TriAug: Out-of-Distribution Detection for Imbalanced Breast Lesion in Ultrasound
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913245232627712 |
|---|---|
| author | Ye, Yinyu Chen, Shijing Ni, Dong Huang, Ruobing |
| author_facet | Ye, Yinyu Chen, Shijing Ni, Dong Huang, Ruobing |
| contents | Different diseases, such as histological subtypes of breast lesions, have severely varying incidence rates. Even trained with substantial amount of in-distribution (ID) data, models often encounter out-of-distribution (OOD) samples belonging to unseen classes in clinical reality. To address this, we propose a novel framework built upon a long-tailed OOD detection task for breast ultrasound images. It is equipped with a triplet state augmentation (TriAug) which improves ID classification accuracy while maintaining a promising OOD detection performance. Meanwhile, we designed a balanced sphere loss to handle the class imbalanced problem. Experimental results show that the model outperforms state-of-art OOD approaches both in ID classification (F1-score=42.12%) and OOD detection (AUROC=78.06%). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07452 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TriAug: Out-of-Distribution Detection for Imbalanced Breast Lesion in Ultrasound Ye, Yinyu Chen, Shijing Ni, Dong Huang, Ruobing Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Different diseases, such as histological subtypes of breast lesions, have severely varying incidence rates. Even trained with substantial amount of in-distribution (ID) data, models often encounter out-of-distribution (OOD) samples belonging to unseen classes in clinical reality. To address this, we propose a novel framework built upon a long-tailed OOD detection task for breast ultrasound images. It is equipped with a triplet state augmentation (TriAug) which improves ID classification accuracy while maintaining a promising OOD detection performance. Meanwhile, we designed a balanced sphere loss to handle the class imbalanced problem. Experimental results show that the model outperforms state-of-art OOD approaches both in ID classification (F1-score=42.12%) and OOD detection (AUROC=78.06%). |
| title | TriAug: Out-of-Distribution Detection for Imbalanced Breast Lesion in Ultrasound |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.07452 |