Deep learning of diffraction image patterns for accurate classification of five cell types.,Journal of Biophotonics

当前位置： X-MOL 学术 › J. Biophotonics › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Deep learning of diffraction image patterns for accurate classification of five cell types.
Journal of Biophotonics ( IF 2.0 ) Pub Date : 2019-12-23 , DOI: 10.1002/jbio.201900242
Jiahong Jin _{1,

2,

3} , Jun Q Lu _{1,

2} , Yuhua Wen _{1,

3} , Peng Tian _{1,

3} , Xin-Hua Hu _{1,

2}

Affiliation

Development of label‐free methods for accurate classification of cells with high throughput can yield powerful tools for biological research and clinical applications. We have developed a deep neural network of DINet for extracting features from cross‐polarized diffraction image (p‐DI) pairs on multiple pixel scales to accurately classify cells in five types. A total of 6185 cells were measured by a polarization diffraction imaging flow cytometry (p‐DIFC) method followed by cell classification with DINet on p‐DI data. The averaged value and SD of classification accuracy were found to be 98.9% ± 1.00% on test data sets for 5‐fold training and test. The invariance of DINet to image translation, rotation, and blurring has been verified with an expanded p‐DI data set. To study feature‐based classification by DINet, two sets of correctly and incorrectly classified cells were selected and compared for each of two prostate cell types. It has been found that the signature features of large dissimilarities between p‐DI data of correctly and incorrectly classified cell sets increase markedly from convolutional layers 1 and 2 to layers 3 and 4. These results clearly demonstrate the importance of high‐order correlations extracted at the deep layers for accurate cell classification.

中文翻译：

衍射图像模式的深度学习，可准确分类五种细胞类型。

开发用于高通量细胞准确分类的无标记方法可以为生物学研究和临床应用提供强大的工具。我们开发了一个 DINet 深度神经网络，用于从多像素尺度上的交叉偏振衍射图像 (p-DI) 对中提取特征，以准确分类五种类型的细胞。通过偏振衍射成像流式细胞术 (p-DIFC) 方法测量了总共 6185 个细胞，然后使用 DINet 对 p-DI 数据进行细胞分类。在 5 倍训练和测试的测试数据集上，发现分类准确度的平均值和 SD 为 98.9% ± 1.00%。DINet 对图像平移、旋转和模糊的不变性已通过扩展的 p-DI 数据集得到验证。通过 DINet 研究基于特征的分类，选择两组正确和错误分类的细胞，并针对两种前列腺细胞类型中的每一种进行比较。已经发现，从卷积层 1 和 2 到第 3 层和第 4 层，正确和错误分类的细胞集的 p-DI 数据之间的巨大差异的特征特征显着增加。这些结果清楚地证明了在用于准确细胞分类的深层。

更新日期：2019-12-23

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11