Chiu Ming-Chuan, Tsai Stella Chin-Shaw, Bai Zhe-Rui, Lin Abraham, Chang Chi-Chang, Wang Guo-Zhi, Lin Frank Cheau-Feng
Department of Industrial Engineering and Industrial Management, National Tsing Hua University, Hsinchu, 300044, Taiwan.
Superintendent Office, Tungs' Taichung MetroHarbor Hospital, Taichung, Taiwan.
Heliyon. 2024 Apr 30;10(9):e30023. doi: 10.1016/j.heliyon.2024.e30023. eCollection 2024 May 15.
Primary spontaneous pneumothorax (PSP) primarily affects slim and tall young males. Exploring the etiological link between chest wall structural characteristics and PSP is crucial for advancing treatment methods. In this case-control study, chest computed tomography (CT) images from patients undergoing thoracic surgery, with or without PSP, were analyzed using Artificial Intelligence. Convolutional Neural Network (CNN) model of EfficientNetB3 and InceptionV3 were used with transfer learning on the Imagenet to compare the images of both groups. A heatmap was created on the chest CT scans to enhance interoperability, and the scale-invariant feature transform (SIFT) was adopted to further compare the image level. A total of 2,312 CT images of 26 non-PSP patients and 1,122 CT images of 26 PSP patients were selected. Chest-wall apex pit (CAP) was found in 25 PSP and three non-PSP patients (p < 0.001). The CNN achieved a testing accuracy of 93.47 % in distinguishing PSP from non-PSP based on chest wall features by identifying the existence of CAP. Heatmap analysis demonstrated CNN's precision in targeting the upper chest wall, accurately identifying CAP without undue influence from similar structures, or inappropriately expanding or minimizing the test area. SIFT results indicated a 10.55 % higher mean similarity within the groups compared to between PSP and non-PSP (p < 0.001). In conclusion, distinctive radiographic chest wall configurations were observed in PSP patients, with CAP potentially serving as an etiological factor linked to PSP. This study accentuates the potential of AI-assisted analysis in refining diagnostic approaches and treatment strategies for PSP.
原发性自发性气胸（PSP）主要影响瘦高的年轻男性。探索胸壁结构特征与PSP之间的病因联系对于改进治疗方法至关重要。在这项病例对照研究中，使用人工智能分析了接受胸外科手术的患者（无论有无PSP）的胸部计算机断层扫描（CT）图像。使用EfficientNetB3和InceptionV3的卷积神经网络（CNN）模型，并在Imagenet上进行迁移学习，以比较两组图像。在胸部CT扫描上创建热图以增强互操作性，并采用尺度不变特征变换（SIFT）进一步比较图像水平。共选择了26例非PSP患者的2312张CT图像和26例PSP患者的1122张CT图像。在25例PSP患者和3例非PSP患者中发现了胸壁尖凹（CAP）（p<0.001）。CNN通过识别CAP的存在，基于胸壁特征区分PSP和非PSP的测试准确率达到93.47%。热图分析表明，CNN在定位上胸壁方面具有精确性，能够准确识别CAP，而不受相似结构的不当影响，也不会不适当地扩大或缩小测试区域。SIFT结果表明，与PSP和非PSP之间相比，组内平均相似度高10.55%（p<0.001）。总之，在PSP患者中观察到了独特的胸部X线胸壁结构，CAP可能是与PSP相关的病因因素。本研究强调了人工智能辅助分析在完善PSP诊断方法和治疗策略方面的潜力。
