An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETR

Automated cell segmentation in cervical cytology images is an essential task because it can present a deep understanding of the characteristics of cervical cells. The main challenge is that cells overlap at a high rate, making the cell boundaries extremely blurred. While the transformer-based models...

Full description

Saved in:
Bibliographic Details
Main Authors: Baocan Zhang, Xiaolu Jiang, Wei Zhao
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10766582/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173231046066176
author Baocan Zhang
Xiaolu Jiang
Wei Zhao
author_facet Baocan Zhang
Xiaolu Jiang
Wei Zhao
author_sort Baocan Zhang
collection DOAJ
description Automated cell segmentation in cervical cytology images is an essential task because it can present a deep understanding of the characteristics of cervical cells. The main challenge is that cells overlap at a high rate, making the cell boundaries extremely blurred. While the transformer-based models have been proven to be effective in vision tasks, this paper proposes an enhanced mask transformer based on DETR to segment overlapping cervical cells. Dynamic anchor box initialization and noised ground truth box embedding are introduced, to improve segmentation performance and accelerate model convergence. The proposed model achieves a 0.974 DSC, 0.971 TPRp, 0.0005 FPRp and 0.0012 FNRo on the ISBI2014 dataset. Specially, the proposed method outperforms state-of-the-art result by about 3.4% on DSC, 2% on TPRp and 1.88% on FNRo, respectively. The metrics of our model on the ISBI2015 dataset are a little better than the averaged metrics of other impressive methods. These findings present strong support for the transformer-based neural networks for effective segmentation of cells in cervical cytology images.
format Article
id doaj-art-7c8e5a3c8e344cd8bf642bb0e1d9e667
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-7c8e5a3c8e344cd8bf642bb0e1d9e6672025-08-20T02:19:54ZengIEEEIEEE Access2169-35362024-01-011217658617659710.1109/ACCESS.2024.350561610766582An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETRBaocan Zhang0https://orcid.org/0000-0001-8421-6404Xiaolu Jiang1https://orcid.org/0000-0002-9290-284XWei Zhao2https://orcid.org/0000-0002-6814-1526Chengyi College, Jimei University, Xiamen, Fujian, ChinaChengyi College, Jimei University, Xiamen, Fujian, ChinaChengyi College, Jimei University, Xiamen, Fujian, ChinaAutomated cell segmentation in cervical cytology images is an essential task because it can present a deep understanding of the characteristics of cervical cells. The main challenge is that cells overlap at a high rate, making the cell boundaries extremely blurred. While the transformer-based models have been proven to be effective in vision tasks, this paper proposes an enhanced mask transformer based on DETR to segment overlapping cervical cells. Dynamic anchor box initialization and noised ground truth box embedding are introduced, to improve segmentation performance and accelerate model convergence. The proposed model achieves a 0.974 DSC, 0.971 TPRp, 0.0005 FPRp and 0.0012 FNRo on the ISBI2014 dataset. Specially, the proposed method outperforms state-of-the-art result by about 3.4% on DSC, 2% on TPRp and 1.88% on FNRo, respectively. The metrics of our model on the ISBI2015 dataset are a little better than the averaged metrics of other impressive methods. These findings present strong support for the transformer-based neural networks for effective segmentation of cells in cervical cytology images.https://ieeexplore.ieee.org/document/10766582/Cervical cell segmentationDETRISBI datasetstransformer
spellingShingle Baocan Zhang
Xiaolu Jiang
Wei Zhao
An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETR
IEEE Access
Cervical cell segmentation
DETR
ISBI datasets
transformer
title An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETR
title_full An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETR
title_fullStr An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETR
title_full_unstemmed An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETR
title_short An Enhanced Mask Transformer for Overlapping Cervical Cell Segmentation Based on DETR
title_sort enhanced mask transformer for overlapping cervical cell segmentation based on detr
topic Cervical cell segmentation
DETR
ISBI datasets
transformer
url https://ieeexplore.ieee.org/document/10766582/
work_keys_str_mv AT baocanzhang anenhancedmasktransformerforoverlappingcervicalcellsegmentationbasedondetr
AT xiaolujiang anenhancedmasktransformerforoverlappingcervicalcellsegmentationbasedondetr
AT weizhao anenhancedmasktransformerforoverlappingcervicalcellsegmentationbasedondetr
AT baocanzhang enhancedmasktransformerforoverlappingcervicalcellsegmentationbasedondetr
AT xiaolujiang enhancedmasktransformerforoverlappingcervicalcellsegmentationbasedondetr
AT weizhao enhancedmasktransformerforoverlappingcervicalcellsegmentationbasedondetr