A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning

Ramazan Terzi

doi:10.29130/dubited.1894627

TR EN

A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning

Abstract

Early and accurate diagnosis of breast cancer is critical for reducing mortality and improving patient outcomes, as it enables timely intervention and more effective treatment planning. In this context, developing reliable and high-performance automated systems for mammography analysis is of great clinical and societal importance. In this study, the classification efficiency of MedSigLIP, one of the most recent technologies in the medical domain, was evaluated on mammography images. Within this scope, both its feature extraction capability and fine-tuning model training competence were assessed, and comprehensive experiments were conducted. For the feature extraction task, features were extracted using MedSigLIP and SigLIP2, the state-of-the-art vision encoder, and their classification performances were reported using seven different machine learning methods. In addition, for the fine-tuning model training task, MedSigLIP was compared with six different convolutional neural network architectures, and the results were reported. According to the obtained results, MedSigLIP achieved the best performance in both tasks, producing 73% F1 score in the MLO view and 83% F1 score in the CC view for feature extraction, and 76% F1 score in the MLO view and 89% F1 score in the CC view for the fine-tuning task.

Keywords

MedSigLIP, Feature extraction, Fine tuning

Supporting Institution

This research received no external funding.

Ethical Statement

This study was approved by the Health Ministry of Türkiye Republic Ankara Bilkent City Hospital Clinical Research Ethics Committee (Approval No: E2-20-53, Date: 27/01/2021). The study used fully anonymized data, and no direct patient involvement was included.

Thanks

The author would like to thank the former Digital Transformation Office of the Presidency of Republic of Türkiye for their support in this study.

References

Al Mansour, A. G. M., Alshomrani, F., Alfahaid, A., & Almutairi, A. T. M. (2025). MammoViT: A custom vision transformer architecture for accurate BIRADS classification in mammogram analysis. Diagnostics, 15(3), Article 285. https://doi.org/10.3390/diagnostics15030285
Beremauro, S., & Girio-Fragkoulakis, C. (2022). Imaging techniques in breast cancer. Surgery (Oxford), 42(2), 94–103. https://doi.org/10.1016/j.mpsur.2021.11.014
Boddu, A. S., & Jan, A. (2025). A systematic review of machine learning algorithms for breast cancer detection. Tissue and Cell,95, Article 102929. https://doi.org/10.1016/j.tice.2025.102929
Cao, Z., Deng, Z., Ma, J., Hu, J., & Ma, L. (2025). MammoVLM: A generative large vision–language model for mammography-related diagnostic assistance. Information Fusion, 118, Article 102998. https://doi.org/10.1016/j.inffus.2025.102998
Chegini, M., & Mahloojifar, A. (2024). Uncertainty-aware deep learning-based CAD system for breast cancer classification using ultrasound and mammography images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 12(1), Article 2297983. https://doi.org/10.1080/21681163.2023.2297983
Chen, Y., Shao, X., Shi, K., Rominger, A., & Caobelli, F. (2025). AI in breast cancer imaging: An update and future trends. Seminars in Nuclear Medicine, 55(3), 358–370. https://doi.org/10.1053/j.semnuclmed.2025.01.008
Díaz, O., Rodríguez-Ruíz, A., & Sechopoulos, I. (2024). Artificial Intelligence for breast cancer detection: Technology, challenges, and prospects. European Journal of Radiology, 175, Article 111457. https://doi.org/10.1016/j.ejrad.2024.111457
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778). IEEE. https://doi.org/10.1109/CVPR.2016.90
Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., Le, Q. V., & Adam, H. (2019). Searching for MobileNetV3. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 1314–1324). IEEE. https://doi.org/10.1109/ICCV.2019.00140
Jiménez-Gaona, Y., Carrión-Figueroa, D., Lakshminarayanan, V., & Rodríguez-Álvarez, M. J. (2024). Gan-based data augmentation to improve breast ultrasound and mammography mass classification. Biomedical Signal Processing and Control, 94, Article 106255. https://doi.org/10.1016/j.bspc.2024.106255

