A Smartphone Application for Personalized Tooth Shade Determination

Abstract

Tooth shade determination methods for evaluating the effectiveness of whitening products at home are limited. In this study, an iPhone app for personalized tooth shade determination was developed. While capturing dental photographs in selfie mode before and after whitening, the app can maintain consistent illumination and tooth appearance conditions that affect tooth color measurement. An ambient light sensor was used to standardize the illumination conditions. To maintain consistent tooth appearance conditions determined by appropriately opening the mouth, facial landmark detection, an artificial intelligence technique that estimates key face parts and outlines, was used. The effectiveness of the app in ensuring uniform tooth appearance was investigated through color measurements of the upper incisors of seven participants via photographs captured in succession. The coefficients of variation for incisors L*, a*, and b* were less than 0.0256 (95% CI, 0.0173–0.0338), 0.2748 (0.1596–0.3899), and 0.1053 (0.0078–0.2028), respectively. To examine the feasibility of the app for tooth shade determination, gel whitening after pseudo-staining by coffee and grape juice was performed. Consequently, whitening results were evaluated by monitoring the ∆Eab color difference values (1.3 unit minimum). Although tooth shade determination remains a relative quantification method, the proposed method can support evidence-based selection of whitening products.

A smartphone application for personalized facial aesthetic monitoring

“…FLD, which estimates predefined landmarks (eyes, nose, mouth, eyebrows, and face outline) on facial images and provides geometric information, 16 was employed to ensure consistent facial appearance conditions. Specifically, the VNDetectFaceLandmarksRequest class 17 was utilized for FLD analysis within the Vision framework, Apple Inc.’s computer vision framework, to ensure uniform face appearance in each captured image. The FLD analysis yields XY coordinate information for 74 landmark points representing facial features when a human face is detected in the input real‐time video.…”

“…This step is crucial for standardizing illumination conditions during image captures, as demonstrated in our previous study, given its significance for relative quantitative color measurements of the captured image. 17 Subsequently, the screen brightness is manually maximized using the brightness bar in the iPhone's Control Center before launching the app. Upon detecting a face, the FAIN system is activated, turning the screen white and displaying the indicators.…”

“…To generate individualized target indicators, facial images of the mannequin and participants were captured in advance using the default Camera app on the iPhone, referred to as the criterion image. Subsequently, geometric information of the four points (Figure 1A ) was obtained using a laboratory‐developed FLD analysis app 17 employing the same VNDetectFaceLandmarksRequest class. This information was then input into the developed app to create personalized target indicators.…”

“…However, to achieve comprehensive facial aesthetic monitoring—a prerequisite for accurately gauging perceptions of age and health—a novel approach is imperative to standardize facial appearance conditions in images captured by smartphone cameras. Here, we introduce the face alignment indicators (FAIN) system, utilizing an artificial intelligence (AI) technique called Facial Landmark Detection (FLD), 16 , 17 to ensure consistent facial appearance during image capture. This system was integrated into an iOS camera application (app).…”

Correction: Kusayanagi et al. A Smartphone Application for Personalized Tooth Shade Determination. Diagnostics 2023, 13, 1969

“…In the original publication [ 1 ], there was a mistake in Figure 5 as published. The coordinate annotation of (d) in Figure 5 is incorrect.…”