---
title: "KANEx：将KAN网络的解释性迁移至医学可解释性"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.24730v1"
permalink: "https://feed.astralor.com/items/itm_4c9ff787b58e8425b95de25a"
published: "2026-07-27T17:57:02.000Z"
score: 79
channel: "ai"
tags: ["KANEx","Kolmogorov-Arnold Networks","MIMIC-CXR","Vision-Language Models","医学可解释性"]
---

# KANEx：将KAN网络的解释性迁移至医学可解释性

## AI 点评

> 这篇论文最值得关注的是它找到了将KAN网络的可解释性从理论推向医学应用的实际落地方式。对于研究可信AI和医学影像的学者，KAN-Map的热力图生成思路和VLM锚定方法值得深入借鉴。具体来说，对算法工程师而言，KAN-Map提供了一种无需梯度的可视化替代方案；对临床AI产品经理，它展示了提升模型解释可信度的技术路径。

## 速览

计算机视觉模型在医学应用中表现优异，但其黑箱特性削弱了临床信任。现有系统将胸部X光分类器与视觉语言模型（VLM）结合生成自然语言解释，但未解决视觉模型本身的不透明性。本文提出KANEx框架，首次利用Kolmogorov-Arnold网络（KAN）的符号透明性来锚定VLM推理，并设计KAN-Map热力图生成方法。在MIMIC-CXR数据集上，KAN架构相比ResNet/ViT基线在语义相似性和显著性图忠实度上均有提升，视觉定位和下游推理质量提高10%。研究认为，将语言解释和视觉归因锚定在数学可解释单元上是构建可信医学AI的必要步骤。

## 关键点

- KANEx首次利用KAN网络的符号可解释性为VLM推理提供锚定。
- 提出KAN-Map热力图方法，直接源自KAN模型而非梯度近似。
- 在MIMIC-CXR上，KAN架构相比基线在语义相似性和显著性图忠实度上均有提升，视觉定位和推理质量提高10%。

## 全文

Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust. In clinical workflows, chest X-ray classifiers are increasingly paired with Vision-Language Models (VLMs) to generate natural-language explanations. However, these systems add linguistic fluency without addressing the underlying opacity of the visual model. With the emergence of Kolmogorov-Arnold Networks (KANs), whose spline-based components provide inherently interpretable functional units, we investigate whether this architectural transparency can be leveraged to produce more trustworthy textual explanations. We introduce KANEx, the first ever framework that leverages the symbolic transparency of KANs to ground VLM reasoning. This interpretability also made it possible to design KAN-Map, a novel heatmap generation method derived directly from KAN models rather than gradient approximations. We feed these grounded contexts into downstream VLMs for enhanced explainability. Benchmarked on the MIMIC-CXR dataset, we demonstrate that KAN-based architectures with ResNet/ViT baselines demonstrate improved semantic similarity while producing significantly more faithful saliency maps. KAN architectures improve visual localization and downstream reasoning quality by 10%. Our findings suggest that grounding linguistic explanations and visual attributions in mathematically interpretable units is a necessary step toward trustworthy medical AI.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_4c9ff787b58e8425b95de25a