用可解释AI分析核磁共振图像的频域特征，提升诊断可信度。
Analyzing the Effect of $k$-Space Features in MRI Classification Models
- 融合图像与频域信息的CNN模型，结合UMAP可视化嵌入特征
- 通过频域特征分析，显著提升模型可解释性与诊断直观性
- 适合关注AI医疗透明性的研究者和临床医生
人工智能在医学诊断中的应用常受限于模型的不透明性，高精度系统往往如‘黑箱’般缺乏可解释的推理过程。这一缺陷在临床环境中尤为关键，因信任与可靠性至关重要。为此，我们开发了一种面向医学影像的可解释AI方法。通过采用在图像域与频率域同时分析核磁共振扫描的卷积神经网络（CNN），并引入均匀流形近似与投影（UMAP）对潜在输入嵌入进行可视化，该方法不仅提升了早期训练效率，更深化了对附加特征如何影响模型预测的理解，从而增强可解释性，支持更准确、直观的诊断推断。
原文摘要 · Abstract (English)
The integration of Artificial Intelligence (AI) in medical diagnostics is often hindered by model opacity, where high-accuracy systems function as "black boxes" without transparent reasoning. This limitation is critical in clinical settings, where trust and reliability are paramount. To address this, we have developed an explainable AI methodology tailored for medical imaging. By employing a Convolutional Neural Network (CNN) that analyzes MRI scans across both image and frequency domains, we introduce a novel approach that incorporates Uniform Manifold Approximation and Projection UMAP] for the visualization of latent input embeddings. This approach not only enhances early training efficiency but also deepens our understanding of how additional features impact the model predictions, thereby increasing interpretability and supporting more accurate and intuitive diagnostic inferences
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。