首页|Capital Medical University Reports Findings in Artificial Intelligence (Artifici al intelligence-driven computer aided diagnosis system provides similar diagnosi s value compared with doctors' evaluation in lung cancer screening)
Capital Medical University Reports Findings in Artificial Intelligence (Artifici al intelligence-driven computer aided diagnosis system provides similar diagnosi s value compared with doctors' evaluation in lung cancer screening)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report. According to news reporting from Beijing, People's Republic of China, by NewsRx journalists, research stated, "To evaluate the con sistency between doctors and artificial intelligence (AI) software in analysing and diagnosing pulmonary nodules, and assess whether the characteristics of pulm onary nodules derived from the two methods are consistent for the interpretation of carcinomatous nodules. This retrospective study analysed participants aged 4 0-74 in the local area from 2011 to 2013." Financial support for this research came from Beijing Science and Technology Pla nning Project. The news correspondents obtained a quote from the research from Capital Medical University, "Pulmonary nodules were examined radiologically using a low-dose che st CT scan, evaluated by an expert panel of doctors in radiology, oncology, and thoracic departments, as well as a computer-aided diagnostic( CAD) system based o n the three-dimensional(3D) convolutional neural network (CNN) with DenseNet arc hitecture(InferRead CT Lung, IRCL). Consistency tests were employed to assess th e uniformity of the radiological characteristics of the pulmonary nodules. The r eceiver operating characteristic (ROC) curve was used to evaluate the diagnostic accuracy. Logistic regression analysis is utilized to determine whether the two methods yield the same predictive factors for cancerous nodules. A total of 570 subjects were included in this retrospective study. The AI software demonstrate d high consistency with the panel's evaluation in determining the position and d iameter of the pulmonary nodules (kappa = 0.883, concordance correlation coeffic ient (CCC) = 0.809, p = 0.000). The comparison of the solid nodules' attenuation characteristics also showed acceptable consistency (kappa = 0.503). In patients diagnosed with lung cancer, the area under the curve (AUC) for the panel and AI were 0.873 (95%CI: 0.829-0.909) and 0.921 (95%CI: 0.8 84-0.949), respectively. However, there was no significant difference (p = 0.095 0). The maximum diameter, solid nodules, subsolid nodules were the crucial facto rs for interpreting carcinomatous nodules in the analysis of expert panel and IR CL pulmonary nodule characteristics."
BeijingPeople's Republic of ChinaAsi aArtificial IntelligenceCancerComputersDiagnostics and ScreeningEmergi ng TechnologiesHealth and MedicineLung CancerLung Diseases and ConditionsLung NeoplasmsMachine LearningOncologySoftware
NETL
NSTL
