Path-Weighted Integrated Gradients for Interpretable Dementia Classification

• URL: http://arxiv.org/abs/2509.17491v1
• Date: Mon, 22 Sep 2025 08:19:48 GMT
• Title: Path-Weighted Integrated Gradients for Interpretable Dementia Classification
• Authors: Firuz Kamalov, Mohmad Al Falasi, Fadi Thabtah,
• Abstract summary: We introduce Path-Weighted Integrated Gradients (PWIG), a generalization of Integrated Gradients (IG) that incorporates a customizable weighting function into the attribution integral.<n>PWIG offers a flexible and theoretically grounded approach for enhancing attribution quality in complex predictive models.
• Score: 1.388610714424775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable artificial intelligence (XAI). In this paper, we introduce Path-Weighted Integrated Gradients (PWIG), a generalization of IG that incorporates a customizable weighting function into the attribution integral. This modification allows for targeted emphasis along different segments of the path between a baseline and the input, enabling improved interpretability, noise mitigation, and the detection of path-dependent feature relevance. We establish its theoretical properties and illustrate its utility through experiments on a dementia classification task using the OASIS-1 MRI dataset. Attribution maps generated by PWIG highlight clinically meaningful brain regions associated with various stages of dementia, providing users with sharp and stable explanations. The results suggest that PWIG offers a flexible and theoretically grounded approach for enhancing attribution quality in complex predictive models.

Related papers

• Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification [16.637098984977055]
  Interpretability is essential in Whole Slide Image (WSI) analysis for computational pathology.<n>We introduce Contrastive Integrated Gradients (CIG), a novel attribution method that enhances interpretability by computing contrastive gradients in logit space.
  arXiv  Detail & Related papers  (2025-11-11T17:07:32Z)
• Unlocking Biomedical Insights: Hierarchical Attention Networks for High-Dimensional Data Interpretation [0.3821469577674901]
  Hierarchical Attention-based Interpretable Network (HAIN) is a novel architecture that unifies multi-level attention mechanisms, dimensionality reduction, and explanation-driven loss functions.<n> Comprehensive evaluation on The Cancer Genome Atlas dataset demonstrates that HAIN achieves a classification accuracy of 94.3%.<n>HAIN effectively identifies biologically relevant cancer biomarkers, supporting its utility for clinical and research applications.
  arXiv  Detail & Related papers  (2025-10-21T20:08:50Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• PathMR: Multimodal Visual Reasoning for Interpretable Pathology Diagnosis [9.728322291979564]
  We propose PathMR, a cell-level Multimodal visual Reasoning framework for Pathological image analysis.<n>We show that PathMR consistently outperforms state-of-the-art visual reasoning methods in text generation quality, segmentation accuracy, and cross-modal alignment.
  arXiv  Detail & Related papers  (2025-08-28T14:46:24Z)
• Explainable AI (XAI) for Arrhythmia detection from electrocardiograms [0.0]
  Deep learning has enabled highly accurate arrhythmia detection from electrocardiogram (ECG) signals, but limited interpretability remains a barrier to clinical adoption.<n>This study investigates the application of Explainable AI (XAI) techniques specifically adapted for time-series ECG analysis.
  arXiv  Detail & Related papers  (2025-08-24T10:44:24Z)
• GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models [1.0456203870202954]
  This work introduces a novel framework for brain tumor segmentation leveraging pre-trained GANs and Unet architectures.<n>By combining a global anomaly detection module with a refined mask generation network, the proposed model accurately identifies tumor-sensitive regions.<n>Multi-modal MRI data and synthetic image augmentation are employed to improve robustness and address the challenge of limited annotated datasets.
  arXiv  Detail & Related papers  (2025-06-26T13:28:09Z)
• PhysLLM: Harnessing Large Language Models for Cross-Modal Remote Physiological Sensing [49.243031514520794]
  Large Language Models (LLMs) excel at capturing long-range signals due to their text-centric design.<n>PhysLLM achieves state-the-art accuracy and robustness, demonstrating superior generalization across lighting variations and motion scenarios.
  arXiv  Detail & Related papers  (2025-05-06T15:18:38Z)
• FODA-PG for Enhanced Medical Imaging Narrative Generation: Adaptive Differentiation of Normal and Abnormal Attributes [26.912139217120874]
  We propose FODA-PG, a novel Fine-grained Organ-Disease Adaptive Partitioning Graph framework. FODA-PG constructs a granular representation of radiological findings by separating disease-related attributes into distinct "disease-specific" and "disease-free" categories. By integrating this fine-grained semantic knowledge into a powerful transformer-based architecture, FODA-PG generates precise and clinically coherent reports.
  arXiv  Detail & Related papers  (2024-09-06T00:04:35Z)
• Physics Inspired Hybrid Attention for SAR Target Recognition [61.01086031364307]
  We propose a physics inspired hybrid attention (PIHA) mechanism and the once-for-all (OFA) evaluation protocol to address the issues. PIHA leverages the high-level semantics of physical information to activate and guide the feature group aware of local semantics of target. Our method outperforms other state-of-the-art approaches in 12 test scenarios with same ASC parameters.
  arXiv  Detail & Related papers  (2023-09-27T14:39:41Z)
• Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning [78.49090351193269]
  We propose a novel graph-based framework to leverage the inter-relationships among different types of nuclei for WSI analysis. Specifically, we formulate the WSI as a heterogeneous graph with "nucleus-type" attribute to each node and a semantic attribute similarity to each edge. Our framework outperforms the state-of-the-art methods with considerable margins on various tasks.
  arXiv  Detail & Related papers  (2023-07-09T14:43:40Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• Attri-VAE: attribute-based, disentangled and interpretable representations of medical images with variational autoencoders [0.5451140334681147]
  We propose a VAE approach that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches.
  arXiv  Detail & Related papers  (2022-03-20T00:19:40Z)
• Transforming Feature Space to Interpret Machine Learning Models [91.62936410696409]
  This contribution proposes a novel approach that interprets machine-learning models through the lens of feature space transformations. It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools. A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach.
  arXiv  Detail & Related papers  (2021-04-09T10:48:11Z)

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.