Detection of live breast cancer cells in bright-field microscopy images containing white blood cells by image analysis and deep learning.
Detection of live breast cancer cells in bright-field microscopy images containing white blood cells by image analysis and deep learning.
复制标题
通过图像分析和深度学习在含有白细胞的明视场显微镜图像中检测活的乳腺癌细胞。
DOI：
10.1117/1.jbo.27.7.076003
复制
发表时间：
2022-07
影响因子：
3.5
通讯作者：
Vanapalli, Siva A.
中科院分区：
文献类型：
--
作者：
Moallem, Golnaz;Pore, Adity A.;Gangadhar, Anirudh;Sari-Sarraf, Hamed;Vanapalli, Siva A.
关键词：
循环肿瘤细胞（CTC）是癌症管理的重要生物标志物。将从血液分离的CTC染色以检测和计数CTC。然而，染色过程是费力的，而且使得CTC不适合用于药物测试和分子表征。其目标是开发和测试深度学习（DL）方法，以检测包含白色血细胞（WBC）的明场显微镜图像中未染色的乳腺癌细胞。我们测试了两种卷积神经网络（CNN）方法。第一种方法允许调查CNN提取的突出特征，以区分体外癌细胞和白细胞。第二种方法是基于更快的基于区域的卷积神经网络（Faster R-CNN）。这两种方法都能以高于95%的灵敏度和99%的特异性检测到癌细胞，而Faster R-CNN更有效，适合部署，灵敏度提高了4%。CNN用于区分的显著特征是细胞大小，然而，在没有大小差异的情况下，CNN被发现能够学习其他特征。发现Faster R-CNN在强度和对比度图像变换方面具有鲁棒性。基于CNN的DL方法可以潜在地应用于从血液样本的图像中检测患者来源的CTC。
Circulating tumor cells (CTCs) are important biomarkers for cancer management. Isolated CTCs from blood are stained to detect and enumerate CTCs. However, the staining process is laborious and moreover makes CTCs unsuitable for drug testing and molecular characterization. The goal is to develop and test deep learning (DL) approaches to detect unstained breast cancer cells in bright-field microscopy images that contain white blood cells (WBCs). We tested two convolutional neural network (CNN) approaches. The first approach allows investigation of the prominent features extracted by CNN to discriminate in vitro cancer cells from WBCs. The second approach is based on faster region-based convolutional neural network (Faster R-CNN). Both approaches detected cancer cells with higher than 95% sensitivity and 99% specificity with the Faster R-CNN being more efficient and suitable for deployment presenting an improvement of 4% in sensitivity. The distinctive feature that CNN uses for discrimination is cell size, however, in the absence of size difference, the CNN was found to be capable of learning other features. The Faster R-CNN was found to be robust with respect to intensity and contrast image transformations. CNN-based DL approaches could be potentially applied to detect patient-derived CTCs from images of blood samples.