Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.
ObjectiveTo explore the necessity of routine X-ray examination after lung surgery based on patient symptom burden. MethodsA retrospective study was conducted on the patients who underwent thoracoscopic lung resection at the Department of Thoracic Surgery of Guangdong Provincial People's Hospital from March 2020 to April 2023. The routine chest X-ray examination results and symptom burden of postoperative patients were analyzed. Symptom burden was evaluated using the Perioperative Symptom Assessment Lung inventory. Results A total of 2 101 patients were collected, including 915 males and 1 100 femals, with a median age of 56 years. Among patients who underwent routine postoperative chest X-ray, only 1.0% patients accepted intervention. Among patients who had chest X-ray after chest tube removal, only 0.5% of them needed intervention. Among patients who had chest X-ray one month after discharge, only 1.3% of them required intervention. The intervention group had significantly worse shortness of breath (3 points vs. 2 points, P=0.015), pain (2 points vs. 1 point, P=0.039), and disturbed sleep (3 points vs. 2 points, P=0.036) compared with the normal group. Conclusion Very few routine postoperative chest X-ray examinations change patients’ management, and patients who need extra-intervention tended to have more severe symptom burden after surgery.