Few-Shot Fingerprinting Subject Re-Identification in 3D-MRI and 2D-X-Ray

2025/12/18 by Alves, Gonçalo Gaspar, Zadeh, Shekoufeh Gorgi, Husch, Andreas +1
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2512.16685

Abstract

Combining open-source datasets can introduce data leakage if the same subject appears in multiple sets, leading to inflated model performance. To address this, we explore subject fingerprinting, mapping all images of a subject to a distinct region in latent space, to enable subject re-identification via similarity matching. Using a ResNet-50 trained with triplet margin loss, we evaluate few-shot fingerprinting on 3D MRI and 2D X-ray data in both standard (20-way 1-shot) and challenging (1000-way 1-shot) scenarios. The model achieves high Mean- Recall-@-K scores: 99.10% (20-way 1-shot) and 90.06% (500-way 5-shot) on ChestXray-14; 99.20% (20-way 1-shot) and 98.86% (100-way 3-shot) on BraTS- 2021.

Citations

• Benchmarking Pretrained Vision Embeddings for Near- and Duplicate Detection in Medical Images
• The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification
• Understanding SSIM
• Cross-Batch Memory for Embedding Learning
• Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Deep Residual Learning for Image Recognition
• The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Related

• Few-Shot Learning for Biometric Verification
• Towards Zero-Shot Interpretable Human Recognition: A 2D-3D Registration Framework
• Latent Fingerprint Recognition: Fusion of Local and Global Embeddings
• Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
• Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification