An Efficient Approach to Detecting Lung Nodules Using Swin Transformer
This work addresses the need for more efficient early lung cancer diagnosis through nodule detection, offering incremental improvements in accuracy for medical imaging.
The paper tackles the problem of inefficient lung nodule detection in CT scans by proposing a model that uses a tiny Swin Transformer with a Feature Pyramid Network and Transfer Learning, achieving state-of-the-art results with a mAP of 94.7% and mAR of 94.9%, including improvements of 1.3% in mAP and 1.6% in mAR for small nodules.
Lung cancer has the highest rate of cancer-caused deaths, and early-stage diagnosis could increase the survival rate. Lung nodules are common indicators of lung cancer, making their detection crucial. Various lung nodule detection models exist, but many lack efficiency. Hence, we propose a more efficient approach by leveraging 2D CT slices, reducing computational load and complexity in training and inference. We employ the tiny version of Swin Transformer to benefit from Vision Transformers (ViT) while maintaining low computational cost. A Feature Pyramid Network is added to enhance detection, particularly for small nodules. Additionally, Transfer Learning is used to accelerate training. Our experimental results show that the proposed model outperforms state-of-the-art methods, achieving higher mAP and mAR for small nodules by 1.3% and 1.6%, respectively. Overall, our model achieves the highest mAP of 94.7% and mAR of 94.9%.