A teacherless lightweight classification framework for benign and malignant pulmonary nodules based on GAS

Deep learning methods have been widely adopted for classifying benign and malignant pulmonary nodules. However, existing models often suffer from high memory usage, computational cost, and large parameter counts. As a result, the development of lightweight classification methods for pulmonary nodules has become a major research focus. This paper proposes a lightweight classification framework specifically designed to distinguish between benign and malignant pulmonary nodules. The model contains only 119,245 parameters and occupies just 0.45 MB, offering significant advantages in terms of computational efficiency. The proposed approach integrates an attention mechanism, residual learning, and an improved DWSGhost module to construct the GAS (Ghost-Attention Separation) network. A teacher-free knowledge distillation strategy is employed to build a lightweight classification model based on GAS. Extensive experiments were conducted on three datasets-LIDC-IDRI, LungX Challenge, and Zhengzhou Ninth People's Hospital-which demonstrated the model's effectiveness in classifying pulmonary nodules. The proposed method exhibits strong competitiveness among lightweight models and achieves promising classification performance. By incorporating depthwise separable convolutions and teacher-free knowledge distillation, along with attention mechanisms and residual learning, the model achieves enhanced performance in terms of lightweight design, discriminative power, adaptability, and generalization ability.The full code is available inhttps://github.com/s1371897388-ctrl/GAS-Pulmonary-Nodule-Classification.