ConcatNeXt: An automated blood cell classification with a new deep convolutional neural network
Article
Erten, Mehmet, Barua, Prabal Datta, Dogan, Sengul, Tuncer, Turker, Tan, Ru‑San and Acharya, U. R.. 2024. "ConcatNeXt: An automated blood cell classification with a new deep convolutional neural network." Multimedia Tools and Applications. https://doi.org/10.1007/s11042-024-19899-x
| Article Title | ConcatNeXt: An automated blood cell classification with a new deep convolutional neural network |
|---|---|
| ERA Journal ID | 18083 |
| Article Category | Article |
| Authors | Erten, Mehmet, Barua, Prabal Datta, Dogan, Sengul, Tuncer, Turker, Tan, Ru‑San and Acharya, U. R. |
| Journal Title | Multimedia Tools and Applications |
| Number of Pages | 19 |
| Year | 2024 |
| Publisher | Springer |
| Place of Publication | United States |
| ISSN | 1380-7501 |
| 1573-7721 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1007/s11042-024-19899-x |
| Web Address (URL) | https://link.springer.com/article/10.1007/s11042-024-19899-x |
| Abstract | Examining peripheral blood smears is valuable in clinical settings, yet manual identification of blood cells proves time-consuming. To address this, an automated blood cell image classification system is crucial. Our objective is to develop a precise automated model for detecting various blood cell types, leveraging a novel deep learning architecture. We harnessed a publicly available dataset of 17,092 blood cell images categorized into eight classes. Our innovation lies in ConcatNeXt, a new convolutional neural network. In the spirit of Geoffrey Hinton's approach, we adapted ConvNeXt by substituting the Gaussian error linear unit with a rectified linear unit and layer normalization with batch normalization. We introduced depth concatenation blocks to fuse information effectively and incorporated a patchify layer. Integrating ConcatNeXt with nested patch-based deep feature engineering, featuring downstream iterative neighborhood component analysis and support vector machine-based functions, establishes a comprehensive approach. ConcatNeXt achieved notable validation and test accuracies of 97.43% and 97.77%, respectively. The ConcatNeXt-based feature engineering model further elevated accuracy to 98.73%. Gradient-weighted class activation maps were employed to provide interpretability, offering valuable insights into model decision-making. Our proposed ConcatNeXt and nested patch-based deep feature engineering models excel in blood cell image classification, showcasing remarkable classification performances. These innovations mark significant strides in computer vision-based blood cell analysis. © The Author(s) 2024. |
| Keywords | Blood cell image classification; ConcatNeXt; Deep feature engineering; Nested patch division; Computer vision |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 400309. Neural engineering |
| Byline Affiliations | Elazig Fethi Sekin City Hospital, Turkey |
| School of Business | |
| Firat University, Turkey | |
| National Heart Centre, Singapore | |
| Duke-NUS Medical School, Singapore | |
| School of Mathematics, Physics and Computing |
Permalink -
https://research.usq.edu.au/item/z99v4/concatnext-an-automated-blood-cell-classification-with-a-new-deep-convolutional-neural-network
Download files
145
total views22
total downloads14
views this month1
downloads this month