Feasibility of an Artificial Intelligence-Driven Classification of Tuberous Breast Deformity: A Siamese Network Approach With a Continuous Tuberosity Score
- 20 May 2025
- journal article
- Published by Oxford University Press (OUP) in Aesthetic Surgery Journal
- Vol. 45 (10) , 1094-1100
Abstract
Background: Tuberous breast deformity (TBD) is a congenital condition characterized by constriction of the breast base, parenchymal hypoplasia, and areolar herniation. The absence of a universally accepted classification system complicates diagnosis and surgical planning, leading to variability in clinical outcomes. Artificial intelligence (AI) has emerged as a powerful adjunct in medical imaging, enabling objective, reproducible, and data-driven diagnostic assessments. Objectives: This study introduces an AI-driven diagnostic tool for TBD classification using a Siamese network trained on paired frontal and lateral images. Additionally, the model generates a continuous Tuberosity Score (ranging from 0 to 1) based on embedding vector distances, offering an objective measure to enhance surgical planning and improved clinical outcomes. Methods: A dataset of 200 expertly classified frontal and lateral breast images (100 tuberous, 100 non-tuberous) was used to train a Siamese network with contrastive loss. The model extracted high-dimensional feature embeddings to differentiate tuberous from non-tuberous breasts. Five-fold cross-validation ensured robust performance evaluation. Performance metrics included accuracy, precision, recall, and F1-score. Visualization techniques, such as t-distributed Stochastic Neighbor Embedding clustering and occlusion sensitivity mapping, were employed to interpret model decisions. Results: The model achieved an average accuracy of 96.2% ± 5.5%, with balanced precision and recall. The Tuberosity Score, derived from the Euclidean distance between embeddings, provided a continuous measure of deformity severity, correlating well with clinical assessments. Conclusions: This AI-based framework offers an objective, high-accuracy classification system for TBD. The Tuberosity Score enhances diagnostic precision, potentially aiding in surgical planning and improving patient outcomes.Keywords
This publication has 19 references indexed in Scilit:
- Siamese Neural Network for Speech-Based Depression Classification and Severity AssessmentJournal of Healthcare Informatics Research, 2024
- The Different Surgical Strategies for Treating Tuberous Breast Deformity: A Scoping ReviewJPRAS Open, 2024
- Artificial Intelligence Optical Biopsy for Evaluating the Functional State of WoundsJournal of Surgical Research, 2023
- Few-shot learning using explainable Siamese twin network for the automated classification of blood cellsMedical & Biological Engineering & Computing, 2023
- Siamese few-shot network: a novel and efficient network for medical image segmentationApplied Intelligence, 2023
- Robust landmark-based brain shift correction with a Siamese neural network in ultrasound-guided brain tumor resectionInternational Journal of Computer Assisted Radiology and Surgery, 2022
- Stenotic Breast Malformation and Its Reconstructive Surgical Correction: A New Concept From Minor Deformity to Tuberous BreastAesthetic Plastic Surgery, 2017
- The Prevalence of Tuberous/Constricted Breast Deformity in Population and in Breast Augmentation and Reduction Mammaplasty PatientsAesthetic Plastic Surgery, 2016
- Tuberous Breast: Revised Classification and a New Hypothesis for its DevelopmentAesthetic Plastic Surgery, 2013
- The tuberous breast deformity: classification and treatmentBritish Journal of Plastic Surgery, 1996