Histopathological examination of tissue sections is the gold standard for disease diagnosis. However, the conventional histopathology workflow requires lengthy and laborious sample preparation to obtain thin tissue slices, causing about a one-week delay to generate an accurate diagnostic report. Recently, microscopy with ultraviolet surface excitation (MUSE), a rapid and slide-free imaging technique, has been developed to image fresh and thick tissues with specific molecular contrast. Here, we propose to apply an unsupervised generative adversarial network framework to translate colorful MUSE images into Deep-MUSE images that highly resemble hematoxylin and eosin staining, allowing easy adaptation by pathologists. By eliminating the needs of all sample processing steps (except staining), a MUSE image with subcellular resolution for a typical brain biopsy (5 mm × 5 mm) can be acquired in 5 minutes, which is further translated into a Deep-MUSE image in 40 seconds, simplifying the standard histopathology workflow dramatically and providing histological images intraoperatively.

中文翻译：

---

具有紫外线表面激发的深度学习辅助显微镜，用于快速无载玻片组织学成像


组织切片的组织病理学检查是疾病诊断的金标准。然而，传统的组织病理学工作流程需要漫长而费力的样品制备才能获得薄组织切片，导致生成准确的诊断报告需要大约一周的延迟。最近，紫外表面激发显微镜（MUSE）是一种快速且无载玻片的成像技术，已被开发出来可以对具有特定分子对比度的新鲜厚组织进行成像。在这里，我们建议应用无监督的生成对抗网络框架将彩色 MUSE 图像转换为高度类似于苏木精和伊红染色的 Deep-MUSE 图像，以便病理学家轻松适应。通过消除所有样本处理步骤（染色除外），可以在 5 分钟内获得典型脑活检（5 mm × 5 mm）的亚细胞分辨率 MUSE 图像，并进一步转化为 Deep-MUSE 图像40 秒，极大简化了标准组织病理学工作流程，并在术中提供组织学图像。