An AI model that includes extracted radiomic features from CT scans more than doubled the sensitivity rate for preoperative prediction of lung cancer recurrence in comparison to traditional TNM staging, according to study findings to be presented at the 2024 American Society of Clinical Oncology (ASCO) Annual Meeting in Chicago.
Can emerging artificial intelligence (AI) models improve the prediction of postoperative lung cancer recurrence?
In a recent retrospective study, which will be presented the 2024 American Society of Clinical Oncology (ASCO) Annual Meeting, researchers compared pre-operative and postoperative AI models to clinical TNM staging and pathological TNM staging, respectively, for the prediction of lung cancer recurrence in 323 patients who had surgical treatment for stage I-IIIA lung cancer.
The AI models included extracted radiomic features from computed tomography (CT) scans and related clinical variables, according to the study. They noted the postoperative AI model also incorporated tumor histology and pathological staging.
In comparison to conventional TNM staging, the researchers found that the preoperative AI model had a higher area under the curve (AUC) (74.1 percent vs. 65.4 percent) and more than double the sensitivity rate (35.3 percent vs. 14.7 percent) for predicting lung cancer recurrence.
In comparison to conventional TNM staging, the researchers found that the preoperative AI model had a higher area under the curve (AUC) (74.1 percent vs. 65.4 percent) and more than double the sensitivity rate (35.3 percent vs. 14.7 percent) for predicting lung cancer recurrence.
The postoperative AI model also had a higher AUC (74.4 percent vs. 67.3 percent) and sensitivity rate (26.5 percent vs. 22.4 percent), according to the study authors.
“Based on this retrospective analysis, we find that the model outperforms staging prediction of lung cancer recurrence in pre- and post-operative settings. With further development, these algorithms could prove a valuable tool to aid the management of lung cancer patients,” noted lead study author Ann Valter, M.D., who is affiliated with the North Estonia Medical Center in Tallinn, Estonia, and colleagues.
The study authors said increased accuracy in predicting lung cancer recurrence risk can inform the use of neoadjunctive therapy and preoperative planning with lung nodule resection as well as postoperative follow-up care.
"The accurate determination of prognosis drives treatment decisions in oncology. Radiomic tools combined with demographics, as shown by Optellum, can be an effective non-invasive technology to optimize decision making early in the patient's journey, which may help to improve outcomes,” added Christine D. Berg, M.D., the co-principal investigator of the National Lung Screening Trial (NLST).
References
1. Valter A, Kordemets T, Gasimova A, et al. Pre- and post-operative lung cancer recurrence prediction following curative surgery: a retrospective study using European radiomics and clinical data. Presented at the 2024 American Society of Clinical Oncology (ASCO) Annual Meeting, May 31-June 4, 2024, Chicago. Available at: https://meetings.asco.org/abstracts-presentations/ . Accessed May 30, 2024.
2. Optellum. Optellum showcases AI for precision lung cancer treatment at ASCO 2024. PR Newswire. Available at: https://www.prnewswire.com/news-releases/optellum-showcases-ai-for-precision-lung-cancer-treatment-at-asco-2024-302159348.html
Stay at the forefront of radiology with the Diagnostic Imaging newsletter, delivering the latest news, clinical insights, and imaging advancements for today’s radiologists.
Study Reveals Significant Prevalence of Abnormal PET/MRI and Dual-Energy CT Findings with Long Covid
July 22nd 2025In a prospective study involving nearly 100 patients with Long Covid, 57 percent of patients had PET/MRI abnormalities and 90 percent of the cohort had abnormalities on dual-energy CT scans.
FDA Clears Point-Of-Care Ultrasound Platform and AI Software for Neuraxial Procedures
July 17th 2025The dual FDA clearances for the Accuro 3S point-of-care ultrasound device and the SpineNav-AI machine learning-based software may enhance precision and safety with ultrasound-guided neuraxial procedures.