Instant diagnosis of gastroscopic biopsy via deep-learned single-shot femtosecond stimulated Raman histology.

Instant diagnosis of gastroscopic biopsy via deep-learned single-shot femtosecond stimulated Raman histology.
复制标题

通过深度学习的单次飞秒刺激拉曼组织学对胃镜活检进行即时诊断

DOI:
10.1038/s41467-022-31339-8
复制
发表时间:
2022-07-13
影响因子:
16.6
通讯作者:
--
中科院分区:
综合性期刊1区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

胃镜活检为胃癌诊断提供了唯一有效的方法,但金标准组织病理学费时且与胃镜不相容。传统的受激拉曼散射(SRS)显微镜在人体组织的无标记诊断中显示出前景,但它需要皮秒激光的调谐,以时间和复杂性为代价来实现化学特异性。在这里,我们证明了单次飞秒SRS (femto-SRS)通过与U-Net集成,在保留化学分辨率的情况下达到了最大的速度和灵敏度。新鲜胃镜活检在60秒内成像,显示基本的组织结构特征与标准组织病理学完全一致。此外,基于279例患者的图像构建了诊断神经网络(CNN),预测胃癌的准确率为bb0.96%。我们进一步展示了肿瘤内异质性的语义分割和内镜下粘膜剥离(ESD)组织切除边缘的评估,以模拟快速和自动的术中诊断。我们的方法具有同步胃镜检查和组织病理学诊断的潜力。目前胃癌的诊断需要胃镜活检,这需要时间和专业知识。在这里,作者展示了一种飞飞- srs成像方法,该方法在诊断胃癌时显示出很高的准确性,而无需基于病理学诊断。
Gastroscopic biopsy provides the only effective method for gastric cancer diagnosis, but the gold standard histopathology is time-consuming and incompatible with gastroscopy. Conventional stimulated Raman scattering (SRS) microscopy has shown promise in label-free diagnosis on human tissues, yet it requires the tuning of picosecond lasers to achieve chemical specificity at the cost of time and complexity. Here, we demonstrate that single-shot femtosecond SRS (femto-SRS) reaches the maximum speed and sensitivity with preserved chemical resolution by integrating with U-Net. Fresh gastroscopic biopsy is imaged in <60 s, revealing essential histoarchitectural hallmarks perfectly agreed with standard histopathology. Moreover, a diagnostic neural network (CNN) is constructed based on images from 279 patients that predicts gastric cancer with accuracy >96%. We further demonstrate semantic segmentation of intratumor heterogeneity and evaluation of resection margins of endoscopic submucosal dissection (ESD) tissues to simulate rapid and automated intraoperative diagnosis. Our method holds potential for synchronizing gastroscopy and histopathological diagnosis. Diagnosis of gastric cancer currently requires gastroscopic biopsy, which requires time and expertize to perform. Here, the authors demonstrate a femto-SRS imaging method which showed high accuracy in diagnosing gastric cancer without the need for pathologistbased diagnosis.
利用深度学习放大窄带图像识别早期胃癌:一项多中心研究
DOI: 10.1016/j.gie.2020.11.014
发表时间: 2021-05-13
影响因子: 7.7
作者:
Hu, Hao;Gong, Lixin;Tian, Jie
通讯作者: Tian, Jie
DOI: 10.1126/sciadv.1500738
发表时间: 2015-10
期刊: Science advances
影响因子: 13.6
作者:
Liao CS;Wang P;Wang P;Li J;Lee HJ;Eakins G;Cheng JX
通讯作者: Cheng JX
DOI: 10.1038/s41592-019-0538-0
发表时间: 2019-09-01
期刊: NATURE METHODS
影响因子: 48
作者:
Hu, Fanghao;Shi, Lixue;Min, Wei
通讯作者: Min, Wei
DOI: 10.1021/jp308938t
发表时间: 2013-04-25
影响因子: 3.3
作者:
Fu, Dan;Holtom, Gary;Freudiger, Christian;Zhang, Xu;Xie, Xiaoliang Sunney
通讯作者: Xie, Xiaoliang Sunney
DOI: 10.1007/s00464-020-07532-5
发表时间: 2021-04
期刊: Surgical endoscopy
影响因子: --
作者:
Chen JN;Wang QW;Zhang QW;Tang ZR;Li XB
通讯作者: Li XB