Deep Learning–Based Pattern Recognition for Detecting Penile Abnormalities: Protocol for Developing a Mobile App for Circumcision Eligibility
Bibliographic record
Abstract
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
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.034 | 0.010 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".