Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.08097 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929675951931392 |
|---|---|
| author | Sarfati, E. Bône, A. Rohé, M-M. Aubé, C. Ronot, M. Gori, P. Bloch, I. |
| author_facet | Sarfati, E. Bône, A. Rohé, M-M. Aubé, C. Ronot, M. Gori, P. Bloch, I. |
| contents | Hepatocellular carcinoma is the most spread primary liver cancer across the world ($\sim$80\% of the liver tumors). The gold standard for HCC diagnosis is liver biopsy. However, in the clinical routine, expert radiologists provide a visual diagnosis by interpreting hepatic CT-scans according to a standardized protocol, the LI-RADS, which uses five radiological criteria with an associated decision tree. In this paper, we propose an automatic approach to predict histology-proven HCC from CT images in order to reduce radiologists' inter-variability. We first show that standard deep learning methods fail to accurately predict HCC from CT-scans on a challenging database, and propose a two-step approach inspired by the LI-RADS system to improve the performance. We achieve improvements from 6 to 18 points of AUC with respect to deep learning baselines trained with different architectures. We also provide clinical validation of our method, achieving results that outperform non-expert radiologists and are on par with expert ones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08097 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guiding the classification of hepatocellular carcinoma on 3D CT-scans using deep and handcrafted radiological features Sarfati, E. Bône, A. Rohé, M-M. Aubé, C. Ronot, M. Gori, P. Bloch, I. Computer Vision and Pattern Recognition Artificial Intelligence Hepatocellular carcinoma is the most spread primary liver cancer across the world ($\sim$80\% of the liver tumors). The gold standard for HCC diagnosis is liver biopsy. However, in the clinical routine, expert radiologists provide a visual diagnosis by interpreting hepatic CT-scans according to a standardized protocol, the LI-RADS, which uses five radiological criteria with an associated decision tree. In this paper, we propose an automatic approach to predict histology-proven HCC from CT images in order to reduce radiologists' inter-variability. We first show that standard deep learning methods fail to accurately predict HCC from CT-scans on a challenging database, and propose a two-step approach inspired by the LI-RADS system to improve the performance. We achieve improvements from 6 to 18 points of AUC with respect to deep learning baselines trained with different architectures. We also provide clinical validation of our method, achieving results that outperform non-expert radiologists and are on par with expert ones. |
| title | Guiding the classification of hepatocellular carcinoma on 3D CT-scans using deep and handcrafted radiological features |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.08097 |