Advanced Industrial SCIence (산업과 과학)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Hybrid Attention and Synergic Neural Network Framework for Medical Image Classification

의료 영상 분류를 위한 하이브리드 어텐션 및 시너지 신경망 프레임워크

  • Zhi Zeng (Dept. of Computer and Media Engineering, Tongmyong University) ;
  • Ji-Hye Kim (Dept. of Game Design, Kongju National University) ;
  • Seung-Soo Shin (Dept. of Computer Engineering, Tongmyong University)
  • 증지 (동명대학교 컴퓨터미디어공학과) ;
  • 김지혜 (공주대학교 게임디자인학과) ;
  • 신승수 (동명대학교 컴퓨터공학과 )
  • Received : 2026.02.09
  • Accepted : 2026.03.20
  • Published : 2026.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

Medical image classification (MIC) plays a crucial role in computer-aided diagnosis by assisting clinicians in identifying pathological patterns. In this study, we propose an attention-enhanced synergic neural network (AM-SNN) framework for fine-grained medical image classification. The model was evaluated on two publicly available datasets: theChestX-ray dataset for thoracic disease detection and the BreakHis dataset for breast cancer histopathological image classification. Experimental results demonstrate that the proposed framework achieves superior performance compared to conventional CNN-based architectures. Furthermore, the consistent improvements observed across two heterogeneous datasets indicate that the proposed model is not limited to a specific disease type but exhibits strong generalization capability in different medical imaging modalities. The integration of attention mechanisms and synergic collaborative learning enables more discriminative feature extraction while improving model interpretability.

의료 영상 분류(MIC)는 병리학적 패턴 식별을 통해 임상의의 컴퓨터 보조 진단을 지원하는 핵심 역할을 수행한다. 본 연구에서는 정밀 의료 영상 분류를 위한 주의력 강화 시너지 신경망(AM-SNN) 프레임워크를 제안한다. 본 모델은 공개 데이터셋 두 가지(흉부 질환 검출용 ChestX-ray 데이터셋 및 유방암 조직병리학적 영상 분류용 BreakHis 데이터셋)에서 평가되었다. 실험 결과, 제안된 프레임워크가 기존 CNN 기반 아키텍처 대비 우수한 성능을 달성함을 입증하였다. 또한 두 이질적 데이터셋 전반에서 관찰된 일관된 성능 향상은 제안 모델이 특정 질환 유형에 국한되지 않고 다양한 의료 영상 모달리티에서 강력한 일반화 능력을 발휘함을 시사한다. 어텐션 메커니즘과 시너지적 협업 학습의 통합은 모델 해석성을 향상시키면서 더 차별화된 특징 추출을 가능케 한다.

Keywords

References

  1. Litjens, G., et al. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60-88. DOI : 10.1016/j.media.2017.07.005.
  2. Shen, D., Wu, G., & Suk, H. I. (2017). Deep learning in medical image analysis. Annual Review of Biomedical Engineering, 19, 221-248. DOI : 10.1146/annurev-bioeng-071516-044442.
  3. Esteva, A., et al.(2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118. DOI: 10.1038/nature21056.
  4. Rajpurkar, P., et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint, arXiv:1711.05225.
  5. Wang, X., et al. (2017). ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification. CVPR, 2097-2106. DOI : 10.1109/CVPR.2017.369.
  6. S. Woo, J. Park, J. Y. Lee, I. S. Kweon. (2018). CBAM: Convolutional block attention modul. ECCV, 3-19. DOI : 10.1007/978-3-030-01234-2_1.
  7. Hu, J. Shen, L., & Sun, G. (2018). Squeeze and-Excitation networks. CVPR, 7132-7141. DOI : 10.1109/CVPR.2018.00745.
  8. Oktay, O., et al., (2018). Attention U-Net: Learning where to look for the pancreas. MICCAI, 65-73. DOI : 10.1007/978-3-030-00934-2_8.
  9. Schlemper, J., et al., (2019). Attention gated networks for medical image analysis. Medical Image Analysis, 53, 197-207. DOI : 10.1016/j.media.2019.01.012.
  10. Zhang, J., et al., (2019). Synergic deep learning for medical image classification. IEEE Transactions on Neural Networks and Learning Systems, 30(8), 2436-2446. DOI : 10.1109/TNNLS.2018.2882018.
  11. Nguyen, H. T., Le, M. H., & Nguyen, T. Q. (2020). Attention-based multi-branch deep neural network for medical image classification. IEEE Access, 8, 191515-191527. DOI : 10.1109/ACCESS.2020.3032924.
  12. Chen, Y., Wang, L., & He, X. (2021). Collaborative learning for medical image recognition with synergic loss. Pattern Recognition, 110, 107630. DOI : 10.1016/j.patcog.2020.107630.
  13. Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2019). UNet++: Redesigning skip connections to exploit multiscale features in medical image segmentation. Medical Image Analysis, 54, 124-138. DOI : 10.1016/j.media.2019.02.002.
  14. Li, X. Xiong, H., & Wang, H. (2022). Dual-path attention network for medical image classification. Computers in Biology and Medicine, 141, 105086. DOI : 10.1016/j.compbiomed.2021.105086.
  15. Li, J., Chen, J., Tang, Y., Wang, C., Zhou, S. K. (2023). Transforming medical imaging with Transformers? A comparative review. Medical Image Analysis, 85, 102762. DOI : 10.1016/j.media.2023.102762.
  16. He, K., Zhang, X., Ren, S., & Sun, J. (2022). Revisiting ResNets: Improved training and scaling strategies. IEEE TPAMI, 44(9), 5589-5602. DOI : 10.1109/TPAMI.2021.3103275.
  17. Liu, T. Guo, Y., & Wu, H. (2021). Channel-spatial attention mechanism for medical image classification. Applied Intelligence, 51(8), 660-5675. DOI : 10.1007/s10489-021-02294-3.
  18. Xu, J., Lin, S., Wei, F., & Hu, H. (2019). GCNet: Non-local networks meet squeeze-excitation networks and beyond. ICCV, 1971-1980. DOI : 10.1109/ICCV.2019.00206.
  19. Azizi, S., et al. (2021). Big self-supervised models advance medical image classification. ICCV, 3478-3488. DOI : 10.1109/ICCV48922.2021.00348.
  20. Touvron, H., et al., (2021). Going deeper with Image Transformers. ICCV, 32-42. DOI: 10.1109/ICCV48922.2021.00010.
  21. Yamashita, R., Nishio, M., Do, R., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into Imaging, 9(4), 611-629. DOI : 10.1007/s13244-018-0639-9.
  22. Irvin, J., et al., (2019). CheXpert: A large chest radiograph dataset with uncertainty labels. AAAI, 33, 590-597. DOI : 10.1609/aaai.v33i01.3301590.
  23. Benhammou, A., Achchab, M., Herrera, F., & Tabik, S. (2020). Break His based breast cancer classification using deep learning. Expert Systems with Applications, 160, 113693. DOI: 10.1016/i.eswa.2020.113693.