Tal Arbel

Biography

Tal Arbel is a professor in the Department of Electrical and Computer Engineering at McGill University, where she is the director of the Probabilistic Vision Group and Medical Imaging Lab in the Centre for Intelligent Machines.

She is also a Canada CIFAR AI Chair, an associate academic member of Mila – Quebec Artificial Intelligence Institute and an associate member of the Goodman Cancer Research Centre.

Arbel’s research focuses on the development of probabilistic deep learning methods in computer vision and medical image analysis for a wide range of real-world applications, with a focus on neurological diseases.

She is a recipient of the 2019 McGill Engineering Christophe Pierre Research Award and regularly serves on organizing committees for major international conferences in computer vision and medical image analysis, including for the Medical Image Computing and Computer-Assisted Intervention Society/MICCAI, the Medical Imaging with Deep Learning/MIDL, the International Conference on Computer Vision/ICCV or the Computer Vision and Pattern Recognition Conference/CVPR). She co-founded the arXiv overlay journal, Machine Learning for Biomedical Imaging (MELBA) and is currently its editor-in-chief.

Current Students

Berardino Barile

Postdoctorate - McGill University

Joshua Durso-finley

PhD - McGill University

Nima Fathi

Master's Research - McGill University

Gian Favero

Master's Research - McGill University

elizabeth.janes@mila.quebec

Ethan Honey

PhD - McGill University

ethan.honey@mila.quebec

Elizabeth Laura Janes

Master's Research - McGill University

Emily Kaczmarek

PhD - McGill University

emily.kaczmarek@mail.mcgill.ca

Anita Kriz

Master's Research - McGill University

Amar Kumar

PhD - McGill University

Mohamed Mohamed

Master's Research - McGill University

Parham Saremi

Master's Research - McGill University

Xing Shen

Master's Research - McGill University

Master's Research - McGill University

Mona Wang Wang

Undergraduate - McGill University

monaw7777@gmail.com

Ritchie Yu

Undergraduate - McGill University

Publications

Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation

Junde Wu

Rao Fu

Huihui Fang

Yuanpei Liu

Zhao-Yang Wang

Yanwu Xu

Yueming Jin

The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in var… (see more)ious segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have shown that SAM underperforms in medical image segmentation, since the lack of the medical specific knowledge. This raises the question of how to enhance SAM's segmentation capability for medical images. In this paper, instead of fine-tuning the SAM model, we propose the Medical SAM Adapter (Med-SA), which incorporates domain-specific medical knowledge into the segmentation model using a light yet effective adaptation technique. In Med-SA, we propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation. We conduct comprehensive evaluation experiments on 17 medical image segmentation tasks across various image modalities. Med-SA outperforms several state-of-the-art (SOTA) medical image segmentation methods, while updating only 2\% of the parameters. Our code is released at https://github.com/KidsWithTokens/Medical-SAM-Adapter.

2023-04-25

ArXiv (preprint)

Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis

Raghav Mehta

Changjian Shui

2023-04-04

MIDL.io/2023/Conference (poster)

Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis

Raghav Mehta

Changjian Shui

Although deep learning (DL) models have shown great success in many medical image analysis tasks, deployment of the resulting models into r… (see more)eal clinical contexts requires: (1) that they exhibit robustness and fairness across different sub-populations, and (2) that the confidence in DL model predictions be accurately expressed in the form of uncertainties. Unfortunately, recent studies have indeed shown significant biases in DL models across demographic subgroups (e.g., race, sex, age) in the context of medical image analysis, indicating a lack of fairness in the models. Although several methods have been proposed in the ML literature to mitigate a lack of fairness in DL models, they focus entirely on the absolute performance between groups without considering their effect on uncertainty estimation. In this work, we present the first exploration of the effect of popular fairness models on overcoming biases across subgroups in medical image analysis in terms of bottom-line performance, and their effects on uncertainty quantification. We perform extensive experiments on three different clinically relevant tasks: (i) skin lesion classification, (ii) brain tumour segmentation, and (iii) Alzheimer's disease clinical score regression. Our results indicate that popular ML methods, such as data-balancing and distributionally robust optimization, succeed in mitigating fairness issues in terms of the model performances for some of the tasks. However, this can come at the cost of poor uncertainty estimates associated with the model predictions. This tradeoff must be mitigated if fairness models are to be adopted in medical image analysis.

