Advancements in Deep Learning Enhance Diagnostic Accuracy in Non-Small Cell Lung Cancer

Strategic Insights -

Research by Jawaharlal Nehru Technological University Kakinada has proposed the integration of Differential Augmentation with Convolutional Neural Networks to address memory overfitting in lung cancer detection. The team utilized multiple datasets, including the IQ-OTH/NCCD dataset, and achieved an accuracy of 98.78% using the proposed CNN + DA model. This surpasses the performance of state-of-the-art models such as DenseNet, ResNet, and EfficientNetB0.

Key Takeaways:

  • The research integrated Differential Augmentation with Convolutional Neural Networks to enhance diagnostic accuracy in non-small cell lung cancer.
  • The proposed CNN + DA model achieved an accuracy of 98.78%, outperforming advanced models like DenseNet, ResNet, and EfficientNetB0.
  • The study utilized multiple datasets, including the IQ-OTH/NCCD dataset, to evaluate the proposed model against existing state-of-the-art methods.
  • The research concluded that the novel CNN + DA architecture provides a robust, accurate, and computationally efficient framework for lung cancer detection.
  • Vahiduddin Shariff, Dept. of Computer Science and Engineering, UCEK, contributed to this research, alongside Chiranjeevi Paritala and Krishna Mohan Ankala.
  • The study suggests that the CNN + DA model effectively addresses the limitations of prior works by reducing overfitting and ensuring reliable generalization across diverse datasets.

Statistics:

  • The proposed CNN + DA model achieved an accuracy of 98.78%.
  • The study utilized multiple datasets, including the IQ-OTH/NCCD dataset.
  • The research concluded that the novel CNN + DA architecture provides a robust, accurate, and computationally efficient framework for lung cancer detection.
  • The study compares the performance of the CNN + DA model to advanced models like:

+ DenseNet: 93.12%

+ ResNet: 94.56%

+ EfficientNetB0: 96.21%

  • The research utilized Random Search to optimize parameters and further improve performance.

Sources:

  • Optimizing non small cell lung cancer detection with convolutional neural networks and differential augmentation. Scientific Reports, 2025;15(1):15640. Scientific Reports can be contacted at: Nature Portfolio, Heidelberger Platz 3, Berlin, 14197, Germany.
  • NewsRx. Jawaharlal Nehru Technological University Kakinada Reports Findings in Non-Small Cell Lung Cancer (Optimizing non small cell lung cancer detection with convolutional neural networks and differential augmentation). Journal of Engineering. May 19, 2025; p 1473.