Skin health and disease · 2026
ALADIN (Acne Lesion And Density INdex): a novel tool for automatic acne severity assessment.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Medela Alfonso, Sabater Alberto, Hernández Montilla Ignacio, Mac Carthy Taig, Aguilar Andy, Fernández Gerardo, Martorell Antonio, Vera Carretero Sofia, Balboni Constanza, Martín Alcalde Javier, Ramírez Bellver Jose Luis, Martin-Gorgojo Alejandro, Rodriguez Jiménez Pedro, López Estebaranz Jose Luis
Аннотация
BACKGROUND: Acne affects approximately 80% of adolescents worldwide, regardless of age, sex or ethnicity. Effective treatment depends on timely and accurate severity assessment. However, the lack of methodological standardization results in high inter- and intraobserver variability. A standardized and explainable grading tool is needed to support consistent acne severity evaluation.
OBJECTIVES: To develop an artificial intelligence-driven tool that quantifies inflammatory lesion count and density from facial images to calculate scores aligned with the Investigator Global Assessment (IGA) scale.
METHODS: ALADIN (Acne Lesion And Density INdex) is designed as a simple mathematical model able to deliver reproducible and interpretable acne severity scores. We validated ALADIN retrospectively using two datasets: (i) a public dataset with predominantly severe cases of acne and (ii) a private dataset of mild-to-moderate cases. Validation results evaluated ALADIN against IGA and Global Acne Grading System (GAGS) scores, annotated by expert dermatologists.
RESULTS: Lesion detection with ALADIN was evaluated using precision, recall, mean average precision and mean absolute error (MAE). Acne grading performance was assessed via Pearson/Spearman correlations, MAE and Cohen's kappa. ALADIN's performance aligned well with the interobserver correlation of dermatologists, achieving Pearson correlations of 0.58 vs. 0.56 and 0.65 vs. 0.65 (private and public datasets, respectively) for IGA scores, and 0.32 vs. 0.44 and 0.43 vs. 0.44 for GAGS scores.
CONCLUSIONS: ALADIN demonstrates consistent performance and excellent interpretability. Compared with manual scoring systems, it provides a streamlined, data-driven alternative capable of minimizing observer bias. When integrated into a medical device software, it can further aid in standardizing acne severity assessment and enhance patient monitoring. However, in this study, analyses were predominately carried out with White and Asian patients. Future work will validate and ensure robustness with darker skin tones.
OBJECTIVES: To develop an artificial intelligence-driven tool that quantifies inflammatory lesion count and density from facial images to calculate scores aligned with the Investigator Global Assessment (IGA) scale.
METHODS: ALADIN (Acne Lesion And Density INdex) is designed as a simple mathematical model able to deliver reproducible and interpretable acne severity scores. We validated ALADIN retrospectively using two datasets: (i) a public dataset with predominantly severe cases of acne and (ii) a private dataset of mild-to-moderate cases. Validation results evaluated ALADIN against IGA and Global Acne Grading System (GAGS) scores, annotated by expert dermatologists.
RESULTS: Lesion detection with ALADIN was evaluated using precision, recall, mean average precision and mean absolute error (MAE). Acne grading performance was assessed via Pearson/Spearman correlations, MAE and Cohen's kappa. ALADIN's performance aligned well with the interobserver correlation of dermatologists, achieving Pearson correlations of 0.58 vs. 0.56 and 0.65 vs. 0.65 (private and public datasets, respectively) for IGA scores, and 0.32 vs. 0.44 and 0.43 vs. 0.44 for GAGS scores.
CONCLUSIONS: ALADIN demonstrates consistent performance and excellent interpretability. Compared with manual scoring systems, it provides a streamlined, data-driven alternative capable of minimizing observer bias. When integrated into a medical device software, it can further aid in standardizing acne severity assessment and enhance patient monitoring. However, in this study, analyses were predominately carried out with White and Asian patients. Future work will validate and ensure robustness with darker skin tones.