On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines

• URL: http://arxiv.org/abs/2508.14482v1
• Date: Wed, 20 Aug 2025 07:13:41 GMT
• Title: On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines
• Authors: Alexander Geiger, Lars Wagner, Daniel Rueckert, Dirk Wilhelm, Alissa Jell,
• Abstract summary: We argue that a clinically normal but input-close counterfactual represents a more accurate representation of a meaningful absence of features in medical data.<n>We evaluate the approach on three distinct medical data sets and empirically demonstrate that counterfactual baselines yield more faithful and medically relevant attributions.
• Score: 48.688209040613216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The explainability of deep learning models remains a significant challenge, particularly in the medical domain where interpretable outputs are critical for clinical trust and transparency. Path attribution methods such as Integrated Gradients rely on a baseline input representing the absence of relevant features ("missingness"). Commonly used baselines, such as all-zero inputs, are often semantically meaningless, especially in medical contexts where missingness can itself be informative. While alternative baseline choices have been explored, existing methods lack a principled approach to dynamically select baselines tailored to each input. In this work, we examine the notion of missingness in the medical setting, analyze its implications for baseline selection, and introduce a counterfactual-guided approach to address the limitations of conventional baselines. We argue that a clinically normal but input-close counterfactual represents a more accurate representation of a meaningful absence of features in medical data. To implement this, we use a Variational Autoencoder to generate counterfactual baselines, though our concept is generative-model-agnostic and can be applied with any suitable counterfactual method. We evaluate the approach on three distinct medical data sets and empirically demonstrate that counterfactual baselines yield more faithful and medically relevant attributions compared to standard baseline choices.

Related papers

• Temporal Sepsis Modeling: a Fully Interpretable Relational Way [0.0]
  Deep learning models often lack interpretability and ignore latent patient sub-phenotypes.<n>We propose a machine learning framework by opening up a new avenue for addressing this issue: a relational approach.
  arXiv  Detail & Related papers  (2026-01-29T14:02:26Z)
• Enhancing interpretability of rule-based classifiers through feature graphs [0.0]
  We propose a framework for estimating feature contributions in rule-based systems.<n>We also introduce a graph-based feature visualisation strategy.<n>We showcase our method's capability to uncover novel insights on the combined predictive value of clinical features.
  arXiv  Detail & Related papers  (2025-06-16T18:29:37Z)
• Weighted Integrated Gradients for Feature Attribution [2.3226745625632947]
  In explainable AI, Integrated Gradients (IG) is a widely adopted technique for assessing the significance of feature attributes of the input on model outputs.<n>This study argues that baselines should not be treated equivalently.<n>We introduce Weighted Integrated Gradients (WG), a novel approach that unsupervisedly evaluates baseline suitability and incorporates a strategy for selecting effective baselines.
  arXiv  Detail & Related papers  (2025-05-06T05:36:47Z)
• High-dimensional multimodal uncertainty estimation by manifold alignment:Application to 3D right ventricular strain computations [1.254652786049077]
  We propose a representation learning strategy to estimate local uncertainties on a physiological descriptor.<n>We first use manifold alignment to match the latent representations associated to different high-dimensional input descriptors.<n>Then, we formulate plausible distributions of latent uncertainties, and finally exploit them to reconstruct uncertainties on the input high-dimensional descriptors.
  arXiv  Detail & Related papers  (2025-01-21T14:35:35Z)
• Pitfalls of topology-aware image segmentation [81.19923502845441]
  We identify critical pitfalls in model evaluation that include inadequate connectivity choices, overlooked topological artifacts, and inappropriate use of evaluation metrics.<n>We propose a set of actionable recommendations to establish fair and robust evaluation standards for topology-aware medical image segmentation methods.
  arXiv  Detail & Related papers  (2024-12-19T08:11:42Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Virtually Objective Quantification of in vitro Wound Healing Scratch Assays with the Segment Anything Model [0.19999259391104385]
  In vitro scratch assay is widely used in cell biology to assess the rate of wound closure. In this paper, we make use of the segment anything model, a deep foundation model based on interactive point-prompts. Results attested very low intra- and interobserver variability, even compared to manual segmentation of domain experts.
  arXiv  Detail & Related papers  (2024-07-02T11:45:56Z)
• Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding [72.18719355481052]
  We introduce a novel task called Medical Report Grounding (MRG)<n>MRG aims to directly identify diagnostic phrases and their corresponding grounding boxes from medical reports in an end-to-end manner.<n>We propose uMedGround, a robust and reliable framework that leverages a multimodal large language model to predict diagnostic phrases.
  arXiv  Detail & Related papers  (2024-04-10T07:41:35Z)
• One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images [22.672569495620895]
  For medical images, saliency maps are the most common form of explanation. Our evaluations show that although most saliency map methods captured modality importance information in general, most of them failed to highlight modality-specific important features consistently and precisely.
  arXiv  Detail & Related papers  (2021-07-11T13:43:02Z)
• Estimating and Improving Fairness with Adversarial Learning [65.99330614802388]
  We propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system. Specifically, we propose to add a discrimination module against bias and a critical module that predicts unfairness within the base classification model. We evaluate our framework on a large-scale public-available skin lesion dataset.
  arXiv  Detail & Related papers  (2021-03-07T03:10:32Z)
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [59.5104563755095]
  We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
  arXiv  Detail & Related papers  (2020-09-27T12:30:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.