2023-04-04

MIDL.io/2023/Conference (poster)

Personalized Prediction of Future Lesion Activity and Treatment Effect in Multiple Sclerosis from Baseline MRI

Joshua D. Durso-Finley

Jean-Pierre R. Falet

Brennan Nichyporuk

Douglas Arnold

Precision medicine for chronic diseases such as multiple sclerosis (MS) involves choosing a treatment which best balances efficacy and side … (see more)effects/preferences for individual patients. Making this choice as early as possible is important, as delays in finding an effective therapy can lead to irreversible disability accrual. To this end, we present the first deep neural network model for individualized treatment decisions from baseline magnetic resonance imaging (MRI) (with clinical information if available) for MS patients which (a) predicts future new and enlarging T2 weighted (NE-T2) lesion counts on follow-up MRI on multiple treatments and (b) estimates the conditional average treatment effect (CATE), as defined by the predicted future suppression of NE-T2 lesions, between different treatment options relative to placebo. Our model is validated on a proprietary federated dataset of 1817 multi-sequence MRIs acquired from MS patients during four multi-centre randomized clinical trials. Our framework achieves high average precision in the binarized regression of future NE-T2 lesions on five different treatments, identifies heterogeneous treatment effects, and provides a personalized treatment recommendation that accounts for treatment-associated risk (side effects, patient preference, administration difficulties,...).

2022-12-04

Proceedings of The 5th International Conference on Medical Imaging with Deep Learning (published)

Segmentation-Consistent Probabilistic Lesion Counting

Julien Schroeter

Chelsea Myers-Colet

Douglas Arnold

Lesion counts are important indicators of disease severity, patient prognosis, and treatment efficacy, yet counting as a task in medical ima… (see more)ging is often overlooked in favor of segmentation. This work introduces a novel continuously differentiable function that maps lesion segmentation predictions to lesion count probability distributions in a consistent manner. The proposed end-to-end approach—which consists of voxel clustering, lesion-level voxel probability aggregation, and Poisson-binomial counting—is non-parametric and thus offers a robust and consistent way to augment lesion segmentation models with post hoc counting capabilities. Experiments on Gadolinium-enhancing lesion counting demonstrate that our method outputs accurate and well-calibrated count distributions that capture meaningful uncertainty information. They also reveal that our model is suitable for multi-task learning of lesion segmentation, is efficient in low data regimes, and is robust to adversarial attacks.

2022-12-04

Proceedings of The 5th International Conference on Medical Imaging with Deep Learning (published)

Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors

Anjun Hu

Jean-Pierre R. Falet

Brennan Nichyporuk

Changjian Shui

Douglas Arnold

Sotirios A. Tsaftaris

We propose a hierarchically structured variational inference model for accurately disentangling observable evidence of disease (e.g. brain l… (see more)esions or atrophy) from subject-specific anatomy in brain MRIs. With flexible, partially autoregressive priors, our model (1) addresses the subtle and fine-grained dependencies that typically exist between anatomical and pathological generating factors of an MRI to ensure the clinical validity of generated samples; (2) preserves and disentangles finer pathological details pertaining to a patient's disease state. Additionally, we experiment with an alternative training configuration where we provide supervision to a subset of latent units. It is shown that (1) a partially supervised latent space achieves a higher degree of disentanglement between evidence of disease and subject-specific anatomy; (2) when the prior is formulated with an autoregressive structure, knowledge from the supervision can propagate to the unsupervised latent units, resulting in more informative latent representations capable of modelling anatomy-pathology interdependencies.

2022-11-15

ArXiv (preprint)

Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentation

Brennan Nichyporuk

Jillian L. Cardinell

Justin Szeto

Raghav Mehta

Jean-Pierre R. Falet

Douglas Arnold

Sotirios A. Tsaftaris

Generalization is an important attribute of machine learning models, particularly for those that are to be deployed in a medical context, wh… (see more)ere unreliable predictions can have real world consequences. While the failure of models to generalize across datasets is typically attributed to a mismatch in the data distributions, performance gaps are often a consequence of biases in the "ground-truth" label annotations. This is particularly important in the context of medical image segmentation of pathological structures (e.g. lesions), where the annotation process is much more subjective, and affected by a number underlying factors, including the annotation protocol, rater education/experience, and clinical aims, among others. In this paper, we show that modeling annotation biases, rather than ignoring them, poses a promising way of accounting for differences in annotation style across datasets. To this end, we propose a generalized conditioning framework to (1) learn and account for different annotation styles across multiple datasets using a single model, (2) identify similar annotation styles across different datasets in order to permit their effective aggregation, and (3) fine-tune a fully trained model to a new annotation style with just a few samples. Next, we present an image-conditioning approach to model annotation styles that correlate with specific image features, potentially enabling detection biases to be more easily identified.

