Shruthi Bannur
Microsoft
14 Papers
8 Citations
Shruthi Bannur is an academic researcher from Microsoft. The author has contributed to research in topics: Computer science & Semantics (computer science). The author has an hindex of 3, co-authored 3 publications.
Chat about Author
Papers
Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing
Benedikt Böcking,Naoto Usuyama,Shruthi Bannur,Daniel C. Castro,Anton Schwaighofer,Stephanie L. Hyland,T. Baumann,Aditya Nori,Javier Alvarez-Valle,H. Poon,Ozan Oktay +10 more
TL;DR: This paper proposed a self-supervised joint vision-language approach with a focus on better text modelling, which achieved state-of-the-art results in radiology natural language inference through its improved vocabulary and novel language pretraining objective leveraging semantics and discourse characteristics in radiological reports.
Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing
Shruthi Bannur,Stephanie L. Hyland,Qianchu Liu,Fernando Perez-Garcia,Maximilian Ilse,Daniel C. Castro,Benedikt Böcking,Harshita Sharma,Kenza Bouzid,Anja Thieme,Anton Schwaighofer,Matthew P. Lungren,Aditya Nori,Javier Alvarez-Valle,Ozan Oktay +14 more
TL;DR: BioViL-T as discussed by the authors uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model, achieving state-of-the-art performance on progression classification, phrase grounding, and report generation.
58
Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiology
Nur Yildirim,Hannah Richardson,M. Wetscherek,Junaid Bajwa,Joseph Jacob,Mark A. Pinnock,Stephen Harris,Daniel C. Castro,Shruthi Bannur,Stephanie L. Hyland,Pratik Ghosh,Mercy Prasanna Ranjit,Kenza Bouzid,Anton Schwaighofer,Fernando P'erez-Garc'ia,Harshita Sharma,Ozan Oktay,M. Lungren,Javier Alvarez-Valle,Aditya Nori,Anja Thieme +20 more
- 22 Feb 2024
TL;DR: This work engaged in an iterative, multidisciplinary design process to envision clinically relevant VLM interactions, and co-designed four VLM use concepts: Draft Report Generation, Augmented Report Review, Visual Search and Querying, and Patient Imaging History Highlights.
26
RAD-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision
Fernando P'erez-Garc'ia,Harshita Sharma,Sam Bond-Taylor,Kenza Bouzid,Valentina Salvatelli,Maximilian Ilse,Shruthi Bannur,Daniel C. Castro,Anton Schwaighofer,M. Lungren,M. Wetscherek,Noel Codella,Stephanie L. Hyland,Javier Alvarez-Valle,Ozan Oktay +14 more
TL;DR: RAD-DINO is introduced, a biomedical image encoder pre-trained solely on unimodal biomedical imaging data that obtains similar or greater performance than state-of-the-art biomedical language supervised models on a diverse range of benchmarks.
17
Patent
Systems and methods for monitoring driver state
Akshay Uttama Nambi Srirangam Narashiman,Venkata N. Padmanabhan,Ishit Mehta,Shruthi Bannur,Sanchit Gupta +4 more
- 31 May 2018
TL;DR: In this article, a system and techniques for monitoring driver state are described, which is adapted to receive a set of color images of a person, such as image of a driver of a vehicle with varying levels of illumination in the images.
8