基于人工智能的血管抑制技术在肺癌筛查计算机断层扫描中检测亚实性结节的应用
Artificial intelligence-based vessel suppression for detection of sub-solid nodules in lung cancer screening computed tomography.
作者信息
Singh Ramandeep, Kalra Mannudeep K, Homayounieh Fatemeh, Nitiwarangkul Chayanin, McDermott Shaunagh, Little Brent P, Lennes Inga T, Shepard Jo-Anne O, Digumarthy Subba R
机构信息
Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.
出版信息
Quant Imaging Med Surg. 2021 Apr;11(4):1134-1143. doi: 10.21037/qims-20-630.
BACKGROUND
Lung cancer screening (LCS) with low-dose computed tomography (LDCT) helps early lung cancer detection, commonly presenting as small pulmonary nodules. Artificial intelligence (AI)-based vessel suppression (AI-VS) and automatic detection (AI-AD) algorithm can improve detection of subsolid nodules (SSNs) on LDCT. We assessed the impact of AI-VS and AI-AD in detection and classification of SSNs [ground-glass nodules (GGNs) and part-solid nodules (PSNs)], on LDCT performed for LCS.
METHODS
Following regulatory approval, 123 LDCT examinations with sub-solid pulmonary nodules (average diameter ≥6 mm) were processed to generate three image series for each examination-unprocessed, AI-VS, and AI-AD series with annotated lung nodules. Two thoracic radiologists in consensus formed the standard of reference (SOR) for this study. Two other thoracic radiologists (R1 and R2; 5 and 10 years of experience in thoracic CT image interpretation) independently assessed the unprocessed images alone, then together with AI-VS series, and finally with AI-AD for detecting all ≥6 mm GGN and PSN. We performed receiver operator characteristics (ROC) and Cohen's Kappa analyses for statistical analyses.
RESULTS
On unprocessed images, R1 and R2 detected 232/310 nodules (R1: 114 GGN, 118 PSN) and 255/310 nodules (R2: 122 GGN, 133 PSN), respectively (P>0.05). On AI-VS images, they detected 249/310 nodules (119 GGN, 130 PSN) and 277/310 nodules (128 GGN, 149 PSN), respectively (P≥0.12). When compared to the SOR, accuracy (AUC) for detection of PSN on the AI-VS images (AUC 0.80-0.81) was greater than on the unprocessed images (AUC 0.70-0.76). AI-VS images enabled detection of solid components in five nodules deemed as GGN on the unprocessed images. Accuracy of AI-AD was lower than both the radiologists (AUC 0.60-0.72).
CONCLUSIONS
AI-VS improved the detection and classification of SSN into GGN and PSN on LDCT of the chest for the two radiologist (R1 and R2) readers.
背景
低剂量计算机断层扫描（LDCT）肺癌筛查有助于早期肺癌检测，常见表现为小的肺结节。基于人工智能（AI）的血管抑制（AI-VS）和自动检测（AI-AD）算法可提高LDCT上亚实性结节（SSN）[磨玻璃结节（GGN）和部分实性结节（PSN）]的检测率。我们评估了AI-VS和AI-AD对用于肺癌筛查的LDCT上SSN（GGN和PSN）的检测和分类的影响。
方法
经监管部门批准后，对123例有亚实性肺结节（平均直径≥6 mm）的LDCT检查进行处理，为每次检查生成三个图像系列——未处理系列、AI-VS系列和带有标注肺结节的AI-AD系列。两位胸放射科医生达成共识，形成了本研究的参考标准（SOR）。另外两位胸放射科医生（R1和R2；分别有5年和10年胸部CT图像解读经验）先独立评估未处理图像，然后与AI-VS系列一起评估，最后与AI-AD一起评估，以检测所有≥6 mm的GGN和PSN。我们进行了受试者操作特征（ROC）和科恩kappa分析以进行统计分析。
结果
在未处理图像上，R1和R2分别检测到232/310个结节（R1：114个GGN，118个PSN）和255/310个结节（R2：122个GGN，133个PSN）（P>0.05）。在AI-VS图像上，他们分别检测到249/310个结节（119个GGN，130个PSN）和277/310个结节（128个GGN，149个PSN）（P≥0.12）。与SOR相比，AI-VS图像上PSN检测的准确性（AUC）（AUC 0.80 - 0.81）高于未处理图像（AUC 0.70 - 0.76）。AI-VS图像能够检测出在未处理图像上被视为GGN的5个结节中的实性成分。AI-AD的准确性低于两位放射科医生（AUC 0.60 - 0.72）。
结论
对于两位放射科医生（R1和R2）读者，AI-VS提高了胸部LDCT上SSN向GGN和PSN的检测和分类。
Zotero 插件