Grad-Cam Empowered Lung Nodule Detecting Using Resnet50

Authors

  • Ushasree Shaini
  • Nithin Boda
  • Abhiram Lingampally
  • M Suneetha
  • K Jamal

Keywords:

Lung cancer, early detection, deep learning, ResNet50, Grad-CAM, nodule detection, CT imaging, interpretability, AI- based diagnostics, model validation, medical imaging, preprocessing, augmentation, feature extraction, clinical practice

Abstract

Lung cancer is a severe worldwide health issue that raises mortality rates. Improving patient survival depends on early detection. Using Grad-CAM and ResNet50, a deep convolutional neural network (CNN), this study offers an original approach for lung nodule detection. The suggested approach uses the sophisticated feature extraction capabilities of ResNet50 to recognize and categorize nodules in computed tomography (CT) data. Grad-CAM is used to improve the model's interpretability by providing visual explanations of its predictions. This helps healthcare professionals validate the results and boosts system trust. To guarantee strong generalization and enhance model performance, the dataset received extensive preprocessing, which included normalization and augmentation. The technique's remarkable accuracy of 0.98 shows the precision with which it can identify lung nodules.

This illustrates how ResNet50 and Grad-CAM can be combined to improve medical diagnoses by increasing the precision and understanding of AI algorithms. Professional annotations validated the model's precision in recognizing patterns in intricate medical imagery. In addition to demonstrating the viability of autonomous lung nodule identification, this work stresses the significance of model transparency, which promotes user trust in clinical contexts. In order to provide even more thorough visual explanations, future research will concentrate on developing the model by adding new datasets and putting Grad-CAM++ into practice. All things considered, this study has encouraging implications for enhancing lung cancer recognition and diagnosis and constitutes a substantial advancement in the use of AI-driven, interpretable medical diagnostics in clinical practice.

Downloads

Download data is not yet available.

References

Y. Wang, X. Liu, and J. Zhang, “Hybrid deep learning framework for lung nodule detection in CT images,” IEEE Access, vol. 9, pp. 112432–112441, 2021.

H. Li, Z. Yang, and K. Xu, “Lung nodule classification using ResNet-DenseNet ensemble with data augmentation,” IEEE Transactions on Medical Imaging, vol. 41, no. 3, pp. 603–614, Mar. 2022.

X. Chen, Q. Wang, and L. Huang, “3D convolutional neural networks for lung nodule detection,” in Proc. IEEE Int. Conf. Bioinformatics and Biomedicine (BIBM), pp. 1478–1484, 2023.

Y. Zhao, Y. Zhang, and B. Feng, “Attention-based CNN with self-attention for accurate lung nodule detection,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 1, pp. 134–143, Jan. 2023.

R. Ravi and S. Kumar, “Explainable lung nodule detection using Grad-CAM with ResNet50,” in Proc. IEEE Int. Symp. Biomedical Imaging (ISBI), pp. 480–483, 2022.

L. Zhu, J. Yu, and H. Wang, “Lung nodule detection in CT scans using CNN and feature fusion,” IEEE Access, vol. 9, pp. 101537–101546, 2021.

M. Jiang, C. Sun, and T. Li, “Ensemble CNN approach for robust lung nodule detection,” in Proc. IEEE Eng. Med. Biol. Soc. (EMBC), pp. 3258–3262, 2022.

S. Kang, D. Lee, and J. Kim, “Multi-task deep learning model for lung nodule classification and segmentation,” IEEE Access, vol. 11, pp. 25071–25082, 2023.

Y. Xia, M. Chen, and K. Liu, “Small lung nodule detection using a hybrid 2D-3D CNN architecture,” in Proc. IEEE Int. Conf. Machine Learning and Applications (ICMLA), pp. 780–785, 2021.

R. Mohan, A. Singh, and S. Verma, “Lung nodule detection using capsule networks: A deep learning approach,” IEEE Access, vol. 10, pp. 115237–115246, 2022.

Downloads

Published

2025-05-21

How to Cite

1.
Shaini U, Boda N, Lingampally A, Suneetha M, Jamal K. Grad-Cam Empowered Lung Nodule Detecting Using Resnet50. J Neonatal Surg [Internet]. 2025May21 [cited 2025Oct.1];14(26S):78-85. Available from: https://www.jneonatalsurg.com/index.php/jns/article/view/6244

Issue

Vol. 14 No. 26S (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.