The aim of this clinical study was to compare the outcome of quantitative laser/light‐induced fluorescence (QLF) and visual inspection (VI) for the detection of initial caries lesions on all maxillary and mandibular smooth surfaces in caries‐risk adolescents. The subjects were 34 students, mean age 15 yr. A total of 879 buccal and 882 lingual surfaces were air‐dried and visually examined at a magnification of ×3.5. Fluorescence images of each smooth surface were captured with QLF\clin equipment, and QLF software 2.00 was used to display, store, and analyse the images. Fluorescence loss (ΔF; %) and area of the lesion (A; mm²), and fluorescence loss integrated over the lesion area (ΔQ; ΔF × A; % × mm²), were determined. The presence or absence of initial caries lesions was scored using both VI and QLF. A total of 87.2% of all smooth surfaces were scored as sound or initially carious when assessed by VI+QLF in combination: 4.9% were detected by VI alone and 7.9% by QLF alone. The parameters ΔF, A, and ΔQ differed significantly between lesions registered with VI+QLF and QLF alone. It was concluded that (i) QLF seems to be a sensitive method that is suitable for the detection of visually undetected initial caries lesions; and (ii) that the clinical use of QLF is limited by several confounding factors in caries‐risk adolescents.