Shantanu Ghosh

Shantanu Ghosh


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2024
Verified
Book Chapter
Closed access
PDF file
SGShantanu Ghosh
Shantanu Ghosh
CPClare B. Poynton
Clare B. Poynton
SVShyam Visweswaran
Shyam Visweswaran
KBKayhan Batmanghelich
Kayhan Batmanghelich

1 September 2024 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
KYKe Yu
Ke Yu
SGShantanu Ghosh
Shantanu Ghosh
ZLZhexiong Liu
Zhexiong Liu
CDChristopher Deible
Christopher Deible
CPClare B. Poynton
Clare B. Poynton
KBKayhan Batmanghelich
Kayhan Batmanghelich
“Just Accepted” papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review ...

1 January 2025
Verified
Conference Paper
Open access
PDF file
SGShantanu Ghosh
Shantanu Ghosh
RSRayan Syed
Rayan Syed
CWChenyu Wang
Chenyu Wang
VCVaibhav Choudhary
Vaibhav Choudhary
BLBinxu Li
Binxu Li
KBKayhan Batmanghelich
Kayhan Batmanghelich
Shantanu Ghosh, Rayan Syed, Chenyu Wang, Vaibhav Choudhary, Binxu Li, Clare B Poynton, Shyam Visweswaran, Kayhan Batmanghelich. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

1 October 2023
Verified
Book Chapter
Closed access
PDF file
SGShantanu Ghosh
Shantanu Ghosh
KYKe Yu
Ke Yu
KBKayhan Batmanghelich
Kayhan Batmanghelich

22 May 2024 in arXiv
Verified
Preprint
Open access
PDF file
SGShantanu Ghosh
Shantanu Ghosh
CPClare B. Poynton
Clare B. Poynton
SVShyam Visweswaran
Shyam Visweswaran
KBKayhan Batmanghelich
Kayhan Batmanghelich
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) (\eg 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: \url{https://github.com/batmanlab/Mammo-CLIP}.

17 September 2026
Verified
Book Chapter
Closed access
PDF file
WDWeicheng Dai
Weicheng Dai
CWChenyu Wang
Chenyu Wang
SGShantanu Ghosh
Shantanu Ghosh
KBKayhan Batmanghelich
Kayhan Batmanghelich