Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2505.15248 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909618044665856 |
|---|---|
| author | Dourson, Andre Taylor, Kylie Qiao, Xiaoli Fitzke, Michael |
| author_facet | Dourson, Andre Taylor, Kylie Qiao, Xiaoli Fitzke, Michael |
| contents | Self-supervised learning has emerged as a powerful paradigm for training deep neural networks, particularly in medical imaging where labeled data is scarce. While current approaches typically rely on synthetic augmentations of single images, we propose VET-DINO, a framework that leverages a unique characteristic of medical imaging: the availability of multiple standardized views from the same study. Using a series of clinical veterinary radiographs from the same patient study, we enable models to learn view-invariant anatomical structures and develop an implied 3D understanding from 2D projections. We demonstrate our approach on a dataset of 5 million veterinary radiographs from 668,000 canine studies. Through extensive experimentation, including view synthesis and downstream task performance, we show that learning from real multi-view pairs leads to superior anatomical understanding compared to purely synthetic augmentations. VET-DINO achieves state-of-the-art performance on various veterinary imaging tasks. Our work establishes a new paradigm for self-supervised learning in medical imaging that leverages domain-specific properties rather than merely adapting natural image techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_15248 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VET-DINO: Learning Anatomical Understanding Through Multi-View Distillation in Veterinary Imaging Dourson, Andre Taylor, Kylie Qiao, Xiaoli Fitzke, Michael Computer Vision and Pattern Recognition Machine Learning Self-supervised learning has emerged as a powerful paradigm for training deep neural networks, particularly in medical imaging where labeled data is scarce. While current approaches typically rely on synthetic augmentations of single images, we propose VET-DINO, a framework that leverages a unique characteristic of medical imaging: the availability of multiple standardized views from the same study. Using a series of clinical veterinary radiographs from the same patient study, we enable models to learn view-invariant anatomical structures and develop an implied 3D understanding from 2D projections. We demonstrate our approach on a dataset of 5 million veterinary radiographs from 668,000 canine studies. Through extensive experimentation, including view synthesis and downstream task performance, we show that learning from real multi-view pairs leads to superior anatomical understanding compared to purely synthetic augmentations. VET-DINO achieves state-of-the-art performance on various veterinary imaging tasks. Our work establishes a new paradigm for self-supervised learning in medical imaging that leverages domain-specific properties rather than merely adapting natural image techniques. |
| title | VET-DINO: Learning Anatomical Understanding Through Multi-View Distillation in Veterinary Imaging |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.15248 |