锐度感知最小化（SAM）提高细菌拉曼光谱数据分类准确率，助力便携式诊断
Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics
- Massachusetts Institute of Technology（麻省理工学院）
- Stanford University（斯坦福大学）
- Google Research（谷歌研究院）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本研究采用锐度感知最小化（SAM）优化器，提升临床细菌拉曼光谱分类模型的泛化能力，较Adam平均准确率提高2.7%，推动便携式耐药性诊断应用。
中文摘要 AI 辅助
预计到2050年，抗菌素耐药性每年将导致1000万人死亡，而资源有限地区受影响最为严重。拉曼光谱是一种新型病原体诊断方法，有望在几小时内实现快速、便携的抗生素耐药性检测，而金标准方法则需要数天。然而，当前用于拉曼光谱分析的算法存在以下问题：1）在跨不同患者群体的有限数据集上泛化能力不足；2）由于需要非平凡预处理步骤（如特征提取）以缓解拉曼光谱数据质量低下的问题，导致算法复杂度增加。在本工作中，我们使用锐度感知最小化（SAM）来解决这些局限性，以增强模型在临床细菌分离物分类任务中跨多种超参数的泛化能力。我们证明，与传统优化器Adam相比，SAM在单次划分上准确率提升高达10.5%，在所有划分的光谱分类任务中平均准确率提升2.7%。这些结果表明，SAM能够推动基于人工智能的拉曼光谱工具在临床中的应用。
英文摘要
Antimicrobial resistance is expected to claim 10 million lives per year by 2050, and resource-limited regions are most affected. Raman spectroscopy is a novel pathogen diagnostic approach promising rapid and portable antibiotic resistance testing within a few hours, compared to days when using gold standard methods. However, current algorithms for Raman spectra analysis 1) are unable to generalize well on limited datasets across diverse patient populations and 2) require increased complexity due to the necessity of non-trivial pre-processing steps, such as feature extraction, which are essential to mitigate the low-quality nature of Raman spectral data. In this work, we address these limitations using Sharpness-Aware Minimization (SAM) to enhance model generalization across a diverse array of hyperparameters in clinical bacterial isolate classification tasks. We demonstrate that SAM achieves accuracy improvements of up to 10.5% on a single split, and an increase in average accuracy of 2.7% across all splits in spectral classification tasks over the traditional optimizer, Adam. These results display the capability of SAM to advance the clinical application of AI-powered Raman spectroscopy tools.
