A deep learning-based computed tomography reading system for the diagnosis of lung cancer associated with cystic airspaces

Objective To propose a deep learning model and explore its performance in the auxiliary diagnosis of lung cancer associated with cystic airspaces (LCCA) in computed tomography (CT) images. Methods This study is a retrospective analysis that incorporated a total of 342 CT images, comprising 272 images from patients diagnosed with LCCA and 70 images from patients with pulmonary bulla. A deep learning model named LungSSFNet, developed based on nnUnet, was utilized for image recognition and segmentation by experienced thoracic surgeons. The dataset was divided into a training set (245 images), a validation set (62 images), and a test set (35 images). The performance of LungSSFNet was compared with other models such as UNet, M2Snet, TANet, MADGNet, and nnUnet to evaluate its effectiveness in recognizing and segmenting LCCA and pulmonary bulla. Results LungSSFNet achieved an intersection over union of 81.05% and a Dice similarity coefficient of 75.15% for LCCA, and 93.03% and 92.04% for pulmonary bulla, respectively. These outcomes demonstrate that LungSSFNet outperformed many existing models in segmentation tasks. Additionally, it attained an accuracy of 96.77%, a precision of 100%, and a sensitivity of 96.15%. Conclusion LungSSFNet, a new deep-learning model, substantially improved the diagnosis of early-stage LCCA and is potentially valuable for auxiliary clinical decision-making. Our LungSSFNet code is available at https://github.com/zx0412/LungSSFNet.