Prognostic impact of artificial intelligence-based volumetric quantification of the solid part of the tumor in clinical stage 0-I adenocarcinoma

• Published in: Lung cancer (Amsterdam, Netherlands) Netherlands), 2022-08, Vol.170, p.85-90
• Main Authors: Kawaguchi, Yohei, Shimada, Yoshihisa, Murakami, Kotaro, Omori, Tomokazu, Kudo, Yujin, Makino, Yojiro, Maehara, Sachio, Hagiwara, Masaru, Kakihana, Masatoshi, Yamada, Takafumi, Park, Jinho, Matsubayashi, Jun, Ohira, Tatsuo, Ikeda, Norihiko
• Format: Article
• Language: English
• Subjects: Adenocarcinoma; Artificial intelligence; Part-solid ground grass nodule; Three-dimensional convolutional network; Three-dimensional volumetric analysis
• ISSN: 0169-5002; 1872-8332
• DOI: 10.1016/j.lungcan.2022.06.007

•Appropriate evaluation of solid component of early-stage lung cancer is crucial.•A new volumetric analysis technique based on artificial intelligence was developed.•Artificial intelligence was more powerful prognostic factor than conventional methods. The size of the solid part of a tumor, as measured using thin-section computed tomography, can help predict disease prognosis in patients with early-stage lung cancer. Although three-dimensional volumetric analysis may be more useful than two-dimensional evaluation, measuring the solid part of some lesions is difficult using this methods. We developed an artificial intelligence-based analysis software that can distinguish the solid and non-solid parts (ground-grass opacity). This software calculates the solid part volume in a totally automated and reproducible manner. The predictive performance of the artificial intelligence software was evaluated in terms of survival or recurrence-free survival. We analyzed the high-resolution computed tomography images of the primary lesion in 772 consecutive patients with clinical stage 0-I adenocarcinoma. We performed automated measurement of the solid part volume using an artificial intelligence-based algorithm in collaboration with FUJIFILM Corporation. The solid part size, the solid part volume based on traditional three-dimensional volumetric analysis, and the solid part volume based on artificial intelligence were compared. Higher areas under the curve related to the solid part volume were provided by the artificial intelligence-based method (0.752) than by the solid part size (0.722) and traditional three-dimensional volumetric analysis-based method (0.723). Multivariate analysis demonstrated that the solid part volume based on artificial intelligence was independently correlated with overall survival (P = 0.019) and recurrence-free survival (P