File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Interactive Dual Network With Adaptive Density Map for Automatic Cell Counting

TitleInteractive Dual Network With Adaptive Density Map for Automatic Cell Counting
Authors
KeywordsAutomatic cell counting
Computer architecture
Deep learning
deep learning in healthcare
density map
Generators
healthcare automation
interactive dual network
Microprocessors
Microscopy
Pipelines
Training
Issue Date2023
Citation
IEEE Transactions on Automation Science and Engineering, 2023 How to Cite?
AbstractCell counting is an essential step in a wide variety of biomedical applications, such as blood examination, semen assessment, and cancer diagnosis. However, microscopic cell counting is conventionally labor-intensive and error-prone for experts, and most of the existing automatic approaches are confined to a specific image type. To address these challenges, we propose a new interactive dual-network framework for automatic and generic cell counting. In this framework, one deep learning model (counter) is trained to regress a density map from a given microscope image. The number of cells in that image can be estimated by performing integration over the regressed density map. Another network (ground truth generator) is employed to dynamically generate suitable ground truth based on the cell samples and the dot annotations to serve as the supervision for training the counter. The interactive process to obtain the optimal model is achieved by jointly training the counter and ground truth generator iteratively. Moreover, we design a hierarchical multi-scale attention-based architecture to act as the counter in the proposed framework. This architecture is crafted to efficiently and effectively process multi-level features, enabling accurate regression of high-quality density maps. Evaluation experiments on three public cell counting datasets demonstrate the superiority of our method. Note to Practitioners—This paper is motivated by the need for advanced healthcare in the deep learning era. As a routine assessment procedure in healthcare settings, cell counting usually suffers from poor accuracy and inefficiency. We provide a solution to ameliorate the situation by developing a deep learning-based framework for automatic cell counting. After being trained in an end-to-end manner, the dual-network system is able to estimate the number of cells from the given microscopic images more accurately than existing methods. Additionally, this method is robust in various scenarios, such as calculating cell populations in suspension and cells in tissues. In the future, the presented pipeline has the potential to be implemented by biomedical practitioners who are non-expert in programming via wrapping it into a graphical user interface.
Persistent Identifierhttp://hdl.handle.net/10722/349989
ISSN
2023 Impact Factor: 5.9
2023 SCImago Journal Rankings: 2.144

 

DC FieldValueLanguage
dc.contributor.authorLiu, Rui-
dc.contributor.authorZhu, Yudi-
dc.contributor.authorWu, Cong-
dc.contributor.authorGuo, Hao-
dc.contributor.authorDai, Wei-
dc.contributor.authorWu, Tianyi-
dc.contributor.authorWang, Min-
dc.contributor.authorLi, Wen Jung-
dc.contributor.authorLiu, Jun-
dc.date.accessioned2024-10-17T07:02:20Z-
dc.date.available2024-10-17T07:02:20Z-
dc.date.issued2023-
dc.identifier.citationIEEE Transactions on Automation Science and Engineering, 2023-
dc.identifier.issn1545-5955-
dc.identifier.urihttp://hdl.handle.net/10722/349989-
dc.description.abstractCell counting is an essential step in a wide variety of biomedical applications, such as blood examination, semen assessment, and cancer diagnosis. However, microscopic cell counting is conventionally labor-intensive and error-prone for experts, and most of the existing automatic approaches are confined to a specific image type. To address these challenges, we propose a new interactive dual-network framework for automatic and generic cell counting. In this framework, one deep learning model (counter) is trained to regress a density map from a given microscope image. The number of cells in that image can be estimated by performing integration over the regressed density map. Another network (ground truth generator) is employed to dynamically generate suitable ground truth based on the cell samples and the dot annotations to serve as the supervision for training the counter. The interactive process to obtain the optimal model is achieved by jointly training the counter and ground truth generator iteratively. Moreover, we design a hierarchical multi-scale attention-based architecture to act as the counter in the proposed framework. This architecture is crafted to efficiently and effectively process multi-level features, enabling accurate regression of high-quality density maps. Evaluation experiments on three public cell counting datasets demonstrate the superiority of our method. <italic>Note to Practitioners</italic>&#x2014;This paper is motivated by the need for advanced healthcare in the deep learning era. As a routine assessment procedure in healthcare settings, cell counting usually suffers from poor accuracy and inefficiency. We provide a solution to ameliorate the situation by developing a deep learning-based framework for automatic cell counting. After being trained in an end-to-end manner, the dual-network system is able to estimate the number of cells from the given microscopic images more accurately than existing methods. Additionally, this method is robust in various scenarios, such as calculating cell populations in suspension and cells in tissues. In the future, the presented pipeline has the potential to be implemented by biomedical practitioners who are non-expert in programming via wrapping it into a graphical user interface.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Automation Science and Engineering-
dc.subjectAutomatic cell counting-
dc.subjectComputer architecture-
dc.subjectDeep learning-
dc.subjectdeep learning in healthcare-
dc.subjectdensity map-
dc.subjectGenerators-
dc.subjecthealthcare automation-
dc.subjectinteractive dual network-
dc.subjectMicroprocessors-
dc.subjectMicroscopy-
dc.subjectPipelines-
dc.subjectTraining-
dc.titleInteractive Dual Network With Adaptive Density Map for Automatic Cell Counting-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TASE.2023.3329973-
dc.identifier.scopuseid_2-s2.0-85177053541-
dc.identifier.eissn1558-3783-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats