Benchmarking Pretrained Vision Embeddings for Near- and Duplicate Detection in Medical Images
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909222771359744 |
|---|---|
| author | Truong, Tuan Jush, Farnaz Khun Lenga, Matthias |
| author_facet | Truong, Tuan Jush, Farnaz Khun Lenga, Matthias |
| contents | Near- and duplicate image detection is a critical concern in the field of medical imaging. Medical datasets often contain similar or duplicate images from various sources, which can lead to significant performance issues and evaluation biases, especially in machine learning tasks due to data leakage between training and testing subsets. In this paper, we present an approach for identifying near- and duplicate 3D medical images leveraging publicly available 2D computer vision embeddings. We assessed our approach by comparing embeddings extracted from two state-of-the-art self-supervised pretrained models and two different vector index structures for similarity retrieval. We generate an experimental benchmark based on the publicly available Medical Segmentation Decathlon dataset. The proposed method yields promising results for near- and duplicate image detection achieving a mean sensitivity and specificity of 0.9645 and 0.8559, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_07273 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Benchmarking Pretrained Vision Embeddings for Near- and Duplicate Detection in Medical Images Truong, Tuan Jush, Farnaz Khun Lenga, Matthias Computer Vision and Pattern Recognition Near- and duplicate image detection is a critical concern in the field of medical imaging. Medical datasets often contain similar or duplicate images from various sources, which can lead to significant performance issues and evaluation biases, especially in machine learning tasks due to data leakage between training and testing subsets. In this paper, we present an approach for identifying near- and duplicate 3D medical images leveraging publicly available 2D computer vision embeddings. We assessed our approach by comparing embeddings extracted from two state-of-the-art self-supervised pretrained models and two different vector index structures for similarity retrieval. We generate an experimental benchmark based on the publicly available Medical Segmentation Decathlon dataset. The proposed method yields promising results for near- and duplicate image detection achieving a mean sensitivity and specificity of 0.9645 and 0.8559, respectively. |
| title | Benchmarking Pretrained Vision Embeddings for Near- and Duplicate Detection in Medical Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.07273 |