Barathi Subramanian

Department of Pathology

Center for AI in Medicine & Imaging

Stanford University

I am a Postdoctoral Scholar in the Department of Pathology and the Center for AI in Medicine & Imaging at Stanford University.

My research focuses on computational pathology, medical AI, and computer vision, with emphasis on whole-slide image analysis, artifact-aware preprocessing, tissue classification, segmentation, survival prediction, and multimodal pathology foundation models.

I develop end-to-end AI pipelines for digital pathology, including whole-slide image preprocessing, tile extraction, quality control, annotation workflows, foundation-model-based feature extraction, and clinically relevant downstream prediction tasks.

Before joining Stanford, I completed my Ph.D. in Computer Vision at Kyungpook National University, South Korea, where I worked on anomaly detection, object detection, gesture recognition, and real-time computer vision systems.

My broader goal is to build reliable, interpretable, and clinically useful AI systems for pathology and healthcare.

news

Mar 01, 2026	Two papers accepted at CVPR 2026 — Gesture2Music (IPA Workshop) and Contrast-Enhanced Gating in GRUs (Women in Computer Vision track).
Oct 15, 2025	Received the Charles B. Carrington Memorial Award for Outstanding Poster Presentation at Stanford University.
Sep 26, 2025	STARC-9, a large-scale colorectal cancer histopathology dataset, accepted at NeurIPS 2025 Datasets and Benchmarks Track.
Jul 01, 2024	Joined Stanford University as a Post-doctoral Scholar at the Center for AI in Medicine & Imaging.
Feb 15, 2024	Received the Best Thesis Award (2024) from Kyungpook National University for my Ph.D. work in Computer Vision.

selected publications

MICCAI’26

TRIAGE-MIL: Multi-Axis Instance Selection and Semantic Hypergraph Modeling for Survival Prediction from Whole-Slide Images

Barathi Subramanian, Rathinaraja Jeyaraj, Jeanne Shen, and others

2026

Provisionally accepted at MICCAI 2026

CVPR’26

Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation

Rathinaraja Jeyaraj, Barathi Subramanian, Kapilya Gangadharan, and Anand Paul

In First International Workshop on Interactive Physical AI (IPA), IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Bib

@inproceedings{jeyaraj2026gesture2music,
  title = {Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation},
  author = {Jeyaraj, Rathinaraja and Subramanian, Barathi and Gangadharan, Kapilya and Paul, Anand},
  booktitle = {First International Workshop on Interactive Physical AI (IPA), IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

CVPR’26

Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning

Barathi Subramanian, Rathinaraja Jeyaraj, and Anand Paul

In Workshop on Women in Computer Vision (WiCV), IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Bib

@inproceedings{subramanian2026contrast,
  title = {Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning},
  author = {Subramanian, Barathi and Jeyaraj, Rathinaraja and Paul, Anand},
  booktitle = {Workshop on Women in Computer Vision (WiCV), IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

CMIG

A Deep Learning-Based Automated Pipeline for Colorectal Cancer Detection in Contrast-Enhanced CT Images

C. Qiu, S. Miller, Barathi Subramanian, A. Ryu, H. Zhang, and 6 more authors

Computerized Medical Imaging and Graphics, 2026

Bib

@article{qiu2026deep,
  title = {A Deep Learning-Based Automated Pipeline for Colorectal Cancer Detection in Contrast-Enhanced CT Images},
  author = {Qiu, C. and Miller, S. and Subramanian, Barathi and Ryu, A. and Zhang, H. and Fisher, G. and Shah, N. and Mongan, J. and Langlotz, C. and Poullos, P. and Shen, Jeanne},
  journal = {Computerized Medical Imaging and Graphics},
  volume = {128},
  year = {2026},
}

NeurIPS’25

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology

Barathi Subramanian, Rathinaraja Jeyaraj, Mitchell Nevin Peterson, Terry Guo, Nigam Shah, and 3 more authors

In Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2025

*Equal contribution

Bib

@inproceedings{subramanian2025starc9,
  title = {STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology},
  author = {Subramanian, Barathi and Jeyaraj, Rathinaraja and Peterson, Mitchell Nevin and Guo, Terry and Shah, Nigam and Langlotz, Curtis and Ng, Andrew Y. and Shen, Jeanne},
  booktitle = {Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track},
  year = {2025},
  note = {*Equal contribution},
}

IEEE Access

Digital Twin Model: A Real-Time Emotion Recognition System for Personalized Healthcare

Barathi Subramanian, Jeonghong Kim, Mohammed Maray, and Anand Paul

IEEE Access, 2022

Bib

@article{subramanian2022digitaltwin,
  title = {Digital Twin Model: A Real-Time Emotion Recognition System for Personalized Healthcare},
  author = {Subramanian, Barathi and Kim, Jeonghong and Maray, Mohammed and Paul, Anand},
  journal = {IEEE Access},
  volume = {10},
  pages = {81155--81165},
  year = {2022},
}

Sci. Rep.

An Integrated MediaPipe-Optimized GRU Model for Indian Sign Language Recognition

Barathi Subramanian, Bekhzod Olimov, Shraddha M. Naik, Sangchul Kim, Kil-Houm Park, and 1 more author

Scientific Reports, 2022

Bib

@article{subramanian2022mediapipe,
  title = {An Integrated MediaPipe-Optimized GRU Model for Indian Sign Language Recognition},
  author = {Subramanian, Barathi and Olimov, Bekhzod and Naik, Shraddha M. and Kim, Sangchul and Park, Kil-Houm and Kim, Jeonghong},
  journal = {Scientific Reports},
  volume = {12},
  pages = {1--16},
  year = {2022},
}