Views
No views yet
1@article{ghosh2025mammo,
2 title={Mammo-FM: Breast-specific foundational model for Integrated Mammographic Diagnosis, Prognosis, and Reporting},
3 author={Ghosh, Shantanu and Joshi, Vedant Parthesh and Syed, Rayan and Kassem, Aya and Varshney, Abhishek and Basak, Payel and Dai, Weicheng and Gichoya, Judy Wawira and Trivedi, Hari M and Banerjee, Imon and others},
4 journal={arXiv preprint arXiv:2512.00198},
5 year={2025}
6}1@InProceedings{10.1007/978-3-031-72390-2_59,
2author="Ghosh, Shantanu
3and Poynton, Clare B.
4and Visweswaran, Shyam
5and Batmanghelich, Kayhan",
6editor="Linguraru, Marius George
7and Dou, Qi
8and Feragen, Aasa
9and Giannarou, Stamatia
10and Glocker, Ben
11and Lekadir, Karim
12and Schnabel, Julia A.",
13title="Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography",
14booktitle="Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024",
15year="2024",
16publisher="Springer Nature Switzerland",
17address="Cham",
18pages="632--642",
19abstract="The lack of large and diverse training data on Computer-Aided Diagnosis (CAD) in breast cancer detection has been one of the concerns that impedes the adoption of the system. Recently, pre-training with large-scale image text datasets via Vision-Language models (VLM) (e.g., CLIP) partially addresses the issue of robustness and data efficiency in computer vision (CV). This paper proposes Mammo-CLIP, the first VLM pre-trained on a substantial amount of screening mammogram-report pairs, addressing the challenges of dataset diversity and size. Our experiments on two public datasets demonstrate strong performance in classifying and localizing various mammographic attributes crucial for breast cancer detection, showcasing data efficiency and robustness similar to CLIP in CV. We also propose Mammo-FActOR, a novel feature attribution method, to provide spatial interpretation of representation with sentence-level granularity within mammography reports. Code is available publicly: https://github.com/batmanlab/Mammo-CLIP.",
20isbn="978-3-031-72390-2"
21}"This work uses Mammo-FM developed by the authors of Mammo-FM, Boston University."