Laser & Optoelectronics Progress, Volume. 60, Issue 10, 1010023(2023)
Esophageal Squamous Cell Carcinoma Recognition Based on Lightweight Residual Networks with an Attention Mechanism
Fig. 1. Architecture of CALite-ResNet
Fig. 2. Schematic of GhostModule
Fig. 3. Schematic illustration of improved SCConv
Fig. 4. Diagrams of residual block structures. (a) Bottleneck structure of ResNet50; (b) GSCBottleneck structure
Fig. 5. Structure of CA attention mechanism
Fig. 6. Structure of CA-GSCBottleneck module
Fig. 7. Schematic of majority voting method
Fig. 8. Example diagrams of effects obtained using different data enhancement methods. (a) Origin image; (b) random rotation; (c) horizontal flip; (d) random scaling
Fig. 9. ROC curves of different network models
Fig. 10. Grad-CAM visualizations
|
|
|
|
|
|
Get Citation
Copy Citation Text
Jinming Wang, Peng Li, Yan Liang, Wei Sun, Jie Song, Yadong Feng, Lingxiao Zhao. Esophageal Squamous Cell Carcinoma Recognition Based on Lightweight Residual Networks with an Attention Mechanism[J]. Laser & Optoelectronics Progress, 2023, 60(10): 1010023
Category: Image Processing
Received: Mar. 2, 2022
Accepted: May. 5, 2022
Published Online: May. 17, 2023
The Author Email: Zhao Lingxiao (hitic@sibet.ac.cn)