# Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening Mammography

arXiv: https://arxiv.org/abs/2506.13964 · HTML: https://mlsanity.com/paper/2506.13964/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 6 of 6)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography](https://mlsanity.com/paper/2405.12255/) (2024)
- [Navigating the landscape of multimodal AI in medicine: a scoping review on technical challenges and clinical applications](https://mlsanity.com/paper/2411.03782/) (2024)
- [KPL: Training-Free Medical Knowledge Mining of Vision-Language Models](https://mlsanity.com/paper/2501.11231/) (2025)

## Built on by (most cited first, 1 of 1)

- [Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations](https://mlsanity.com/paper/2511.17828/) (2025)

## Abstract (arXiv)

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.