L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction
Guardado en:
| Publicado en: | arXiv.org (Mar 24, 2024), p. n/a |
|---|---|
| Autor principal: | |
| Otros Autores: | , , , , , , , , , , |
| Publicado: |
Cornell University Library, arXiv.org
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full text outside of ProQuest |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2986603353 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 2986603353 | ||
| 045 | 0 | |b d20240324 | |
| 100 | 1 | |a Zeghlache, Rachid | |
| 245 | 1 | |a L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction | |
| 260 | |b Cornell University Library, arXiv.org |c Mar 24, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of typical SSL is not straightforward in medical imaging. Additionally, those pretext tasks often lack context, which is critical for computer-aided clinical decision support. In this paper, we developed a longitudinal masked auto-encoder (MAE) based on the well-known Transformer-based MAE. In particular, we explored the importance of time-aware position embedding as well as disease progression-aware masking. Taking into account the time between examinations instead of just scheduling them offers the benefit of capturing temporal changes and trends. The masking strategy, for its part, evolves during follow-up to better capture pathological changes, ensuring a more accurate assessment of disease progression. Using OPHDIAT, a large follow-up screening dataset targeting diabetic retinopathy (DR), we evaluated the pre-trained weights on a longitudinal task, which is to predict the severity label of the next visit within 3 years based on the past time series examinations. Our results demonstrated the relevancy of both time-aware position embedding and masking strategies based on disease progression knowledge. Compared to popular baseline models and standard longitudinal Transformers, these simple yet effective extensions significantly enhance the predictive ability of deep classification models. | |
| 653 | |a Masking | ||
| 653 | |a Diabetes | ||
| 653 | |a Self-supervised learning | ||
| 653 | |a Computer vision | ||
| 653 | |a Machine learning | ||
| 653 | |a Computer aided decision processes | ||
| 653 | |a Coders | ||
| 653 | |a Diabetic retinopathy | ||
| 653 | |a Transformers | ||
| 653 | |a Embedding | ||
| 653 | |a Medical imaging | ||
| 700 | 1 | |a Pierre-Henri Conze | |
| 700 | 1 | |a Mostafa El Habib Daho | |
| 700 | 1 | |a Li, Yihao | |
| 700 | 1 | |a Rezaei, Alireza | |
| 700 | 1 | |a Hugo Le Boité | |
| 700 | 1 | |a Tadayoni, Ramin | |
| 700 | 1 | |a Massin, Pascal | |
| 700 | 1 | |a Cochener, Béatrice | |
| 700 | 1 | |a Ikram Brahim | |
| 700 | 1 | |a Quellec, Gwenolé | |
| 700 | 1 | |a Lamard, Mathieu | |
| 773 | 0 | |t arXiv.org |g (Mar 24, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2986603353/abstract/embedded/75I98GEZK8WCJMPQ?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2403.16272 |