Biomedical Signal Processing and Control
Task-Adaptive Multi-Prototype Prototypical Networks for keratoconus diagnosis under unbalanced small samples
By Shumin Zeng, Junsheng Yang, Wen Lin and 4 others.
Abstract
Objective
This study aims to develop and evaluate a meta-learning-based intelligent diagnostic algorithm for Keratoconus (KC), addressing limited training samples and class imbalance in corneal topography analysis. Early detection of KC remains clinically challenging yet crucial for timely intervention.
Methods
This study proposes a Task-Adaptive Multi-Prototype Prototypical Network (TA-MPN) architecture with a Swin Transformer backbone. The approach features: (1) a multi-prototype representation strategy (2-4-2 configuration for Normal, E-KC (incipient stage), and KC (complete stage) classes), (2) a task-level prototype adaptation mechanism, and (3) a balanced task sampling strategy with dual-loss optimization. The dataset comprised 462 corneal topographies with patient-level stratification into training (70%), validation (15%), and test (15%) sets.