Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.13964 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909650347098112 |
|---|---|
| author | Molina-Román, Yusdivia Gómez-Ortiz, David Menasalvas-Ruiz, Ernestina Tamez-Peña, José Gerardo Santos-Díaz, Alejandro |
| author_facet | Molina-Román, Yusdivia Gómez-Ortiz, David Menasalvas-Ruiz, Ernestina Tamez-Peña, José Gerardo Santos-Díaz, Alejandro |
| contents | Mammographic breast density classification is essential for cancer risk assessment but remains challenging due to subjective interpretation and inter-observer variability. This study compares multimodal and CNN-based methods for automated classification using the BI-RADS system, evaluating BioMedCLIP and ConvNeXt across three learning scenarios: zero-shot classification, linear probing with textual descriptions, and fine-tuning with numerical labels. Results show that zero-shot classification achieved modest performance, while the fine-tuned ConvNeXt model outperformed the BioMedCLIP linear probe. Although linear probing demonstrated potential with pretrained embeddings, it was less effective than full fine-tuning. These findings suggest that despite the promise of multimodal learning, CNN-based models with end-to-end fine-tuning provide stronger performance for specialized medical imaging. The study underscores the need for more detailed textual representations and domain-specific adaptations in future radiology applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening Mammography Molina-Román, Yusdivia Gómez-Ortiz, David Menasalvas-Ruiz, Ernestina Tamez-Peña, José Gerardo Santos-Díaz, Alejandro Image and Video Processing Machine Learning Mammographic breast density classification is essential for cancer risk assessment but remains challenging due to subjective interpretation and inter-observer variability. This study compares multimodal and CNN-based methods for automated classification using the BI-RADS system, evaluating BioMedCLIP and ConvNeXt across three learning scenarios: zero-shot classification, linear probing with textual descriptions, and fine-tuning with numerical labels. Results show that zero-shot classification achieved modest performance, while the fine-tuned ConvNeXt model outperformed the BioMedCLIP linear probe. Although linear probing demonstrated potential with pretrained embeddings, it was less effective than full fine-tuning. These findings suggest that despite the promise of multimodal learning, CNN-based models with end-to-end fine-tuning provide stronger performance for specialized medical imaging. The study underscores the need for more detailed textual representations and domain-specific adaptations in future radiology applications. |
| title | Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening Mammography |
| topic | Image and Video Processing Machine Learning |
| url | https://arxiv.org/abs/2506.13964 |