Automatic Colorectal Cancer Screening Using Deep Learning in Spatial Light Interference Microscopy Data.
Automatic Colorectal Cancer Screening Using Deep Learning in Spatial Light Interference Microscopy Data.
复制标题
在空间光干扰显微镜数据中使用深度学习的自动结直肠癌筛查。
DOI：
10.3390/cells11040716
复制
发表时间：
2022-02-17
期刊：
影响因子：
6
通讯作者：
Popescu G
中科院分区：
文献类型：
--
作者：
Zhang JK;Fanous M;Sobh N;Kajdacsy-Balla A;Popescu G
目前临床采用的外科病理学工作流程使用染色来揭示薄切片中的组织结构。然后，训练有素的病理学家对这些切片进行肉眼检查，由于调查是基于经验评估，一定程度的主观性是不可避免的。此外，依赖于外部造影剂，如苏木素和曙红(H&E)，虽然是成熟的方法，但很难标准化颜色平衡、染色强度和成像条件，阻碍了自动化计算分析。为了应对这些挑战，我们应用了空间光干涉显微镜(SLIM)，这是一种基于组织固有折射率特征产生对比度的无标记方法。因此，我们减少了人的偏见，并使成像数据在不同仪器和诊所之间具有可比性。我们将MASK R-CNN深度学习算法应用到SLIM数据中，实现了结直肠癌的自动筛查程序，即对正常样本和癌变样本进行分类。我们的结果在由132名患者的样本组成的组织微阵列上获得，腺体检测的准确率为91%，腺体水平分类的准确率为99.71%，核心水平分类的准确率为97%。结合特定应用的深度学习算法的超薄组织扫描仪可能会成为一种有价值的临床工具，使病理学家能够更快、更准确地进行评估。
The surgical pathology workflow currently adopted by clinics uses staining to reveal tissue architecture within thin sections. A trained pathologist then conducts a visual examination of these slices and, since the investigation is based on an empirical assessment, a certain amount of subjectivity is unavoidable. Furthermore, the reliance on external contrast agents such as hematoxylin and eosin (H&E), albeit being well-established methods, makes it difficult to standardize color balance, staining strength, and imaging conditions, hindering automated computational analysis. In response to these challenges, we applied spatial light interference microscopy (SLIM), a label-free method that generates contrast based on intrinsic tissue refractive index signatures. Thus, we reduce human bias and make imaging data comparable across instruments and clinics. We applied a mask R-CNN deep learning algorithm to the SLIM data to achieve an automated colorectal cancer screening procedure, i.e., classifying normal vs. cancerous specimens. Our results, obtained on a tissue microarray consisting of specimens from 132 patients, resulted in 91% accuracy for gland detection, 99.71% accuracy in gland-level classification, and 97% accuracy in core-level classification. A SLIM tissue scanner accompanied by an application-specific deep learning algorithm may become a valuable clinical tool, enabling faster and more accurate assessments by pathologists.
登录
查看更多内容
影响因子：
4.6
作者：
Majeed, Hassaan;Keikhosravi, Adib;Popescu, Gabriel
通讯作者：
Popescu, Gabriel
影响因子：
3.3
作者：
Giacosa, A;Frascio, F;Munizzi, F
通讯作者：
Munizzi, F
影响因子：
4.6
作者：
Majeed H;Nguyen TH;Kandel ME;Kajdacsy-Balla A;Popescu G
通讯作者：
Popescu G
影响因子：
35
作者：
Kim, Taewoo;Zhou, Renjie;Popescu, Gabriel
通讯作者：
Popescu, Gabriel
影响因子：
6.2
作者：
MUTO, T;BUSSEY, HJR;MORSON, BC
通讯作者：
MORSON, BC