Artificial intelligence-driven computer aided diagnosis system provides similar diagnosis value compared with doctors' evaluation in lung cancer screening

• Published in: BMC medical imaging Vol. 24; no. 1; p. 141
• Main Authors: Gao, Shan, Xu, Zexuan, Kang, Wanli, Lv, Xinna, Chu, Naihui, Xu, Shaofa, Hou, Dailun
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 11.06.2024; BioMed Central; BMC
• Subjects: Adult; Aged; Algorithms; Antigens; Artificial Intelligence; Artificial neural networks; Cancer; Cancer screening; Comparative analysis; Computed Tomography; Consistency tests; Correlation coefficient; Correlation coefficients; CT imaging; Diagnosis; Diagnosis, Computer-Assisted - methods; Diagnostic imaging; Diameters; Early Detection of Cancer - methods; Evaluation; Female; Humans; Lung cancer; Lung Neoplasms - diagnostic imaging; Lung nodules; Male; Medical imaging; Medical screening; Middle Aged; Morphology; Neural networks; Neural Networks, Computer; Nodules; Pulmonary nodule; Radiographic Image Interpretation, Computer-Assisted - methods; Radiology; Regression analysis; Retrospective Studies; ROC Curve; Software; Thorax; Tomography, X-Ray Computed - methods; China; Beijing China; Computed Tomography; Diagnosis; Artificial Intelligence; Lung cancer; Pulmonary nodule
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-024-01288-3

To evaluate the consistency between doctors and artificial intelligence (AI) software in analysing and diagnosing pulmonary nodules, and assess whether the characteristics of pulmonary nodules derived from the two methods are consistent for the interpretation of carcinomatous nodules. This retrospective study analysed participants aged 40-74 in the local area from 2011 to 2013. Pulmonary nodules were examined radiologically using a low-dose chest 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 on the three-dimensional(3D) convolutional neural network (CNN) with DenseNet architecture(InferRead CT Lung, IRCL). Consistency tests were employed to assess the uniformity of the radiological characteristics of the pulmonary nodules. The receiver 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 demonstrated high consistency with the panel's evaluation in determining the position and diameter of the pulmonary nodules (kappa = 0.883, concordance correlation coefficient (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: 0.884-0.949), respectively. However, there was no significant difference (p = 0.0950). The maximum diameter, solid nodules, subsolid nodules were the crucial factors for interpreting carcinomatous nodules in the analysis of expert panel and IRCL pulmonary nodule characteristics. AI software can assist doctors in diagnosing nodules and is consistent with doctors' evaluations and diagnosis of pulmonary nodules.