Temporal Inversion for Learning Interval Change in Chest X-Rays
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914454896115712 |
|---|---|
| author | Ko, Hanbin Jeon, Kyungmin Choi, Doowoong Park, Chang Min |
| author_facet | Ko, Hanbin Jeon, Kyungmin Choi, Doowoong Park, Chang Min |
| contents | Recent advances in vision--language pretraining have enabled strong medical foundation models, yet most analyze radiographs in isolation, overlooking the key clinical task of comparing prior and current images to assess interval change. For chest radiographs (CXRs), capturing interval change is essential, as radiologists must evaluate not only the static appearance of findings but also how they evolve over time. We introduce TILA (Temporal Inversion-aware Learning and Alignment), a simple yet effective framework that uses temporal inversion, reversing image pairs, as a supervisory signal to enhance the sensitivity of existing temporal vision-language models to directional change. TILA integrates inversion-aware objectives across pretraining, fine-tuning, and inference, complementing conventional appearance modeling with explicit learning of temporal order. We also propose a unified evaluation protocol to assess order sensitivity and consistency under temporal inversion, and introduce MS-CXR-Tretrieval, a retrieval evaluation set constructed through a general protocol that can be applied to any temporal CXR dataset. Experiments on public datasets and real-world hospital cohorts demonstrate that TILA consistently improves progression classification and temporal embedding alignment when applied to multiple existing architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04563 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Temporal Inversion for Learning Interval Change in Chest X-Rays Ko, Hanbin Jeon, Kyungmin Choi, Doowoong Park, Chang Min Computer Vision and Pattern Recognition Artificial Intelligence Recent advances in vision--language pretraining have enabled strong medical foundation models, yet most analyze radiographs in isolation, overlooking the key clinical task of comparing prior and current images to assess interval change. For chest radiographs (CXRs), capturing interval change is essential, as radiologists must evaluate not only the static appearance of findings but also how they evolve over time. We introduce TILA (Temporal Inversion-aware Learning and Alignment), a simple yet effective framework that uses temporal inversion, reversing image pairs, as a supervisory signal to enhance the sensitivity of existing temporal vision-language models to directional change. TILA integrates inversion-aware objectives across pretraining, fine-tuning, and inference, complementing conventional appearance modeling with explicit learning of temporal order. We also propose a unified evaluation protocol to assess order sensitivity and consistency under temporal inversion, and introduce MS-CXR-Tretrieval, a retrieval evaluation set constructed through a general protocol that can be applied to any temporal CXR dataset. Experiments on public datasets and real-world hospital cohorts demonstrate that TILA consistently improves progression classification and temporal embedding alignment when applied to multiple existing architectures. |
| title | Temporal Inversion for Learning Interval Change in Chest X-Rays |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.04563 |