Using Deep Learning Models: A Reviewcited by 0
  8. 2025PULSE: A Unified Multi-Task Architecture for Cardiac Segmentation, Diagnosis, and Few-Shot Cross-Modality Clinical Adaptationcited by 0