Breast cancer detection using infrared spectral pathology from H&E stained tissue on glass slides
Breast cancer detection using infrared spectral pathology from H&E stained tissue on glass slides
复制标题
使用 H 的红外光谱病理学检测乳腺癌
DOI：
10.1016/j.clispe.2021.100008
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Tang J
中科院分区：
文献类型：
--
作者：
Tang J
红外光谱病理学在过去的几年中得到了极大的关注，因为它已经被证明能够容易地识别活检样本中的癌组织。然而，红外技术通常需要将组织切片固定在红外透明载玻片上。不幸的是，这些载玻片既昂贵又特别易碎。此外，将样本固定在专业载玻片上是样本制备工作流程中的一个额外步骤，理想情况下应避免。将红外成像直接应用于病理学家通常使用的载玻片上的H&E染色组织，可以帮助红外成像技术纳入当前的癌症诊断工作流程，并降低检测的总成本。使用载玻片的缺点是可用的光谱范围仅限于高波数区域（2500-3600 cm−1）。在这项工作中，对来自不同患者的120个乳腺组织活检芯进行了研究，以证明在有限的光谱信息下，可以从H&E载玻片中识别乳腺癌。构建了四类组织学Adboost分类模型。进行分类阈值的优化以减少假阴性的数量。使用0.1的阈值，可以以95.8%的准确度检测癌核心。这被纳入一个简单的交通灯系统，可用作预筛选工具。这项工作，演示了使用红外光谱病理学的标准病理学样本载玻片，从而在一定程度上克服了红外技术成功转化为临床的障碍之一。
Infrared spectral pathology has gained significant attention in the last few years, since it has been demonstrated to be able to readily identify cancerous tissue in biopsy samples. The Infrared technique, however, normally requires tissue sections to be mounted on infrared transparent slides. Unfortunately, these slides are both expensive and particularly frangible. In addition, mounting samples on specialist slides is an additional step in the sample preparation workflow, which ideally should be avoided. Applying infrared imaging directly to the H&E stained tissue on the glass slides that are normally used by pathologists, could help the infrared imaging technique be incorporated into current cancer diagnosis work flow and lower the total cost of detection. The disadvantage of using glass slides is that the spectral range available is restricted to just the high wavenumber region (2500–3600 cm−1). In this work a study has been conducted on 120 breast tissues biopsy cores from different patients, to demonstrate that with the limited spectral information, breast cancer can be identified from the H&E glass slides. A four-class histological Adboost classification model has been constructed. Optimisation of the classification threshold was carried out to reduce the number of false negatives. Using a threshold of 0.1 the cancerous cores could be detected with an accuracy of 95.8 %. This was incorporated into a simple traffic light system that could be used as a prescreening tool. This work, demonstrating the use of infrared spectral pathology on standard pathology samples slide, thus goes some way to overcome one of the barriers to successful translation of the infrared technique into the clinic.
登录
查看更多内容
肺癌光谱组织病理学 (SHP) 数据集的统计分析。
DOI：
10.1039/c4an01832j
发表时间：
2015
期刊：
The Analyst
影响因子：
--
作者：
Mu,Xinying;Kon,Mark;Ergin,Ayşegül;Remiszewski,Stan;Akalin,Ali;Thompson,ClayM;Diem,Max
通讯作者：
Diem,Max
影响因子：
7.4
作者：
Bassan, Paul;Mellor, Joe;Gardner, Peter
通讯作者：
Gardner, Peter
使用高清傅立叶变换红外 (FT-IR) 光谱成像的数字乳腺组织病理学四类模型
影响因子：
3.8
作者：
Shachi Mittal;T. Wróbel;L. S. Leslie;Andre Kadjacsy;R. Bhargava
通讯作者：
R. Bhargava
影响因子：
4.2
作者：
Bassan, Paul;Weida, Miles J.;Gardner, Peter
通讯作者：
Gardner, Peter
使用基于随机决策森林的红外光谱成像数据分类进行乳腺组织病理学
影响因子：
7.4
作者：
D. Mayerich;M. Walsh;Andre Kadjacsy;Shachi Mittal;R. Bhargava
通讯作者：
R. Bhargava