A Pneumonia Recognition Model Based on Multiscale Attention Improved EfficientNetV2
Source abstract
Abstract
To solve the problems of complex lesion region morphology, blurred edges, and limited hardware resources for deploying the recognition model in pneumonia image recognition, an improved EfficientNetV2 pneumonia recognition model based on multiscale attention is proposed. First, the number of main module stacks of the model is reduced to avoid overfitting, while the dilated convolution is introduced in the first convolutional layer to expand the receptive field of the model; second, a redesigned improved mobile inverted bottleneck convolution (IMBConv) module is proposed, in which GSConv is introduced to enhance the model’s attention to inter-channel information, and a SimAM module is introduced to reduce the number of model parameters while guaranteeing the model’s recognition performance; finally, an improved multi-scale efficient local attention (MELA) module is proposed to ensure the model’s recognition ability for pneumonia images with complex lesion regions. The experimental results show that the improved model has a computational complexity of 1.96 GFLOPs, which is reduced by 32% relative to the baseline model, and the number of model parameters is also reduced, and achieves an accuracy of 86.67% on the triple classification task of the public dataset Chest X-ray, representing an improvement of 2.74% compared to the baseline model. The recognition accuracies of ResNet50, Inception-V4, and Swin Transformer V2 on this dataset are 84.36%, 85.98%, and 83.42%, respectively, and their computational complexities and model parameter counts are all higher than those of the proposed model. This indicates that the proposed model has very high feasibility for deployment in edge computing or mobile healthcare systems. In addition, the improved model achieved the highest accuracy of 90.98% on the four-classification public dataset compared to other models, indicating that the model has better recognition accuracy and generalization ability for pneumonia image recognition.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Traditional Chinese Medicine Studies · COVID-19 diagnosis using AI · Ideological and Political Education
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (43)
Show source-provided references
1. Automated pneumonia diagnosis using a customized sequential convolutional neural network
2. An efficient deep learning approach to pneumonia classification in healthcare10.1155/2019/4180949 ↗
3. Computer-aided diagnosis in chest radiography for detection of childhood pneumonia10.1016/j.ijmedinf.2007.10.010 ↗
4. Computer-aided diagnosis of pulmonary infections using texture analysis and support vector machine classification10.1016/j.acra.2010.11.013 ↗
5. Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification10.1088/1361-6560/abe838 ↗
6. Comparative performance analysis of machine learning classifiers in detection of childhood pneumonia using chest radiographs10.1016/j.procs.2013.05.444 ↗
7. CoroNet: a deep neural network for detection and diagnosis of COVID-19 from chest X-ray images10.1016/j.cmpb.2020.105581 ↗
8. Automatic detection of multiple types of pneumonia: open dataset and a multi-scale attention network10.1016/j.bspc.2021.103415 ↗
9. DSEception: a noval neural networks architecture for enhancing pneumonia and tuberculosis diagnosis10.3389/fbioe.2024.1454652 ↗
10. Attention-based DenseNet for pneumonia classification10.1016/j.irbm.2021.12.004 ↗
11. Identifying medical diagnoses and treatable diseases by image-based deep learning10.1016/j.cell.2018.02.010 ↗
12. Pneumonia detection with QCSA network on chest X-ray10.1038/s41598-023-35922-x ↗
13. Pediatric pneumonia diagnosis using stacked ensemble learning on multi-model deep CNN architectures10.1007/s11042-022-13844-6 ↗
14. Tan · International Conference on Machine Learning · 2021 · 10096
15. Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification10.1007/s10586-024-04532-1 ↗
16. A lightweight CNN-based network on COVID-19 detection using X-ray and CT images10.1016/j.compbiomed.2022.105604 ↗
17. Slim-neck by GSConv: a lightweight-design for real-time detector architectures10.1007/s11554-024-01436-6 ↗
18. Squeeze-and-excitation networks
19. Yang · International Conference on Machine Learning · 2021 · 11863
20. Grad-CAM: visual explanations from deep networks via gradient-based localization
21. Lundberg S, Lee SI. A unified approach to interpreting model predictions. arXiv:1705.07874. 2017.
22. Tan · Proceedings of the 36th International Conference on Machine Learning · 2019 Jun 9–15 · 6105
23. Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122. 2015.
24. CBAM: convolutional block attention module
25. ECA-net: efficient channel attention for deep convolutional neural networks
26. Deep residual learning for image recognition
27. MobileNetV2: inverted residuals and linear bottlenecks
28. Multiscale attention guided network for COVID-19 diagnosis using chest X-ray images10.1109/JBHI.2021.3058293 ↗
29. MDRANet: a multiscale dense residual attention network for magnetic resonance and nuclear medicine image fusion10.1016/j.bspc.2022.104382 ↗
30. Xu W, Wan Y. ELA: efficient local attention for deep convolutional neural networks. arXiv:2403.01123. 2024.10.1007/s11554-025-01719-6 ↗
31. Lin T. Focal loss for dense object detection. arXiv:1708.02002. 2017.10.1109/ICCV.2017.324 ↗
32. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. 2014.
33. Inception-v4, inception-ResNet and the impact of residual connections on learning
34. Swin transformer V2: scaling up capacity and resolution
35. Mehta S, Rastegari M. Separable self-attention for mobile vision transformers. arXiv:2206.02680. 2022.
36. A ConvNet for the 2020s
37. Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16 × 16 words: transformers for image recognition at scale. arXiv:2010.11929. 2020.
38. LeViT: a vision transformer in ConvNet’s clothing for faster inference
39. Yue Y, Li Z. MedMamba: vision mamba for medical image classification. arXiv:2403.03849. 2024.
40. EfficientViT: memory efficient vision transformer with cascaded group attention
41. MetaFormer is actually what you need for vision
42. Li J, Xia X, Li W, Li H, Wang X, Xiao X, et al. Next-ViT: next generation vision transformer for efficient deployment in realistic industrial scenarios. arXiv:2207.05501. 2022.
43. Soares E, Angelov P, Biaso S, Froes MH, Abe DK. SARS-CoV-2 CT-scan dataset: a large dataset of real patients CT scans for SARS-CoV-2 identification. arXiv:2020.04.24.20078584. 2020.