News Lung Cancer Diagnostics & Imaging Operational Efficiency

First AI-Backed Medical Device FDA Approved for Detection and Diagnosis in Lung Cancer Screening

February 11, 2026 By ASCO AI Staff 2 min read
Share Share via Email Share on Facebook Share on LinkedIn Share on Twitter

The U.S. Food and Drug Administration (FDA) has issued a 510(k) clearance for eyonis® LCS, an AI/machine learning–powered software developed by Median Technologies for the detection and diagnosis of lung cancer, as a medical device for lung cancer screening. The software helps clinicians detect and characterize suspicious parenchymal pulmonary nodules earlier on low-dose CT scans.

“eyonis LCS is the first end-to-end detection and diagnosis device FDA cleared, specifically targeting lung cancer screenings. We believe eyonis LCS will prove to be a game changer for clinical teams as they manage rising screening volumes and help healthcare systems deliver high-accuracy and timely lung cancer diagnosis for eligible patients,” stated Fredrik Brag, the CEO and Founder of Median Technologies, in a press release. “Lung cancer screening combined with eyonis LCS has the capacity to deliver one of the most impactful advances in cancer care by identifying cancer at a stage where it can be cured. eyonis LCS will empower US clinicians to significantly transform lung cancer patient outcomes.” 

Under current eligibility criteria, about 14.5 million individuals qualify for lung cancer screening, with guidelines expected to expand to encompass an even broader population. However, real-world uptake of lung cancer screening remains low.

Additionally, the rate of false-positive results from low-dose CT-based lung cancer screenings amounts to about one in five patients, according to a study presented at the American Association for Cancer Research 2025 Annual Meeting (Abstract 7408), with rates potentially higher among older individuals.

According to Median Technologies, eyonis LCS can compensate for the growing shortage of radiologists by expanding access to screening and reducing operational burden.

The manufacturer tested eyonis LCS’s performance on a reference group of individuals eligible for lung cancer screening, and the software achieved a sensitivity of 93.3%, a specificity of 92.4%, and a negative predictive value of 99.9%.

eyonis LCS will be positioned under the existing New Technology APC 1508 code for accelerated adoption in this established reimbursement pathway. Through Medicare, payments for eyonis LCS are expected to range between $601 and $700.

ASCO AI in Oncology is published by Conexiant under a license arrangement with the American Society of Clinical Oncology, Inc. (ASCO®). The ideas and opinions expressed in ASCO AI in Oncology do not necessarily reflect those of Conexiant or ASCO. For more information, see Policies.

Performance of a convolutional neural network in determining differentiation levels of cutaneous squamous cell carcinomas was on par with that of experienced dermatologists, according to the results of a recent study published in JAAD International.

“This type of cancer, which is a result of mutations of the most common cell type in the top layer of the skin, is strongly linked to accumulated [ultraviolet] radiation over time. It develops in sun-exposed areas, often on skin already showing signs of sun damage, with rough scaly patches, uneven pigmentation, and decreased elasticity,” stated lead researcher Sam Polesie, MD, PhD, Associate Professor of Dermatology and Venereology at the University of Gothenburg and Practicing Dermatologist at Sahlgrenska University Hospital, both in Gothenburg, Sweden.

KOL Commentary
Watch

Related Content