Long-Term Survival and CANARY-Based Artificial Intelligence for Multifocal Lung Adenocarcinoma

Objective: To investigate whether an artificial intelligence (AI)–based model can predict tumor invasiveness in patients with multifocal lung adenocarcinoma (MFLA). Patients and Methods: Patients with MFLA who underwent surgical resection were enrolled to a prospective registry trial (NCT01946100). Each identified nodule underwent retrospective computer-aided nodule assessment and risk yield (CANARY)–based AI to determine a quantitative degree of invasiveness. Data regarding age, sex, medical and surgical management, and survival were collected and analyzed. Pathologic review was performed by a pulmonary pathologist with comprehensive histologic subtyping. Results: From January 1, 2013, through December 31, 2018, 68 patients with MFLA underwent at least 1 surgical resection. Five-year survival for the cohort was 91%, and 10-year survival was 73.6%. No significant differences in survival were observed when separated by sex, number, or size of the nodules. A 10-year survival trend was seen when comparing patients with unilateral (100% survival) vs bilateral disease (66%). Retrospective CANARY-based AI analysis demonstrated that the majority of the nodules present at the time of diagnosis (229/302; 75.8%) were classified good, with an average score of 0.19, suggesting indolent clinical behavior and noninvasive pathology. However, AI-CANARY scores of the surgically removed nodules were significantly higher compared with those of the nonresected nodules (P=.001). Conclusion: The long-term survival for patients with N0, M0 MFLA who have undergone surgical resection may approach those of stage I non–small cell lung cancer. CANARY-based AI has the potential to stratify individual nodules to help guide surgical intervention versus observation of nodules. Trial Registration: clinicaltrials.gov Identifier: NCT01946100