Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classifiers

• URL: http://arxiv.org/abs/2606.16362v1
• Date: Mon, 15 Jun 2026 07:57:50 GMT
• Title: Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classifiers
• Abstract summary: This work introduces a local sensitivity analysis framework based on the input-dependent Fisher Information Matrix.<n>It provides a model-intrinsic description of local predictive sensitivity, rather than a conventional pixel-wise attribution heatmap.<n>Results support the iFIM framework as a principled tool for analyzing local decision sensitivity and for complementing existing attribution-based interpretability methods in medical imaging.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks have achieved strong performance in medical image classification, but often work like black-box. Commonly used post-hoc interpretation methods often provide heuristic visualizations whose relationship to the classifier's predictive distribution is indirect. This work introduces a local sensitivity analysis framework based on the input-dependent Fisher Information Matrix (iFIM) of a trained classifier. The iFIM characterizes how the classifier's predictive distribution changes under infinitesimal perturbations of the input image. By using a Gram-matrix formulation, the nonzero eigenspectrum of the iFIM can be recovered without explicitly forming the full image-dimensional Fisher matrix. The leading iFIM eigenspace is then used to project an input image into a high local-sensitivity component and its orthogonal component. These components provide a model-intrinsic description of local predictive sensitivity, rather than a conventional pixel-wise attribution heatmap or a causal segmentation of task-relevant anatomy. The framework is evaluated on controlled and clinical medical image classification tasks using multiple classifier architectures. Perturbation-based experiments show that high-sensitivity iFIM components are more strongly coupled to changes in predictive confidence and classification performance than lower-sensitivity complementary components. The results support the iFIM framework as a principled tool for analyzing local decision sensitivity and for complementing existing attribution-based interpretability methods in medical imaging.

Related papers

• CFR-Net:Collaborative Feature Refnement Network for Medical Image Anomaly Detection [23.30777405878389]
  We propose the Collaborative Feature Refinement Network (CFR-Net), which combines shared teacher-student feature refinement before decoding with cross-space consistency after decoding.<n>Experiments on medical benchmarks show that CFR-Net achieves competitive anomaly classification and strong anomaly localization performance when trained on normal data.
  arXiv  Detail & Related papers  (2026-07-13T12:59:21Z)
• Diffusion-Based Feature Denoising and Using NNMF for Robust Brain Tumor Classification [0.0]
  This study suggests a robust brain tumor classification framework that combines Non-Negative Matrix Factorization (NNMF), lightweight convolutional neural networks (CNNs), and diffusion-based feature purification.<n>The experimental results show that the proposed framework achieves competitive classification performance while significantly enhancing robustness against adversarial perturbations.
  arXiv  Detail & Related papers  (2026-03-13T17:15:46Z)
• MAMBO-NET: Multi-Causal Aware Modeling Backdoor-Intervention Optimization for Medical Image Segmentation Network [51.68708264694361]
  Confusion factors can affect medical images, such as complex anatomical variations and imaging modality limitations.<n>We propose a multi-causal aware modeling backdoor-intervention optimization network for medical image segmentation.<n>Our method significantly reduces the influence of confusion factors, leading to enhanced segmentation accuracy.
  arXiv  Detail & Related papers  (2025-05-28T01:40:10Z)
• PathSegDiff: Pathology Segmentation using Diffusion model representations [63.20694440934692]
  We propose PathSegDiff, a novel approach for histopathology image segmentation that leverages Latent Diffusion Models (LDMs) as pre-trained featured extractors.<n>Our method utilizes a pathology-specific LDM, guided by a self-supervised encoder, to extract rich semantic information from H&E stained histopathology images.<n>Our experiments demonstrate significant improvements over traditional methods on the BCSS and GlaS datasets.
  arXiv  Detail & Related papers  (2025-04-09T14:58:21Z)
• Intuitionistic Fuzzy Cognitive Maps for Interpretable Image Classification [2.130156029408832]
  This paper introduces a novel framework, named Interpretable Intuitionistic Fuzzy Cognitive Maps (I2FCMs)<n>Intuitionistic FCMs offer a mechanism to assess the quality of their output through the estimation of hesitancy.<n>The proposed I2FCM framework can be applied to DL models, including CNN, rendering them interpretable.
  arXiv  Detail & Related papers  (2024-08-07T12:58:39Z)
• FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms [60.195642571004804]
  We introduce FlowSDF, an image-guided conditional flow matching framework, to represent an implicit distribution of segmentation masks.<n>Our framework enables accurate sampling of segmentation masks and the computation of relevant statistical measures.
  arXiv  Detail & Related papers  (2024-05-28T11:47:12Z)
• FeaInfNet: Diagnosis in Medical Image with Feature-Driven Inference and Visual Explanations [4.022446255159328]
  Interpretable deep learning models have received widespread attention in the field of image recognition. Many interpretability models that have been proposed still have problems of insufficient accuracy and interpretability in medical image disease diagnosis. We propose feature-driven inference network (FeaInfNet) to solve these problems.
  arXiv  Detail & Related papers  (2023-12-04T13:09:00Z)
• Score-Based Generative Models for Medical Image Segmentation using Signed Distance Functions [11.137438870686026]
  We propose a conditional score-based generative modeling framework to represent the signed distance function (SDF) The advantage of leveraging the SDF is a more natural distortion when compared to that of binary masks.
  arXiv  Detail & Related papers  (2023-03-10T14:55:35Z)
• PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training [52.895952593202054]
  We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation. PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state. Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
  arXiv  Detail & Related papers  (2022-07-24T07:45:47Z)
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification [74.84221280249876]
  An efficient analysis of large amounts of chest radiographs can aid physicians and radiologists. We propose a novel Discrete Wavelet Transform (DWT)-based method for the efficient identification and encoding of visual information.
  arXiv  Detail & Related papers  (2022-05-08T15:29:54Z)
• Collaborative Boundary-aware Context Encoding Networks for Error Map Prediction [65.44752447868626]
  We propose collaborative boundaryaware context encoding networks called AEP-Net for error prediction task. Specifically, we propose a collaborative feature transformation branch for better feature fusion between images and masks, and precise localization of error regions. The AEP-Net achieves an average DSC of 0.8358, 0.8164 for error prediction task, and shows a high Pearson correlation coefficient of 0.9873.
  arXiv  Detail & Related papers  (2020-06-25T12:42:01Z)

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.