LEAVS: An LLM-based Labeler for Abdominal CT Supervision
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915311112945664 |
|---|---|
| author | Lanfredi, Ricardo Bigolin Zhuang, Yan Finkelstein, Mark Balamuralikrishna, Praveen Thoppey Srinivasan Krembs, Luke Khoury, Brandon Reddy, Arthi Mukherjee, Pritam Rofsky, Neil M. Summers, Ronald M. |
| author_facet | Lanfredi, Ricardo Bigolin Zhuang, Yan Finkelstein, Mark Balamuralikrishna, Praveen Thoppey Srinivasan Krembs, Luke Khoury, Brandon Reddy, Arthi Mukherjee, Pritam Rofsky, Neil M. Summers, Ronald M. |
| contents | Extracting structured labels from radiology reports has been employed to create vision models to simultaneously detect several types of abnormalities. However, existing works focus mainly on the chest region. Few works have been investigated on abdominal radiology reports due to more complex anatomy and a wider range of pathologies in the abdomen. We propose LEAVS (Large language model Extractor for Abdominal Vision Supervision). This labeler can annotate the certainty of presence and the urgency of seven types of abnormalities for nine abdominal organs on CT radiology reports. To ensure broad coverage, we chose abnormalities that encompass most of the finding types from CT reports. Our approach employs a specialized chain-of-thought prompting strategy for a locally-run LLM using sentence extraction and multiple-choice questions in a tree-based decision system. We demonstrate that the LLM can extract several abnormality types across abdominal organs with an average F1 score of 0.89, significantly outperforming competing labelers and humans. Additionally, we show that extraction of urgency labels achieved performance comparable to human annotations. Finally, we demonstrate that the abnormality labels contain valuable information for training a single vision model that classifies several organs as normal or abnormal. We release our code and structured annotations for a public CT dataset containing over 1,000 CT volumes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13330 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LEAVS: An LLM-based Labeler for Abdominal CT Supervision Lanfredi, Ricardo Bigolin Zhuang, Yan Finkelstein, Mark Balamuralikrishna, Praveen Thoppey Srinivasan Krembs, Luke Khoury, Brandon Reddy, Arthi Mukherjee, Pritam Rofsky, Neil M. Summers, Ronald M. Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Extracting structured labels from radiology reports has been employed to create vision models to simultaneously detect several types of abnormalities. However, existing works focus mainly on the chest region. Few works have been investigated on abdominal radiology reports due to more complex anatomy and a wider range of pathologies in the abdomen. We propose LEAVS (Large language model Extractor for Abdominal Vision Supervision). This labeler can annotate the certainty of presence and the urgency of seven types of abnormalities for nine abdominal organs on CT radiology reports. To ensure broad coverage, we chose abnormalities that encompass most of the finding types from CT reports. Our approach employs a specialized chain-of-thought prompting strategy for a locally-run LLM using sentence extraction and multiple-choice questions in a tree-based decision system. We demonstrate that the LLM can extract several abnormality types across abdominal organs with an average F1 score of 0.89, significantly outperforming competing labelers and humans. Additionally, we show that extraction of urgency labels achieved performance comparable to human annotations. Finally, we demonstrate that the abnormality labels contain valuable information for training a single vision model that classifies several organs as normal or abnormal. We release our code and structured annotations for a public CT dataset containing over 1,000 CT volumes. |
| title | LEAVS: An LLM-based Labeler for Abdominal CT Supervision |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.13330 |