File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/JBHI.2018.2878878
- Scopus: eid_2-s2.0-85055863346
- PMID: 30387753
- WOS: WOS:000489729400028
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Large-scale multi-class image-based cell classification with deep learning
Title | Large-scale multi-class image-based cell classification with deep learning |
---|---|
Authors | |
Keywords | Bright field imaging Cell classification Convolutional neural network Multiclass classification |
Issue Date | 2019 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6221020 |
Citation | IEEE Journal of Biomedical and Health Informatics, 2019, v. 23 n. 5, p. 2091-2098 How to Cite? |
Abstract | Recent advances in ultra-high-throughput microscopy have enabled a new generation of cell classification methodologies using image-based cell phenotypes alone. In contrast to current single-cell analysis techniques that rely solely on slow and costly genetic/epigenetic analysis, these image-based analyses allow morphological profiling and screening of thousands or even millions of single cells at a fraction of the cost, and have been proven to demonstrate the statistical significance required for understanding the role of cell heterogeneity in diverse biological applications, ranging from cancer screening to drug candidate identification/validation processes. This paper examines the efficacies and opportunities presented by machine learning algorithms in processing large scale datasets with millions of label-free cell images. An automatic single-cell classification framework using convolutional neural network (CNN) has been developed. A comparative analysis of its efficiency in classifying large datasets against conventional k-nearest neighbors (kNN) and support vector machine (SVM) based methods are also presented. Experiments have shown that our proposed framework can efficiently identify multiple types cells with over 99% accuracy based on the phenotypic label-free bright-field images; and CNN-based models perform well and relatively stable against data volume compared with kNN and SVM. |
Persistent Identifier | http://hdl.handle.net/10722/275020 |
ISSN | 2023 Impact Factor: 6.7 2023 SCImago Journal Rankings: 1.964 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Meng, N | - |
dc.contributor.author | Lam, EY | - |
dc.contributor.author | Tsia, KK | - |
dc.contributor.author | So, HKH | - |
dc.date.accessioned | 2019-09-10T02:33:49Z | - |
dc.date.available | 2019-09-10T02:33:49Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | IEEE Journal of Biomedical and Health Informatics, 2019, v. 23 n. 5, p. 2091-2098 | - |
dc.identifier.issn | 2168-2194 | - |
dc.identifier.uri | http://hdl.handle.net/10722/275020 | - |
dc.description.abstract | Recent advances in ultra-high-throughput microscopy have enabled a new generation of cell classification methodologies using image-based cell phenotypes alone. In contrast to current single-cell analysis techniques that rely solely on slow and costly genetic/epigenetic analysis, these image-based analyses allow morphological profiling and screening of thousands or even millions of single cells at a fraction of the cost, and have been proven to demonstrate the statistical significance required for understanding the role of cell heterogeneity in diverse biological applications, ranging from cancer screening to drug candidate identification/validation processes. This paper examines the efficacies and opportunities presented by machine learning algorithms in processing large scale datasets with millions of label-free cell images. An automatic single-cell classification framework using convolutional neural network (CNN) has been developed. A comparative analysis of its efficiency in classifying large datasets against conventional k-nearest neighbors (kNN) and support vector machine (SVM) based methods are also presented. Experiments have shown that our proposed framework can efficiently identify multiple types cells with over 99% accuracy based on the phenotypic label-free bright-field images; and CNN-based models perform well and relatively stable against data volume compared with kNN and SVM. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6221020 | - |
dc.relation.ispartof | IEEE Journal of Biomedical and Health Informatics | - |
dc.subject | Bright field imaging | - |
dc.subject | Cell classification | - |
dc.subject | Convolutional neural network | - |
dc.subject | Multiclass classification | - |
dc.title | Large-scale multi-class image-based cell classification with deep learning | - |
dc.type | Article | - |
dc.identifier.email | Meng, N: nanmeng@eee.hku.hk | - |
dc.identifier.email | Lam, EY: elam@eee.hku.hk | - |
dc.identifier.email | Tsia, KK: tsia@hku.hk | - |
dc.identifier.email | So, HKH: hso@eee.hku.hk | - |
dc.identifier.authority | Lam, EY=rp00131 | - |
dc.identifier.authority | Tsia, KK=rp01389 | - |
dc.identifier.authority | So, HKH=rp00169 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/JBHI.2018.2878878 | - |
dc.identifier.pmid | 30387753 | - |
dc.identifier.scopus | eid_2-s2.0-85055863346 | - |
dc.identifier.hkuros | 303389 | - |
dc.identifier.volume | 23 | - |
dc.identifier.issue | 5 | - |
dc.identifier.spage | 2091 | - |
dc.identifier.epage | 2098 | - |
dc.identifier.isi | WOS:000489729400028 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 2168-2194 | - |