A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise images
Histopathology image classification is crucial in pathological diagnosis workflow for early detection and treatment. The integration of deep learning technology has greatly improved diagnostic accuracy and efficiency. However, there are limitations when morphological features are not obvious in path...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824012468 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583105533181952 |
|---|---|
| author | Hui Zong Wenlong An Xin Chen Zhanhui Yang Heng Zhou Xiangchao Liu Jianchu Lin Chuanyue Zong |
| author_facet | Hui Zong Wenlong An Xin Chen Zhanhui Yang Heng Zhou Xiangchao Liu Jianchu Lin Chuanyue Zong |
| author_sort | Hui Zong |
| collection | DOAJ |
| description | Histopathology image classification is crucial in pathological diagnosis workflow for early detection and treatment. The integration of deep learning technology has greatly improved diagnostic accuracy and efficiency. However, there are limitations when morphological features are not obvious in pathological sections, leading to difficulties in identifying deep cells and an increased risk of misdiagnosis. To address this issue, this study introduces a new hybrid network model, termed ICDNET, designed to fuse global and local features without destroying the integrity of the feature data, thus enhancing the accuracy of medical image classification. The ICDNET model consists of two main features: (i) a serial hierarchical structure composed of global and local feature blocks; and (ii) an Internal Communication Hierarchical Fusion Block (ICHF) and an Efficient Dual Self-Attention (EDA) mechanism. This network structure solves internal communication issues and enriches contextual semantic information, extracting local features and global representations from different internal spaces. To evaluate the performance of the ICDNET network model, experiments were conducted on four major public datasets with the addition of Gaussian noise. The experimental results demonstrate excellent accuracy and the ability to handle limited training samples, highlighting the potential of the ICDNET model to assist pathologists in pathological diagnosis. |
| format | Article |
| id | doaj-art-99c343c1ea814460bc1692993a9ba6e9 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-99c343c1ea814460bc1692993a9ba6e92025-01-29T05:00:06ZengElsevierAlexandria Engineering Journal1110-01682025-01-011123748A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise imagesHui Zong0Wenlong An1Xin Chen2Zhanhui Yang3Heng Zhou4Xiangchao Liu5Jianchu Lin6Chuanyue Zong7Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, China; Faculty of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China; Corresponding author at: Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, China.Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, ChinaFaculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, ChinaFaculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, ChinaFaculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, ChinaFaculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, ChinaFaculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, China; Jiangsu Key Lab of Image and Video Understanding for Social Security, and Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and Technology, Nanjing, 210094, ChinaThe Affiliated Huaian Hospital of Xuzhou Medical University, Huaian 223001, ChinaHistopathology image classification is crucial in pathological diagnosis workflow for early detection and treatment. The integration of deep learning technology has greatly improved diagnostic accuracy and efficiency. However, there are limitations when morphological features are not obvious in pathological sections, leading to difficulties in identifying deep cells and an increased risk of misdiagnosis. To address this issue, this study introduces a new hybrid network model, termed ICDNET, designed to fuse global and local features without destroying the integrity of the feature data, thus enhancing the accuracy of medical image classification. The ICDNET model consists of two main features: (i) a serial hierarchical structure composed of global and local feature blocks; and (ii) an Internal Communication Hierarchical Fusion Block (ICHF) and an Efficient Dual Self-Attention (EDA) mechanism. This network structure solves internal communication issues and enriches contextual semantic information, extracting local features and global representations from different internal spaces. To evaluate the performance of the ICDNET network model, experiments were conducted on four major public datasets with the addition of Gaussian noise. The experimental results demonstrate excellent accuracy and the ability to handle limited training samples, highlighting the potential of the ICDNET model to assist pathologists in pathological diagnosis.http://www.sciencedirect.com/science/article/pii/S1110016824012468Internal Communication Network with Dual Self-Attention (ICDNET)Internal Communication Hierarchical Fusion (ICHF)Efficient Dual Self-Attention (EDA)Feature fusionHistopathological imagesGaussian noise |
| spellingShingle | Hui Zong Wenlong An Xin Chen Zhanhui Yang Heng Zhou Xiangchao Liu Jianchu Lin Chuanyue Zong A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise images Alexandria Engineering Journal Internal Communication Network with Dual Self-Attention (ICDNET) Internal Communication Hierarchical Fusion (ICHF) Efficient Dual Self-Attention (EDA) Feature fusion Histopathological images Gaussian noise |
| title | A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise images |
| title_full | A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise images |
| title_fullStr | A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise images |
| title_full_unstemmed | A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise images |
| title_short | A deep learning ICDNET architecture for efficient classification of histopathological cancer cells using Gaussian noise images |
| title_sort | deep learning icdnet architecture for efficient classification of histopathological cancer cells using gaussian noise images |
| topic | Internal Communication Network with Dual Self-Attention (ICDNET) Internal Communication Hierarchical Fusion (ICHF) Efficient Dual Self-Attention (EDA) Feature fusion Histopathological images Gaussian noise |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824012468 |
| work_keys_str_mv | AT huizong adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT wenlongan adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT xinchen adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT zhanhuiyang adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT hengzhou adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT xiangchaoliu adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT jianchulin adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT chuanyuezong adeeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT huizong deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT wenlongan deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT xinchen deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT zhanhuiyang deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT hengzhou deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT xiangchaoliu deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT jianchulin deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages AT chuanyuezong deeplearningicdnetarchitectureforefficientclassificationofhistopathologicalcancercellsusinggaussiannoiseimages |