RESUMO
OBJECTIVES: Skin cancer is a prevalent type of malignancy, necessitating efficient diagnostic tools. This study aimed to develop an automated skin lesion classification model using the dynamically expandable representation (DER) incremental learning algorithm. This algorithm adapts to new data and expands its classification capabilities, with the goal of creating a scalable and efficient system for diagnosing skin cancer. METHODS: The DER model with incremental learning was applied to the HAM10000 and ISIC 2019 datasets. Validation involved two steps: initially, training and evaluating the HAM10000 dataset against a fixed ResNet-50; subsequently, performing external validation of the trained model using the ISIC 2019 dataset. The model's performance was assessed using precision, recall, the F1-score, and area under the precision-recall curve. RESULTS: The developed skin lesion classification model demonstrated high accuracy and reliability across various types of skin lesions, achieving a weighted-average precision, recall, and F1-score of 0.918, 0.808, and 0.847, respectively. The model's discrimination performance was reflected in an average area under the curve (AUC) value of 0.943. Further external validation with the ISIC 2019 dataset confirmed the model's effectiveness, as shown by an AUC of 0.911. CONCLUSIONS: This study presents an optimized skin lesion classification model based on the DER algorithm, which shows high performance in disease classification with the potential to expand its classification range. The model demonstrated robust results in external validation, indicating its adaptability to new disease classes.
RESUMO
BACKGROUND: Children's motor development is a crucial tool for assessing developmental levels, identifying developmental disorders early, and taking appropriate action. Although the Korean Developmental Screening Test for Infants and Children (K-DST) can accurately assess childhood development, its dependence on parental surveys rather than reliable, professional observation limits it. This study constructed a dataset based on a skeleton of recordings of K-DST behaviors in children aged between 20 and 71 months, with and without developmental disorders. The dataset was validated using a child behavior artificial intelligence (AI) learning model to highlight its possibilities. RESULTS: The 339 participating children were divided into 3 groups by age. We collected videos of 4 behaviors by age group from 3 different angles and extracted skeletons from them. The raw data were used to annotate labels for each image, denoting whether each child performed the behavior properly. Behaviors were selected from the K-DST's gross motor section. The number of images collected differed by age group. The original dataset underwent additional processing to improve its quality. Finally, we confirmed that our dataset can be used in the AI model with 93.94%, 87.50%, and 96.31% test accuracy for the 3 age groups in an action recognition model. Additionally, the models trained with data including multiple views showed the best performance. CONCLUSION: Ours is the first publicly available dataset that constitutes skeleton-based action recognition in young children according to the standardized criteria (K-DST). This dataset will enable the development of various models for developmental tests and screenings.