Constantin von See

Smartphone-based augmented reality (AR) may help dentists visualize an implant axis during treatment or training. Before a virtual overlay can be displayed, however, the application must first recognize the real target reliably. This in vitro study tested how five lighting conditions affected recognition of a two-colored, 3D-printed polylactic acid (PLA) dental model by a Unity/Vuforia smartphone application. The application ran on a Samsung Galaxy S22. A GoPro HERO10 recorded the smartphone display at 240 frames per second, and the videos were evaluated frame by frame. Red, green, blue, daylight-like light-emitting diode (LED) and halogen illumination were tested at a central and an eccentric model position, with ten repetitions per condition and position. The model was not recognized under red or blue illumination within the predefined observation interval. Recognition was successful in all repetitions under green, daylight-like and halogen illumination. Recognition speed differed among these successful conditions, and the eccentric position delayed recognition under daylight-like and halogen illumination. A supplementary region-of-interest analysis also showed lighting-dependent differences in image brightness and contrast. These findings indicate that lighting should be standardized and documented when smartphone-based dental AR systems are developed and tested.

Osteoporosis may alter mandibular bone structure and peri-implant remodeling, but it remains unclear whether such changes are detectable on dental radiographs using deep learning. This retrospective study evaluated whether osteoporosis can be discriminated in two mandibular regions of interest: peri-implant bone and the mental foramen region. Digital periapical radiographs acquired between November 2012 and October 2024 were analyzed in 51 women, including 25 patients with osteoporosis and 26 non-osteoporotic controls without a documented history or diagnosis of osteoporosis; the osteoporosis group was significantly older than the control group. Two binary classification experiments were performed using patient-level fivefold grouped cross-validation. The peri-implant experiment included 1682 cropped images and used an image-plus-metadata ResNet-18 model incorporating the time interval between implant placement and radiograph acquisition. The mental foramen experiment included 102 cropped images and used an image-only ResNet-18 model. Mean accuracy, F1 score, and area under the receiver operating characteristic curve were 0.613, 0.628, and 0.713 for the peri-implant region of interest (ROI) and 0.701, 0.713, and 0.744 for the mental foramen ROI, respectively. Both experiments showed substantial fold-to-fold variability. These findings suggest that ROI selection influences model behavior, but neither approach yielded sufficiently stable ROI-level classification performance under patient-level grouped validation to support individual patient-level screening claims. Nondiscriminatory AI results should therefore be interpreted as limited evidence under the present experimental conditions rather than as proof of radiographic equivalence.