发表机构
Marquette University; Medical College of Wisconsin; Georgia State University; University of Wisconsin–Oshkosh（马凯特大学; 威斯康星医学院; 佐治亚州立大学; 威斯康星大学奥什科什分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究对比了4x与10x倍率的MUSE图像，采用纹理分析与深度学习方法，证实4x成像与10x诊断准确率相当，且视野更大、采集更快，可用于术中乳腺癌切缘评估。
AI 中文摘要
采用紫外表面激发显微镜（MUSE）可获取未处理乳腺手术组织的高分辨率图像，该技术被视为乳腺癌手术中检查手术切缘的有前景方法。本研究采用 patch 级分类方法，对比了放大倍数为 4x 和 10x 的 MUSE 图像，所用方法包括基于局部二值模式（LBP）的纹理分析（TA）以及以基础视觉 Transformer（ViT）模型为核心的深度学习（DL）。两种方法在两种放大倍数下的性能相近：采用深度学习方法时，4x 和 10x 放大倍数均达到 96.30% 的灵敏度、100% 的特异度和 98.18% 的准确率；采用纹理分析方法时，4x 放大倍数的特异度更优（100% 对比 93.33%），10x 放大倍数的灵敏度更高（100% 对比 93.33%），但两者准确率相同（96.67%）。10x 放大倍数未观察到性能的明显提升，结果显示 4x 成像与 10x 成像具有相同的诊断准确率，同时 4x 成像提供更大的视野且图像采集速度更快，因此低倍率可有效应用于 MUSE 系统，实现准确高效的术中切缘评估。
英文摘要
High-resolution images of unprocessed surgical breast tissue can be obtained using microscopy with ultraviolet surface excitation (MUSE). This technique is considered a promising method for checking surgical margins during breast cancer surgery. In this study, MUSE images at 4x and 10x magnifications were compared using patch-level classification methods. Texture analysis (TA) based on local binary patterns (LBP) and deep learning (DL) with a base Vision Transformer (ViT) model were used. Both methods achieved similar performance at both magnifications. Using DL method, both 4x and 10x magnifications achieved 96.30% sensitivity, 100% specificity and 98.18% accuracy. Using TA method, 4x achieved better specificity (100% vs 93.33%) and 10x yielded higher sensitivity (100% vs 93.33%), but both had the same accuracy (96.67%). No clear improvement in performance was observed with 10x magnification. These results show that 4x imaging achieves the same diagnostic accuracy as 10x imaging. At the same time, 4x offers a larger field of view and faster image capture. Therefore, lower magnification can be effectively used in MUSE systems for accurate and efficient intraoperative margin assessment.
CommentsThis research has been accepted and published in Journal "Biomedical Optics Express" in July 2026 with Manuscript ID is 596807
Journal refBiomedical Optics Express 2026
