Journal of pediatric surgery · 2025
Circapproved: Digital Pattern Recognition via Artificial Neural Network for the Identification of Normal Penis Parameters for Circumcision Eligibility Using Mobile App.
СтатьяНазвание и аннотация: Перевод в очереди
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.
Wahyudi Irfan, Utomo Chandra Prasetyo, Djauzi Samsuridjal, Fathurahman Muhamad, Situmorang Gerhard Reinaldi, Rodjani Arry, Risky Raharja Putu Angga, Yonathan Kevin, Santoso Budi, Khresna Dwidian, Pratama Muhammad Wildan, Insani Nashuha, Raditya Marco
Аннотация
BACKGROUND: Circumcision is a prevalent surgical procedure performed for medical, cultural, and religious reasons, requiring a thorough assessment of penile anatomy to determine eligibility, especially for identifying contraindications such as congenital anomalies. This study focuses on developing an artificial intelligence (AI) based digital pattern recognition system to accurately identify normal penile parameters for circumcision eligibility using a mobile application.
METHODS: Utilizing an Artificial Neural Network (ANN), the AI model was trained on digital images captured by parents or healthcare personnel from dorsal, lateral, and ventral views of the penis. The training employed advanced techniques such as image augmentation and transfer learning to overcome the challenges posed by a limited dataset. Ethical guidelines were strictly adhered to, with informed consent obtained from all participants, ensuring the study's compliance with the Declaration of Helsinki.
RESULTS: The AI model, integrated into the Circapproved mobile app, demonstrated high accuracy in classifying normal and abnormal penile conditions, achieving 88.89 % accuracy for the dorsal view, 90.91 % for the lateral view, and 92.5 % for the ventral view. The development pipeline included data preprocessing, data splitting, and augmentation, with the AI model being deployed on a cloud-based platform to ensure scalability and accessibility. The results indicate significant potential for the AI-driven mobile application to facilitate large-scale screening and streamline the circumcision approval process, particularly in resource-limited settings.
CONCLUSION: This approach highlights the potential of AI integration for enhancing the precision of circumcision approval process. Future research should focus on further addition to the dataset to increase model accuracy.
METHODS: Utilizing an Artificial Neural Network (ANN), the AI model was trained on digital images captured by parents or healthcare personnel from dorsal, lateral, and ventral views of the penis. The training employed advanced techniques such as image augmentation and transfer learning to overcome the challenges posed by a limited dataset. Ethical guidelines were strictly adhered to, with informed consent obtained from all participants, ensuring the study's compliance with the Declaration of Helsinki.
RESULTS: The AI model, integrated into the Circapproved mobile app, demonstrated high accuracy in classifying normal and abnormal penile conditions, achieving 88.89 % accuracy for the dorsal view, 90.91 % for the lateral view, and 92.5 % for the ventral view. The development pipeline included data preprocessing, data splitting, and augmentation, with the AI model being deployed on a cloud-based platform to ensure scalability and accessibility. The results indicate significant potential for the AI-driven mobile application to facilitate large-scale screening and streamline the circumcision approval process, particularly in resource-limited settings.
CONCLUSION: This approach highlights the potential of AI integration for enhancing the precision of circumcision approval process. Future research should focus on further addition to the dataset to increase model accuracy.