Search Results for author: Akshay Chaudhari

Found 31 papers, 15 papers with code

Explaining 3D Computed Tomography Classifiers with Counterfactuals

1 code implementation11 Feb 2025 Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari

Counterfactual explanations in medical imaging are critical for understanding the predictions made by deep learning models.

Computed Tomography (CT) counterfactual

Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation

no code implementations20 Jan 2025 Ivan Lopez, Fateme Nateghi Haredasht, Kaitlin Caoili, Jonathan H Chen, Akshay Chaudhari

We propose an embedding-driven approach that uses diversity sampling from a small set of real clinical notes to guide large language models in few-shot prompting, generating synthetic text that better reflects clinical syntax.

Diversity Synthetic Data Generation

Best Practices for Large Language Models in Radiology

no code implementations2 Dec 2024 Christian Bluethgen, Dave Van Veen, Cyril Zakka, Katherine Link, Aaron Fanous, Roxana Daneshjou, Thomas Frauenfelder, Curtis Langlotz, Sergios Gatidis, Akshay Chaudhari

At the heart of radiological practice is the challenge of integrating complex imaging data with clinical information to produce actionable insights.

Navigate

Foundation Models in Radiology: What, How, When, Why and Why Not

no code implementations27 Nov 2024 Magdalini Paschali, Zhihong Chen, Louis Blankemeier, Maya Varma, Alaa Youssef, Christian Bluethgen, Curtis Langlotz, Sergios Gatidis, Akshay Chaudhari

Given the potentially transformative impact that foundation models can have on the field of radiology, this review aims to establish a standardized terminology concerning foundation models, with a specific focus on the requirements of training data, model training paradigms, model capabilities, and evaluation strategies.

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

1 code implementation6 Nov 2024 Maya Varma, Jean-Benoit Delbrouck, Zhihong Chen, Akshay Chaudhari, Curtis Langlotz

Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time.

Image Classification Zero-Shot Learning

SOE: SO(3)-Equivariant 3D MRI Encoding

1 code implementation15 Oct 2024 Shizhe He, Magdalini Paschali, Jiahong Ouyang, Adnan Masood, Akshay Chaudhari, Ehsan Adeli

This approach requires moving beyond traditional representation learning methods, as we need a representation vector space that allows for the application of the same SO(3) operation in that space.

Anatomy Representation Learning

Spectral Graph Sample Weighting for Interpretable Sub-cohort Analysis in Predictive Models for Neuroimaging

no code implementations1 Oct 2024 Magdalini Paschali, Yu Hang Jiang, Spencer Siegel, Camila Gonzalez, Kilian M. Pohl, Akshay Chaudhari, Qingyu Zhao

To this end, we propose to model the subject weights as a linear combination of the eigenbases of a spectral population graph that captures the similarity of factors across subjects.

LieRE: Generalizing Rotary Position Encodings

1 code implementation14 Jun 2024 Sophie Ostmeier, Brian Axelrod, Michael E. Moseley, Akshay Chaudhari, Curtis Langlotz

While Rotary Position Embeddings (RoPE) for large language models have become widely adopted, their application for other modalities has been slower.

Image Classification Position

OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics

no code implementations14 Jun 2024 Yoni Gozlan, Antoine Falisse, Scott Uhlrich, Anthony Gatti, Michael Black, Akshay Chaudhari

To mitigate this challenge, we introduce SynthPose, a new approach that enables finetuning of pre-trained 2D human pose models to predict an arbitrarily denser set of keypoints for accurate kinematic analysis through the use of synthetic data.

Pose Estimation

MediSyn: Text-Guided Diffusion Models for Broad Medical 2D and 3D Image Synthesis

no code implementations16 May 2024 Joseph Cho, Cyril Zakka, Dhamanpreet Kaur, Rohan Shad, Ross Wightman, Akshay Chaudhari, William Hiesinger

Diffusion models have recently gained significant traction due to their ability to generate high-fidelity and diverse images and videos conditioned on text prompts.

Image Generation

Deep Learning for Accelerated and Robust MRI Reconstruction: a Review

no code implementations24 Apr 2024 Reinhard Heckel, Mathews Jacob, Akshay Chaudhari, Or Perlman, Efrat Shimron

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology.

