Imon Banerjee

Associate Professor @Mayoclinic. Was Assistant Professor in @Emory and was Instructor @StanfordAIMI. Core expertise are #machinelearning #deeplearning and #NLP

[Imon Banerjee @ImonBanerjee6]

📘 New @NCICancerStats chapter: We developed a domain-specific #LLM for prostate cancer using 1.8M clinical notes from 15K+ patients. It outperforms generic LLMs—showing the power of tailored training + domain vocab. #AI #ProstateCancer https://t.co/rL8o3sAC2J

[Imon Banerjee @ImonBanerjee6]

#AIinHealthcare #MedicalImaging #KidneySegmentation #DomainAdaptation

[Imon Banerjee @ImonBanerjee6]

New Research Alert: Robust Kidney Segmentation Across Contrast Phases https://t.co/ezQgt6h6Zf

[Imon Banerjee @ImonBanerjee6]

📂 Open-source code available: https://t.co/bKqhyQzDR5.
Let’s build AI tools that generalize better—because patients deserve consistent care, regardless of imaging conditions.

[Imon Banerjee @ImonBanerjee6]

🔍 Why it matters:
✅ Handles contrast-to-non-contrast and arterial-to-venous shifts
✅ Works on both normal and abnormal kidneys
✅ Open-source and data-efficient
✅ Clinically relevant for automated, contrast-invariant kidney health assessment

[Imon Banerjee @ImonBanerjee6]

Trained on multi-phase public datasets and tested on diverse external datasets (including KiTS21, STU, and Mayo Clinic), our model achieved a DICE score of 0.8892, outperforming state-of-the-art baselines like #TotalSegmentator.

[Imon Banerjee @ImonBanerjee6]

Accurate kidney segmentation from #CT is critical—but current models struggle when faced with domain shifts like contrast phase variation or kidney abnormalities.
Our work introduces a #domainadaptation approach using a latent space discriminator to overcome these challenges.

[Imon Banerjee @ImonBanerjee6]

@woojinrad Completely agree

[datascience@uw @datascience_uw]

.@ImonBanerjee6's research addresses fairness in AI, multimodal deep learning, and AI translation for digital healthcare. She'll discuss her work at the July 14 ML4MI seminar, 10am CT on Zoom. @uwsmph https://t.co/HBSfS3R3E0

[Imon Banerjee @ImonBanerjee6]

Implication: Opportunistic, scalable, and cost-effective screening—especially useful in resource-limited settings.

[Imon Banerjee @ImonBanerjee6]

MACE remains the leading global cause of death. Our MICCAI 2025 work, MOSCARD, fuses CXR+ECG via multimodal causal reasoning for bias-aware risk prediction. Outperforms SOTA on ED & MIMIC (AUC: 0.75–0.83). #MICCAI2025 #AIHealth
https://t.co/DDwwJ4hAxV

[Imon Banerjee @ImonBanerjee6]

Results: Strong generalization and superior AUC vs single modality and foundation models.

[Imon Banerjee @ImonBanerjee6]

Key innovations:

Cross-modal co-attention for CXR-ECG alignment

Causal inference to handle confounders

Dual back-propagation for de-biasing

[Imon Banerjee @ImonBanerjee6]

We developed MOSCARD: a novel multimodal framework aligning CXR with ECG via causal reasoning

[Imon Banerjee @ImonBanerjee6]

Existing risk models often rely on single modalities or clinical scores—limited by bias and incomplete data.

[Imon Banerjee @ImonBanerjee6]

Codebase https://t.co/joAfROnpcU

[Imon Banerjee @ImonBanerjee6]

🔓 The full pipeline and model are publicly available under an academic license—ready to support clinical and research applications. (https://t.co/fCIWn2R33T).

[Imon Banerjee @ImonBanerjee6]

📢 New paper: We propose a framework that leverages weak supervision to train LMs for structured information extraction—minimizing annotation cost while maintaining clinical relevance.
#NLP #RadiologyAI #WeakSupervision #ClinicalNLP #LLMs https://t.co/F6gpRdN7cQ

[Imon Banerjee @ImonBanerjee6]

🧠 Evaluation used both:

Manual expert annotations
LLM-based metrics: G-eval and Prometheus

[Imon Banerjee @ImonBanerjee6]

The fine-tuned model was evaluated on:

Internal test set (Mayo Clinic, n=80)
External test set (MIMIC-III, n=123)
Large-scale validation (MIMIC-IV, n=5000)

[Imon Banerjee @ImonBanerjee6]

🧪 Our two-phase approach fine-tunes LLMs on 15,000 unlabeled Mayo Clinic reports, using heuristics and domain knowledge to guide learning.