AI-Assisted LC-OCT Feasible for Detecting Subclinical Basal Cell Carcinomas
By: Lisa Astor
Posted: Friday, September 25, 2026
Systematic screening with line-field confocal optical coherence tomography (LC-OCT) paired with artificial intelligence (AI)-assisted image recognition may be a feasible approach to detecting preclinical basal cell carcinomas in high-risk individuals, according to the results of a cross-sectional feasibility study published in JAMA Dermatology.
Researchers from Uniklinikum Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany, conducted a prospective cross-sectional feasibility study between April and October 2025 at their center. The study included patients receiving inpatient care who had at least two established risk factors (including history of basal cell carcinoma, number of prior basal cell carcinomas, older age, phototype 1 or 2 on the Fitzpatrick scale, and UV light exposure) for basal cell carcinoma, focusing on inconspicuous facial skin rather than lesions macroscopically suggestive of cancer.
Among 150 participants, 17 subclinical basal cell carcinomas were identified in 14 patients (9.3%). The AI-assisted LC-OCT diagnosed 18 lesions as basal cell carcinoma; 15 of these were histologically confirmed. The approach achieved a positive predictive value of 83.3% (95% confidence interval [CI] = 58.1%–96.4%). One lesion was actually actinic keratosis, and two patients declined biopsy, but experts analyzed and confirmed the diagnosis. In a sensitivity analysis that included the two nonbiopsied lesions, the positive predictive value increased to 94.4% (95% CI = 72.7%–99.9%).
Among the positive results were 13 cases of superficial basal cell carcinoma (76.5%), 3 cases of nodular basal cell carcinoma (17.6%), and 1 case of infiltrative disease (5.9%). Classification of subtypes was correct in 13 of 15 histologically confirmed cases (86.7%; 95% CI = 59.5%–98.3%).
The researchers noted that this approach could be integrated into the follow-up care of patients at an increased risk of developing basal cell carcinoma. They noted, however, that further prospective studies are needed to determine the sensitivity and cost-effectiveness of this screening approach, and to assess whether early detection leads to clinical benefit.
DISCLOSURE: For full disclosures of the study authors, visit jamanetwork.com.
