Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening Mammography
- 18 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 636-641
Abstract
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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- A Multimodal Biomedical Foundation Model Trained from Fifteen Million Image–Text PairsNEJM AI, 2025
- Microscopic Hematological Image Classification with Captions Using Few-Shot Learning in Data-Scarce Environments2024
- Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography2024
- Named Entity Recognition in Mammography Radiology Reports using a Multilingual Transfer Learning Approach2024
- BioCLIP: A Vision Foundation Model for the Tree of Life2024
- ConvNext: A Contemporary Architecture for Convolutional Neural Networks for Image Classification2023
- Transformers in medical imaging: A surveyMedical Image Analysis, 2023
- An Image Classification Method Based on Self-attention ConvNeXt2022
- A ConvNet for the 2020s2022
- Automatic breast density classification using neural networkJournal of Instrumentation, 2015