Portrait de Anita Kriz n'est pas disponible

Anita Kriz

Représentant du laboratoire
Maitrise de recherche
Sujets de recherche
Causalité
Modèles génératifs
Vision par ordinateur
Site web
Google Scholar
GitHub

Biographie

Je suis étudiante en deuxième année de Maîtrise, travaillant avec la Professeure Tal Arbel au sein du Probabilistic Vision Group. Mes recherches se situent à l'intersection de l'imagerie médicale et de l'inférence causale, en mettant l'accent sur la modélisation des effets longitudinaux des traitements et la génération de contrefactuels. De manière plus générale, mon objectif est de développer des modèles pratiques pour une utilisation dans les environnements de soins de santé.

Avant de rejoindre Mila, j'ai obtenu un baccalauréat en bioingénierie à l'Université McGill, avec une mineure en intelligence artificielle appliquée. En dehors du travail, j'aime lire, cuisiner, et profiter du plein air à travers la course, le tennis et le ski.

Publications

Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical Imaging
Amar Kumar
Anita Kriz
B. Pertzov
Tal Arbel
Vision-language foundation models (VLMs) have shown impressive performance in guiding image generation through text, with emerging applicati… (voir plus)ons in medical imaging. In this work, we are the first to investigate the question: 'Can fine-tuned foundation models help identify critical, and possibly unknown, data properties?' By evaluating our proposed method on a chest x-ray dataset, we show that these models can generate high-resolution, precisely edited images compared to methods that rely on Structural Causal Models (SCMs) according to numerous metrics. For the first time, we demonstrate that fine-tuned VLMs can reveal hidden data relationships that were previously obscured due to available metadata granularity and model capacity limitations. Our experiments demonstrate both the potential of these models to reveal underlying dataset properties while also exposing the limitations of fine-tuned VLMs for accurate image editing and susceptibility to biases and spurious correlations.
2025-03-30
ArXiv (prépublication)
doi.org
arxiv.org
Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical Imaging
Amar Kumar
Anita Kriz
B. Pertzov
Tal Arbel
2025-03-30
ArXiv (prépublication)
arxiv.org
arxiv.org
Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical Imaging
Amar Kumar
Anita Kriz
B. Pertzov
Tal Arbel
2025-03-30
ArXiv (prépublication)
doi.org
arxiv.org
PRISM: High-Resolution&Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusion
Amar Kumar
Anita Kriz
Mohammad Havaei
Tal Arbel
Developing reliable and generalizable deep learning systems for medical imaging faces significant obstacles due to spurious correlations, da… (voir plus)ta imbalances, and limited text annotations in datasets. Addressing these challenges requires architectures robust to the unique complexities posed by medical imaging data. The rapid advancements in vision-language foundation models within the natural image domain prompt the question of how they can be adapted for medical imaging tasks. In this work, we present PRISM, a framework that leverages foundation models to generate high-resolution, language-guided medical image counterfactuals using Stable Diffusion. Our approach demonstrates unprecedented precision in selectively modifying spurious correlations (the medical devices) and disease features, enabling the removal and addition of specific attributes while preserving other image characteristics. Through extensive evaluation, we show how PRISM advances counterfactual generation and enables the development of more robust downstream classifiers for clinically deployable solutions. To facilitate broader adoption and research, we make our code publicly available at https://github.com/Amarkr1/PRISM.
2025-03-27
MIDL.io/2025/Conference (présentation orale)
doi.org
openreview.net
PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusion
Amar Kumar
Anita Kriz
Mohammad Havaei
Tal Arbel
Developing reliable and generalizable deep learning systems for medical imaging faces significant obstacles due to spurious correlations, da… (voir plus)ta imbalances, and limited text annotations in datasets. Addressing these challenges requires architectures robust to the unique complexities posed by medical imaging data. The rapid advancements in vision-language foundation models within the natural image domain prompt the question of how they can be adapted for medical imaging tasks. In this work, we present PRISM, a framework that leverages foundation models to generate high-resolution, language-guided medical image counterfactuals using Stable Diffusion. Our approach demonstrates unprecedented precision in selectively modifying spurious correlations (the medical devices) and disease features, enabling the removal and addition of specific attributes while preserving other image characteristics. Through extensive evaluation, we show how PRISM advances counterfactual generation and enables the development of more robust downstream classifiers for clinically deployable solutions. To facilitate broader adoption and research, we make our code publicly available at https://github.com/Amarkr1/PRISM.
2025-03-01
arXiv (publié)
doi.org
PRISM: High-Resolution&Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusion
Amar Kumar
Anita Kriz
Mohammad Havaei
Tal Arbel
Developing reliable and generalizable deep learning systems for medical imaging faces significant obstacles due to spurious correlations, da… (voir plus)ta imbalances, and limited text annotations in datasets. Addressing these challenges requires architectures robust to the unique complexities posed by medical imaging data. The rapid advancements in vision-language foundation models within the natural image domain prompt the question of how they can be adapted for medical imaging tasks. In this work, we present PRISM, a framework that leverages foundation models to generate high-resolution, language-guided medical image counterfactuals using Stable Diffusion. Our approach demonstrates unprecedented precision in selectively modifying spurious correlations (the medical devices) and disease features, enabling the removal and addition of specific attributes while preserving other image characteristics. Through extensive evaluation, we show how PRISM advances counterfactual generation and enables the development of more robust downstream classifiers for clinically deployable solutions. To facilitate broader adoption and research, we make our code publicly available at https://github.com/Amarkr1/PRISM.
2025-02-28
ArXiv (prépublication)
arxiv.org
arxiv.org
Exploring Compound Loss Functions for Brain Tumor Segmentation
Anita Kriz
Raghav Mehta
Brennan Nichyporuk
Tal Arbel
2024-12-28
Lecture Notes in Computer Science (publié)
doi.org