Rxivist logo

Deep learning-based adaptive detection of fetal nucleated red blood cells

By Chao Sun, Ruijie Wang, Lanbo Zhao, Lu Han, Sijia Ma, Dongxin Liang, Lei Wang, Xiaoqian Tuo, Dexing Zhong, Qiling Li

Posted 08 Mar 2020
bioRxiv DOI: 10.1101/2020.03.06.980227

Aim: this study, we established an artificial intelligence system for the rapid identification of fetal nucleated red blood cells (fNRBCs). Method: Density gradient centrifugation and magnetic-activated cell sorting were used for the separation of fNRBCs from umbilical cord blood. The cell block technique was used for fixation. We proposed a novel preprocessing method based on imaging characteristics of fNRBCs for the region of interest (ROI) extraction, which automatically segmented individual cells in peripheral blood cell smears. The discriminant information from ROIs was encoded into a feature vector and pathological diagnosis was provided by the prediction network. Results: Four umbilical cord blood samples were collected and validated based on a large dataset containing 260 samples. Finally, the dataset was classified into 3,720 and 1,040 slides for training and testing, respectively. In the test set, the classifier obtained 98.5% accuracy and 96.5% sensitivity. Conclusion: Therefore, this study offers an effective and accurate method for fNRBCs preservation and identification.

Download data

  • Downloaded 333 times
  • Download rankings, all-time:
    • Site-wide: 73,792
    • In pathology: 369
  • Year to date:
    • Site-wide: 59,312
  • Since beginning of last month:
    • Site-wide: 59,312

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)