Kanika Bhalla, PhD
Applied AI researcher · Computer vision · Medical imaging
I'm Kanika Bhalla, PhD, an AI researcher at Washington University School of Medicine. I develop robust, clinically grounded models across breast MRI, mammography, and multimodal health data.
DCE-MRI
DBT
Clinical data
01 / Selected work
From pixels to prognosis, I build and rigorously evaluate AI systems designed for real-world medical complexity.
Developing robust AI for pretreatment response prediction using multicenter breast MRI, with multimodal evaluation, molecular subtype-specific analysis, and fairness assessment across patient groups.
Developed an end-to-end multimodal AI pipeline encompassing DCE-MRI tumor segmentation, image preprocessing, modality-specific feature extraction, and learned fusion. Integrated MIRAI-derived DBT representations with Pillar-0 MRI embeddings to predict treatment response before neoadjuvant therapy.
Imaging, clinical, and fusion models evaluated with survival-aware metrics, time-dependent AUC, Kaplan–Meier analysis, and molecular-subtype studies.
Evaluated the robustness of six multimodal report-generation models using embedding-based unusualness scoring, BERTScore, RadGraph-F1, and LLM evaluation.
Led a multidisciplinary datathon team to benchmark foundation-model embeddings, analyze equity across race and density, and study complementarity with the Gail model.
Computer-vision methods for image localization, segmentation, multimodal fusion, and feature learning across multiple imaging applications.
Investigated how histogram-equalization techniques can discard clinically relevant information through mathematical analysis and experiments on brain MRI and colorectal histopathology, with downstream evaluation using deep learning–based image classification.
02 / About
My work sits at the intersection of artificial intelligence, medical imaging, and translational research.
I design end-to-end research pipelines from data curation and harmonization to model development, subgroup analysis, and clinical evaluation. I care equally about model performance, reproducibility, and whether an AI system works fairly across the people it is meant to serve.
Recognition
2026 Emory
Health AI Datathon
2025 Emory
Health AI Datathon
Paper Award
JCVI · Elsevier
Paper Award
iFUZZY 2022
Best Dissertation
Award
03 / Leadership & service
The Open Neuroimaging Journal
IEEE ISBI 2026
DBBS First-Generation Scholars
BMC Medical Imaging · Springer Nature