In Thoracic cancer
Artificial intelligence (AI) based on deep learning, convolutional neural networks and big data has been increasingly effective in the diagnosis and treatment of multiple primary pulmonary nodules. In comparison to previous imaging systems, AI measures more objective parameters such as three-dimensional (3D) volume, probability of malignant nodules, and possible pathological patterns, making the access to the properties of nodules more objective. In our retrospective study, a total of 53 patients with synchronous and metachronous multiple pulmonary nodules were enrolled of which 33 patients were confirmed by pathological tests to have primary binodules, and nine to have primary trinodules. A total of 15 patients had only one focus removed. The statistical results showed that the agreement in the AI diagnosis and postoperative pathological tests was 88.8% in identifying benign or malignant lesions. In addition, the probability of malignancy of benign lesions, preinvasive lesions (AAH, AIS) and invasive lesions (MIA, IA) was totally different (49.40±38.41% vs 80.22±13.55% vs 88.17±17.31%). The purpose of our study was to provide references for the future application of AI in the diagnosis and follow-up of multiple pulmonary nodules. AI may represent a relevant diagnostic aid that shows more accurate and objective results in the diagnosis of multiple pulmonary nodules, reducing the time required for interpretation of results by directly displaying visual information to doctors and patients and together with the clinical conditions of MPLC patients, offering plans for follow-up and treatment that may be more beneficial and reasonable for patients. Despite the great application potential in pneumosurgery, further research is needed to verify the accuracy and range of the application of AI.
Li Xin, Hu Bin, Li Hui, You Bin
3D volume, AI, follow-up, multiple primary lung cancer