2022-10-31

ArXiv (preprint)

Estimating individual treatment effect on disability progression in multiple sclerosis using deep learning

Jean-Pierre R. Falet

Joshua D. Durso-Finley

Brennan Nichyporuk

Julien Schroeter

Francesca Bovis

Maria-Pia Sormani

Doina Precup

Douglas Arnold

2022-09-26

Nature Communications (published)

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Metrics and Benchmarking Results

Raghav Mehta

Angelos Filos

Ujjwal Baid

Chiharu Sako

Richard McKinley

Michael Rebsamen

Katrin Dätwyler

Raphael Meier

Piotr Radojewski

Gowtham Krishnan Murugesan

Sahil Nalawade

Chandan Ganesh

Benjamin C. Wagner

Fang Frank Yu

Baowei Fei

Ananth J. Madhuranthakam

Joseph A. Maldjian

Laura Daza

Catalina Gómez

Pablo Arbeláez … (see 72 more)

Chengliang Dai

Shuo Wang

Hadrien Reynaud

Yuanhan Mo

Elsa Angelini

Yike Guo

Wenjia Bai

Subhashis Banerjee

Linmin Pei

Murat AK

Sarahi Rosas-González

Ilyess Zemmoura

Clovis Tauber

Minh H. Vu

Tufve Nyholm

Tommy Löfstedt

Laura Mora Ballestar

Veronica Vilaplana

Hugh McHugh

Gonzalo Maso Talou

Alan Wang

Jay Patel

Ken Chang

Katharina Hoebel

Mishka Gidwani

Nishanth Arun

Sharut Gupta

Mehak Aggarwal

Praveer Singh

Elizabeth R. Gerstner

Jayashree Kalpathy-Cramer

Nicolas Boutry

Alexis Huard

Lasitha Vidyaratne

Md Monibor Rahman

Khan M. Iftekharuddin

Joseph Chazalon

Elodie Puybareau

Guillaume Tochon

Jun Ma

Mariano Cabezas

Xavier Llado

Arnau Oliver

Liliana Valencia

Sergi Valverde

Mehdi Amian

Mohammadreza Soltaninejad

Andriy Myronenko

Ali Hatamizadeh

Xue Feng

Quan Dou

Nicholas Tustison

Craig Meyer

Nisarg A. Shah

Sanjay Talbar

Marc-André Weber

Abhishek Mahajan

Andras Jakab

Roland Wiest

Hassan M. Fathallah-Shaykh

Arash Nazeri

Mikhail Milchenko

Daniel Marcus

Aikaterini Kotrotsou

Rivka R. Colen

John Freymann

Justin Kirby

Christos Davatzikos

Bjoern Menze

Spyridon Bakas

Yarin Gal

2022-08-26

Machine Learning for Biomedical Imaging (published)

Heatmap Regression for Lesion Detection using Pointwise Annotations

Chelsea Myers-Colet

Julien Schroeter

Douglas Arnold

In many clinical contexts, detecting all lesions is imperative for evaluating disease activity. Standard approaches pose lesion detection as… (see more) a segmentation problem despite the time-consuming nature of acquiring segmentation labels. In this paper, we present a lesion detection method which relies only on point labels. Our model, which is trained via heatmap regression, can detect a variable number of lesions in a probabilistic manner. In fact, our proposed post-processing method offers a reliable way of directly estimating the lesion existence uncertainty. Experimental results on Gad lesion detection show our point-based method performs competitively compared to training on expensive segmentation labels. Finally, our detection model provides a suitable pre-training for segmentation. When fine-tuning on only 17 segmentation samples, we achieve comparable performance to training with the full dataset.

2022-08-11

ArXiv (preprint)

Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markers

Amar Kumar

Anjun Hu

Brennan Nichyporuk

Jean-Pierre R. Falet

Douglas Arnold

Sotirios A. Tsaftaris