基于深度学习的活体细胞有丝分裂检测方法

Translated title of the contribution: Deep Learning-Based Detection Method for Mitosis in Living Cells

Baosheng Ke, Ying Li, Zhenbo Ren, Jianglei Di, Jianlin Zhao

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

Owing to the spatiotemporal randomness of mitosis, the automatic identification and accurate location of mitosis in living cells are challenging tasks for researchers. Herein, a deep learning-based detection method was proposed to automatically identify and locate mitosis in living cells. Here, we built a deep neural network called DetectNet by improving the backbone network of YOLOv3 and introducing an attention mechanism. Under the condition of bright-field microscopic imaging, multiscale images of living cells were acquired and then a dataset was constructed to train the network. The trained network DetectNet was compared with multiple object detection algorithms, and its effectiveness was verified. Experimental results show that aiming at the bright-field microscopic images, DetectNet can directly identify and locate mitosis from the multiscale live cell images with a large field, achieving a higher detection accuracy and faster detection speed compared with other multiple object detection algorithms. Thus, DetectNet shows a great potential application value in the fields of biology and medicine.

Translated title of the contributionDeep Learning-Based Detection Method for Mitosis in Living Cells
Original languageChinese (Traditional)
Article number1511001
JournalGuangxue Xuebao/Acta Optica Sinica
Volume41
Issue number15
DOIs
StatePublished - 10 Aug 2021

Fingerprint

Dive into the research topics of 'Deep Learning-Based Detection Method for Mitosis in Living Cells'. Together they form a unique fingerprint.

Cite this