Kim, J., Harper, A., McCormack, V., Sung, H., Houssami, N., Morgan, E., Mutebi, M., Garvey, G., Soeerjomataram, I., & Fidler-Benaoudia, M. M. (2025). Global patterns and trends in breast cancer incidence and mortality across 185 countries. Nature medicine, 31(4), 1154–1162. https://doi.org/10.1038/s41591-025-03502-3
Kulkarni, S., & Rabidas, R. (2025). BI-RADS classification of breast masses based on deep contourlet features. Multimedia Tools and Applications, 84(21), 24209–24228. https://doi.org/10.1007/s11042-024-19913-2
Kumar Saha, D., Hossain, T., Safran, M., Alfarhood, S., Mridha, M. F., & Che, D. (2024). Segmentation for mammography classification utilizing deep convolutional neural network. BMC Medical Imaging, 24(1), Article 334. https://doi.org/10.1186/s12880-024-01510-2
Li, P., Zhong, J., Chen, H., Hong, J., Li, H., Li, X., & Shi, P. (2025). An explainable and comprehensive BI-RADS assisted diagnosis pipeline for mammograms. Physica Medica, 132, Article 104949. https://doi.org/10.1016/j.ejmp.2025.104949
Lou, M., Wang, R., Qi, Y., Zhao, W., Xu, C., Meng, J., Deng, X., & Ma, Y. (2021). MGBN: Convolutional neural networks for automated benign and malignant breast masses classification. Multimedia Tools and Applications, 80(17), 26731–26750. https://doi.org/10.1007/s11042-021-10929-6
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018). ShuffleNet V2: Practical guidelines for efficient CNN architecture design. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 116–131). Springer. https://doi.org/10.1007/978-3-030-01264-9_8
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. Proceedings of the 38th International Conference on Machine Learning, 139, 8748–8763. PMLR. https://proceedings.mlr.press/v139/radford21a.html
Sabani, A., Landsmann, A., Hejduk, P., Schmidt, C., Marcon, M., Borkowski, K., Rossi, C., Ciritsis, A., & Boss, A. (2022). BI-RADS-based classification of mammographic soft tissue opacities using a deep convolutional neural network. Diagnostics, 12(7), Article 1564. https://doi.org/10.3390/diagnostics12071564
Schönenberger, C., Hejduk, P., Ciritsis, A., Marcon, M., Rossi, C., & Boss, A. (2021). Classification of mammographic breast microcalcifications using a deep convolutional neural network: A BI-RADS–based approach. Investigative Radiology, 56(4), 224–231. https://doi.org/10.1097/RLI.0000000000000729
Sellergren, A., Kazemzadeh, S., Jaroensri, T., Kiraly, A., Traverse, M., Kohlberger, T., Xu, S., Jamil, F., Hughes, C., Lau, C., Chen, J., Mahvar, F., Yatziv, L., Chen, T., Sterling, B., Baby, S. A., Baby, S. M., Lai, J., Schmidgall, S., ... Yang, L. (2025). MedGemma technical report. arXiv. https://doi.org/10.48550/arXiv.2507.05201
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv. https://doi.org/10.48550/arXiv.1409.1556
Soltani, H., Bendib, I., Haouam, M. Y., & Amroune, M. (2024). Advancements in breast cancer diagnosis: a comprehensive review of mammography datasets, preprocessing and classification techniques. Acta Informatica Pragensia, 13(2), 308–326. https://doi.org/10.18267/j.aip.244
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2818–2826). IEEE. https://doi.org/10.1109/CVPR.2016.308
Tan, M., & Le, Q. (2021). EfficientNetV2: Smaller models and faster training. In Proceedings of the 38th International Conference on Machine Learning (pp. 10096–10106). PMLR. https://proceedings.mlr.press/v139/tan21a.html
Terzi, R. (2025). Evaluating vision encoders for feature extraction in mammography image classification. In Proceedings of the 2025 9th International Artificial Intelligence and Data Processing Symposium (IDAP) (pp. 1–8). IEEE. https://doi.org/10.1109/IDAP68205.2025.11222215
Terzi, R., Kılıç, A. E., Karaahmetoğlu, G., & Özdemir, O. B. (2025). The digital eye for mammography: deep transfer learning and model ensemble based open-source toolkit for mass detection and classification. Signal, Image and Video Processing, 19(2), Article 170. https://doi.org/10.1007/s11760-024-03737-6
Tsai, K. J., Chou, M. C., Li, H. M., Liu, S. T., Hsu, J. H., Yeh, W. C., Hung, C. M., Yeh, C. Y., & Hwang, S. H. (2022). A high-performance deep neural network model for BI-RADS classification of screening mammography. Sensors, 22(3), Article 1160. https://doi.org/10.3390/s22031160
Tschannen, M., Gritsenko, A., Wang, X., Naeem, M. F., Alabdulmohsin, I., Parthasarathy, N., Evans, T., Beyer, L., Xia, Y., Mustafa, B., Hénaff, O., Harmsen, J., Steiner, A., & Zhai, X. (2025). SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv. https://doi.org/10.48550/arXiv.2502.14786
Wang, B., Hu, X., Zhang, J., Xu, C., & Gao, Z. (2023). Intelligent internet of things in mammography screening using multicenter transformation between unified capsules. IEEE Internet of Things Journal, 10(2), 1536–1545. https://doi.org/10.1109/JIOT.2022.3209895
Xue, J., Yu, J., Mao, Q., & Gu, X. (2025). Advancements and future directions of artificial intelligence in tumor imaging: A comprehensive review of techniques and applications. EngMedicine, 2(3), Article 100086. https://doi.org/10.1016/j.engmed.2025.100086
Yang, Y., Zhong, Y., Li, J., Feng, J., Gong, C., Yu, Y., Hu, Y., Gu, R., Wang, H., Liu, F., Mei, J., Jiang, X., Wang, J., Yao, Q., Wu, W., Liu, Q., & Yao, H. (2024). Deep learning combining mammography and ultrasound images to predict the malignancy of BI-RADS US 4A lesions in women with dense breasts: A diagnostic study. International Journal of Surgery, 110(5), 2604–2613. https://doi.org/10.1097/JS9.0000000000001186
Zhai, X., Mustafa, B., Kolesnikov, A., & Beyer, L. (2023). Sigmoid loss for language image pre-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 11975–11986). IEEE. https://doi.org/10.1109/ICCV51070.2023.01100

