Breakthrough in Lung Cancer Diagnosis Using Quantum Hippo Optimized Convolutional Neural Networks

Strategic Insights -

Lung cancer is one of the most deadly diseases affecting both men and women worldwide, causing a significant disturbance in life cycles and sometimes leading to fatal outcomes when left unnoticed. Recent advancements in artificial intelligence, particularly in medical and engineering fields, have led to the development of novel diagnostic tools. Researchers from the Department of Computer Science and Engineering have proposed a quantum-based learning framework, the Quantum Hippo Optimized Convolution Neural Network (QHO-CNN), to overcome the limitations of classical machine learning models in diagnosing lung cancer. The QHO-CNN combines classical and quantum computations to achieve high-speed diagnosis.

Key Takeaways:

  • The QHO-CNN learning framework consists of four components: data collection & data pre-processing, classical hippo optimized convolutional neural networks, quantum-based model using parametric quantum circuits (PQC), and evaluation and analysis.
  • The framework effectively diagnoses lung cancer with high accuracy, precision, recall, and F1-score.
  • The QHO-CNN demonstrated the strength of success in recognizing image data and quantum training compared to existing quantum models.
  • The learning framework is based on classical hippo optimized convolutional neural networks and parametric quantum circuits.
  • Classical learning frameworks consume significant computational resources, leading to complexity and low diagnostic performance.
  • The proposed learning framework was tested using the LIDC-IDRI Lung cancer dataset, which consists of 1018 CT lung images.
  • The QHO-CNN showed improved diagnostic performance compared to other existing quantum models.
  • The researchers conducted extensive experimentation, which included a variety of learning capability tests.

Statistics:

  • The QHO-CNN achieved an accuracy of 0.97, precision of 0.964, recall of 0.963, and F1-score of 0.97 in diagnosing lung cancer.
  • The framework showed strength of success in recognizing image data and quantum training with a time efficiency of 5.431 HRS.
  • The QHO-CNN outperformed other existing quantum models in diagnosing lung cancer.

Sources:

  • "Design and implementation of quantum hippo inspired convolutional neural networks using parametric quantum circuits for an efficient lung cancer classification." Discover Computing, 2025, 28(1):1-18.
  • "Research from Department of Computer Science and Engineering Provide New Insights into Lung Cancer (Design and implementation of quantum hippo inspired convolutional neural networks using parametric quantum circuits for an efficient lung cancer ...)." Health & Medicine Week. July 11, 2025; p 5137.