Computer-Aided Nodule Assessment and Risk Yield is Associated with Clinical Outcome After Surgical Resection in Clinical Stage I Lung Adenocarcinoma 2cm and Less

J. Park¹, D. Pham², L. Ramsey², A. Sipok², S. Khandhar³, M. Weyant⁴, K. Suzuki^5
1Inova Health System, Fairfax, Virginia ²Inova Health System, Falls Church, Virginia ³Virginia Cancer Specialists, Fairfax, Virginia ⁴INOVA, Fairfax, Virginia ⁵Inova, Falls Church, Virginia

Purpose: As sub-lobar resection becomes acceptable for lung cancer ≤2cm, a preoperative marker to choose an appropriate extent of resection becomes necessary. Computer-Aided Nodule Assessment and Risk Yield (CANARY) is a validated radiomic tool in assessing recurrence risk in resected lung adenocarcinoma. We sought to assess its utility in ≤2cm lesions.

Methods: We performed a retrospective review of resected lung cancer patients from 2016-2021. Our eligibility criteria included clinical stage I adenocarcinoma ≤2cm and availability of pre-operative CT imaging. Recurrence dates, if any, were collected up to 5 years from the date of surgery. Preoperative imaging was entered into the CANARY software, and each lesion was categorized into good, intermediate, and poor risk. Kaplan-Meier curves were used to compare the recurrence free survival (RFS). Descriptive statistics and log-rank tests were conducted to compare RFS between risk groups. Hazard ratios (HR) and 95% confidence interval (CI) for poor risk vs good/intermediate risk were obtained from a Cox regression model adjusted for the patient’s gender, race/ethnicity, smoking status, age at surgery, and surgical procedure with p-value statistically significant at α=0.05.

Results: In total, 134 patients met our eligibility criteria. For the study cohort, average age at surgery was 68.5, 90 (67.2%) patients were female, and 25 (18.7%) were current smokers. By procedure, 82 (61.2%) patients underwent lobectomy, 51 (38.1%) underwent wedge resection, and 1 (0.7%) underwent a bilobectomy. By clinical stage, there were 18 (13.4%) stage IA1 and 109 (81.3%) IA2. Median follow-up period was 2.9 years.
By CANARY profile, there were 30 (22.4%) patients with good, 51 (38.1%) with intermediate, and 53 (39.6%) with poor risk. A total of 20 (14.9%) patients had recurrence, of whom 1 (0.7%) had good risk, 3 (2.2%) had intermediate risk, and 16 (11.9%) had poor risk. 5-year RFS for the entire cohort was 75.1%. By CANARY profile, 5-year RFS was 96.4%, 92.0%, and 56.8% for good, intermediate, and poor risks, respectively (p=0.002; Figure 1). Patients with poor risk were associated with a significantly increased risk of recurrence relative to those with good/intermediate risks (HR=5.4, 95% CI 1.8-16.4, p=0.003).

Conclusion: CANARY is able to risk stratify recurrence in stage I lung adenocarcinoma ≤2cm undergoing surgical resection. Future efforts will focus on assessing CANARY in determining risk of recurrence in sub-lobar vs lobectomy in this population.

Identify the source of the funding for this research project: No funding utilized