Details

Primary Language

English

Subjects

Deep Learning

Journal Section

Research Article

Authors

Ramazan Terzi ^*
0000-0003-2345-8666
Türkiye

Publication Date

July 24, 2026

Submission Date

February 21, 2026

Acceptance Date

April 4, 2026

Published in Issue

Year 2026 Volume: 14 Number: 3

DOI

https://doi.org/10.29130/dubited.1894627

IZ

https://izlik.org/JA66EH45XH

APA

Terzi, R. (2026). A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning. Duzce University Journal of Science and Technology, 14(3), 821-831. https://doi.org/10.29130/dubited.1894627

AMA

1.Terzi R. A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning. DUBİTED. 2026;14(3):821-831. doi:10.29130/dubited.1894627

Chicago

Terzi, Ramazan. 2026. “A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning”. Duzce University Journal of Science and Technology 14 (3): 821-31. https://doi.org/10.29130/dubited.1894627.

EndNote

Terzi R (July 1, 2026) A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning. Duzce University Journal of Science and Technology 14 3 821–831.

IEEE

[1]R. Terzi, “A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning”, DUBİTED, vol. 14, no. 3, pp. 821–831, July 2026, doi: 10.29130/dubited.1894627.

ISNAD

Terzi, Ramazan. “A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning”. Duzce University Journal of Science and Technology 14/3 (July 1, 2026): 821-831. https://doi.org/10.29130/dubited.1894627.

JAMA

1.Terzi R. A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning. DUBİTED. 2026;14:821–831.

MLA

Terzi, Ramazan. “A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning”. Duzce University Journal of Science and Technology, vol. 14, no. 3, July 2026, pp. 821-3, doi:10.29130/dubited.1894627.

Vancouver

1.Ramazan Terzi. A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning. DUBİTED. 2026 Jul. 1;14(3):821-3. doi:10.29130/dubited.1894627

A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning

Özellik Çıkarma ve İnce Ayar Yöntemiyle Mamografi Sınıflandırması için MedSigLIP'in Teknik Değerlendirmesi

Abstract

Keywords

A Technical Evaluation of MedSigLIP for Mammography Classification via Feature Extraction and Fine-Tuning

Abstract

Keywords

Supporting Institution

Ethical Statement

Thanks

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite