Deep Learning-Based Pattern Recognition for Detecting Penile Abnormalities: Protocol for Developing a Mobile App for Circumcision Eligibility.

BACKGROUND

Circumcision is a widely practiced procedure with cultural and medical significance. However, certain penile abnormalities-such as hypospadias or webbed penis-may contraindicate the procedure and require specialized care. In low-resource settings, limited access to pediatric urologists often leads to missed or delayed diagnoses. Artificial intelligence (AI)-based image recognition presents a scalable solution to facilitate early detection and informed decision-making.

OBJECTIVE

This study aims to develop and validate an AI-powered image classification system integrated into a mobile app to detect penile abnormalities and assess circumcision eligibility. The system is designed to support preliminary screening by general practitioners and caregivers in underserved areas.

METHODS

A prospective cohort study was conducted involving pediatric patients at Cipto Mangunkusumo Hospital, Jakarta, Indonesia. Digital images will be collected prospectively from pediatric patients at Cipto Mangunkusumo Hospital captured by health care professionals or caregivers. High-resolution penile images were systematically captured from ventral, dorsal, and lateral angles and subsequently classified as either having normal or abnormal anatomy by urologists. Leveraging pretrained deep learning architectures, the AI models were developed to accurately classify these images and assess circumcision eligibility based on anatomical criteria. Image preprocessing included resizing, normalization, and augmentation. Transfer learning techniques were used to enhance accuracy. The model was developed using TensorFlow and Keras. Performance evaluation used accuracy, sensitivity, specificity, and F1-score. Following development, the model will be embedded into a mobile app to enable real-time analysis, with feedback on whether further clinical evaluation or referral is needed.

RESULTS

Model development began in January 2024 and is currently ongoing. Integration into the mobile app and deployment testing are scheduled across 3 sequential phases-refinement, integration, and user testing-through January 2026. Preliminary models have been trained, and refinement is underway to improve diagnostic accuracy and usability.

CONCLUSIONS

The proposed AI-based system offers a promising tool to support early diagnosis of penile abnormalities and safe circumcision decision-making in resource-limited settings. Its integration into a mobile app enables preliminary screening outside specialized centers, facilitating telemedicine and optimizing referral pathways.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/65811.