Deep Learning MRI Reconstruction

Identifying Spurious Correlations using Counterfactual Alignment

1 code implementation1 Dec 2023 Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari

We propose the counterfactual (CF) alignment method to detect and quantify spurious correlations of black box classifiers.

Attribute counterfactual

ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data

1 code implementation ICCV 2023 Maya Varma, Jean-Benoit Delbrouck, Sarah Hooper, Akshay Chaudhari, Curtis Langlotz

The first key contribution of this work is to demonstrate through systematic evaluations that as the pairwise complexity of the training dataset increases, standard VLMs struggle to learn region-attribute relationships, exhibiting performance degradations of up to 37% on retrieval tasks.

Attribute object-detection +3

Exploring Image Augmentations for Siamese Representation Learning with Chest X-Rays

1 code implementation30 Jan 2023 Rogier van der Sluijs, Nandita Bhaskhar, Daniel Rubin, Curtis Langlotz, Akshay Chaudhari

Thus, it is unknown whether common augmentation strategies employed in Siamese representation learning generalize to medical images and to what extent.

Anomaly Detection Representation Learning +1

RoentGen: Vision-Language Foundation Model for Chest X-ray Generation

1 code implementation23 Nov 2022 Pierre Chambon, Christian Bluethgen, Jean-Benoit Delbrouck, Rogier van der Sluijs, Małgorzata Połacin, Juan Manuel Zambrano Chaves, Tanishq Mathew Abraham, Shivanshu Purohit, Curtis P. Langlotz, Akshay Chaudhari

We present evidence that the resulting model (RoentGen) is able to create visually convincing, diverse synthetic CXR images, and that the output can be controlled to a new extent by using free-form text prompts including radiology-specific language.

Data Augmentation

Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains

no code implementations9 Oct 2022 Pierre Chambon, Christian Bluethgen, Curtis P. Langlotz, Akshay Chaudhari

Multi-modal foundation models are typically trained on millions of pairs of natural images and text captions, frequently obtained through web-crawling approaches.

SSFD: Self-Supervised Feature Distance as an MR Image Reconstruction Quality Metric

no code implementations NeurIPS Workshop Deep_Invers 2021 Philip M Adamson, Beliz Gunel, Jeffrey Dominic, Arjun D Desai, Daniel Spielman, Shreyas Vasanawala, John M. Pauly, Akshay Chaudhari

Self-supervised learning (SSL) has become a popular pre-training tool due to its ability to capture generalizable and domain-specific feature representations of the underlying data for downstream tasks.

MRI Reconstruction Self-Supervised Learning +1

Designing Counterfactual Generators using Deep Model Inversion

no code implementations NeurIPS 2021 Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Deepta Rajan, Jason Liang, Akshay Chaudhari, Andreas Spanias

Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models.

counterfactual Image Generation +1

Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rays

3 code implementations18 Feb 2021 Joseph Paul Cohen, Rupert Brooks, Sovann En, Evan Zucker, Anuj Pareek, Matthew P. Lungren, Akshay Chaudhari

We also found that the Latent Shift explanation allows a user to have more confidence in true positive predictions compared to traditional approaches (0. 15$\pm$0. 95 in a 5 point scale with p=0. 01) with only a small increase in false positive predictions (0. 04$\pm$1. 06 with p=0. 57).

counterfactual Image Attribution

MRSaiFE: Tissue Heating Prediction for MRI: a Feasibility Study

no code implementations1 Feb 2021 Simone Angela Winkler, Isabelle Saniour, Akshay Chaudhari, Fraser Robb, J Thomas Vaughan

We trained the software with a small database of image as a feasibility study and achieved successful proof of concept for both field strengths.

Prediction SSIM

Deep Learning Super-Resolution Enables Rapid Simultaneous Morphological and Quantitative Magnetic Resonance Imaging

no code implementations7 Aug 2018 Akshay Chaudhari, Zhongnan Fang, Jin Hyung Lee, Garry Gold, Brian Hargreaves

Obtaining magnetic resonance images (MRI) with high resolution and generating quantitative image-based biomarkers for assessing tissue biochemistry is crucial in clinical and research applications.

Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.