Back to Search Start Over

Automated cervical cell segmentation using deep ensemble learning

Authors :
Jie Ji
Weifeng Zhang
Yuejiao Dong
Ruilin Lin
Yiqun Geng
Liangli Hong
Source :
BMC Medical Imaging, Vol 23, Iss 1, Pp 1-10 (2023)
Publication Year :
2023
Publisher :
BMC, 2023.

Abstract

Abstract Background Cervical cell segmentation is a fundamental step in automated cervical cancer cytology screening. The aim of this study was to develop and evaluate a deep ensemble model for cervical cell segmentation including both cytoplasm and nucleus segmentation. Methods The Cx22 dataset was used to develop the automated cervical cell segmentation algorithm. The U-Net, U-Net + + , DeepLabV3, DeepLabV3Plus, Transunet, and Segformer were used as candidate model architectures, and each of the first four architectures adopted two different encoders choosing from resnet34, resnet50 and denseNet121. Models were trained under two settings: trained from scratch, encoders initialized from ImageNet pre-trained models and then all layers were fine-tuned. For every segmentation task, four models were chosen as base models, and Unweighted average was adopted as the model ensemble method. Results U-Net and U-Net + + with resnet34 and denseNet121 encoders trained using transfer learning consistently performed better than other models, so they were chosen as base models. The ensemble model obtained the Dice similarity coefficient, sensitivity, specificity of 0.9535 (95% CI:0.9534–0.9536), 0.9621 (0.9619–0.9622),0.9835 (0.9834–0.9836) and 0.7863 (0.7851–0.7876), 0.9581 (0.9573–0.959), 0.9961 (0.9961–0.9962) on cytoplasm segmentation and nucleus segmentation, respectively. The Dice, sensitivity, specificity of baseline models for cytoplasm segmentation and nucleus segmentation were 0.948, 0.954, 0.9823 and 0.750, 0.713, 0.9988, respectively. Except for the specificity of cytoplasm segmentation, all metrics outperformed the best baseline models (P

Details

Language :
English
ISSN :
14712342
Volume :
23
Issue :
1
Database :
Directory of Open Access Journals
Journal :
BMC Medical Imaging
Publication Type :
Academic Journal
Accession number :
edsdoj.26a8f66833b643edbd1b0f0c91816012
Document Type :
article
Full Text :
https://doi.org/10.1186/s12880-023-01096-1