Publications

Correlation between Preoperative MRI Parameters and Oswestry Disability Index in Patients with Lumbar Spinal Stenosis: A Retrospective Study

Radu Caprariu

Manuel D. Oprea

Dan V. Poenaru

Diana Andrei

Background and Objectives: Lumbar spinal stenosis (LSS) is a degenerative condition posing significant challenges in clinical management. De… (see more)spite the use of radiological parameters and patient-reported outcome measures like the Oswestry Disability Index (ODI) for evaluation, there is limited understanding of their interrelationship. This study aimed to investigate the correlation between preoperative MRI parameters and ODI scores in patients with LSS undergoing surgical treatment. Materials and Methods: A retrospective analysis was conducted on 86 patients diagnosed with LSS over a 5-year period. Preoperative MRI measurements, including the cross-sectional area of the psoas muscle, lumbar canal stenosis, neural foramina area, and facet joint osteoarthritis, were assessed. ODI scores were collected preoperatively and at a 1-year follow-up. Statistical analyses were performed using IBM SPSS Statistics software (version 26). Results: Weak to moderate correlations were observed between certain MRI parameters and ODI scores. The initial ODI score had a weak positive correlation with the severity of lumbar canal stenosis according to Schizas criteria (rho = 0.327, p = 0.010) and a moderate negative correlation with the relative cross-sectional area of the psoas muscle (rho = −0.498, p = 0.000). At 1-year follow-up, the ODI had a weak negative correlation with the relative cross-sectional area of the psoas muscle (rho = −0.284, p = 0.026). Conclusions: While the severity of LSS showed a weak correlation with initial ODI, it was not a predictor of 1-year postoperative ODI. Furthermore, although the cross-sectional area of the thecal sac, the sagittal area of the neural foramen, and the grade of facet joint osteoarthritis influence the imagistic severity, none of them correlate with ODI. These findings underscore the need for a comprehensive model that integrates multiple imaging and clinical parameters for a holistic understanding of LSS and its functional outcomes.

2023-11-13

Medicina (published)

doi.org

Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning

Yuchen Lu

Romain Laroche

2023-11-13

Transactions on Machine Learning Research (accepted)

doi.org

openreview.net

General anaesthesia reduces the uniqueness of brain connectivity across individuals and across species

Andrea I. Luppi

Daniel Golkowski

Andreas Ranft

Rudiger Ilg

Denis Jordan

Danilo Bzdok

Adrian M. Owen

Lorina Naci

Emmanuel A. Stamatakis

Enrico Amico

Bratislav Misic

The human brain is characterised by idiosyncratic patterns of spontaneous thought, rendering each brain uniquely identifiable from its neura… (see more)l activity. However, deep general anaesthesia suppresses subjective experience. Does it also suppress what makes each brain unique? Here we used functional MRI under the effects of the general anaesthetics sevoflurane and propofol to determine whether anaesthetic-induced unconsciousness diminishes the uniqueness of the human brain: both with respect to the brains of other individuals, and the brains of another species. We report that under anaesthesia individual brains become less self-similar and less distinguishable from each other. Loss of distinctiveness is highly organised: it co-localises with the archetypal sensory-association axis, correlating with genetic and morphometric markers of phylogenetic differences between humans and other primates. This effect is more evident at greater anaesthetic depths, reproducible across sevoflurane and propofol, and reversed upon recovery. Providing convergent evidence, we show that under anaesthesia the functional connectivity of the human brain becomes more similar to the macaque brain. Finally, anaesthesia diminishes the match between spontaneous brain activity and meta-analytic brain patterns aggregated from the NeuroSynth engine. Collectively, the present results reveal that anaesthetised human brains are not only less distinguishable from each other, but also less distinguishable from the brains of other primates, with specifically human-expanded regions being the most affected by anaesthesia.

2023-11-12

bioRxiv (preprint)

doi.org

Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games

Arjun Vaithilingam Sudhakar

Prasanna Parthasarathi

Janarthanan Rajendran

Sarath Chandar

2023-11-12

arXiv (preprint)

doi.org

arxiv.org

Towards Climate Variable Prediction with Conditioned Spatio-Temporal Normalizing Flows

Christina Winkler

David Rolnick

2023-11-11

ArXiv (preprint)

arxiv.org

Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies

Shiva Kanth Sujit

Pedro Braga

Jörg Bornschein

S Ebrahimi Kahou

Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from … (see more)scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a tremendous amount of environment interactions for learning. This can be infeasible in situations where such interactions are expensive, such as in robotics. Offline RL algorithms try to address this issue by bootstrapping the learning process from existing logged data without needing to interact with the environment from the very beginning. While online RL algorithms are typically evaluated as a function of the number of environment interactions, there isn't a single established protocol for evaluating offline RL methods. In this paper, we propose a sequential approach to evaluate offline RL algorithms as a function of the training set size and thus by their data efficiency. Sequential evaluation provides valuable insights into the data efficiency of the learning process and the robustness of algorithms to distribution changes in the dataset while also harmonizing the visualization of the offline and online learning phases. Our approach is generally applicable and easy to implement. We compare several existing offline RL algorithms using this approach and present insights from a variety of tasks and offline datasets.

2023-11-09

TMLR (accepted)

doi.org

openreview.net

DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection

Hadi Hojjati

Narges Armanfard

Semi-supervised anomaly detection aims to detect anomalies from normal samples using a model that is trained on normal data. With recent adv… (see more)ancements in deep learning, researchers have designed efficient deep anomaly detection methods. Existing works commonly use neural networks to map the data into a more informative representation and then apply an anomaly detection algorithm. In this paper, we propose a method, DASVDD, that jointly learns the parameters of an autoencoder while minimizing the volume of an enclosing hyper-sphere on its latent representation. We propose an anomaly score which is a combination of autoencoder's reconstruction error and the distance from the center of the enclosing hypersphere in the latent representation. Minimizing this anomaly score aids us in learning the underlying distribution of the normal class during training. Including the reconstruction error in the anomaly score ensures that DASVDD does not suffer from the common hypersphere collapse issue since the DASVDD model does not converge to the trivial solution of mapping all inputs to a constant point in the latent representation. Experimental evaluations on several benchmark datasets show that the proposed method outperforms the commonly used state-of-the-art anomaly detection algorithms while maintaining robust performance across different anomaly classes.

2023-11-09

IEEE Transactions on Knowledge and Data Engineering (unknown)

doi.org

arxiv.org

CD3ζ ITAMs enable ligand discrimination and antagonism by inhibiting TCR signaling in response to low-affinity peptides

Guillaume Gaud

Sooraj Achar

François X. P. Bourassa

John Davies

Teri Hatzihristidis

Seeyoung Choi

Taisuke Kondo

Selamawit Gossa

Jan Lee

Paul Juneau

Naomi Taylor

Christian S. Hinrichs

Dorian B. McGavern

Paul François

Grégoire Altan‐Bonnet

Paul E. Love

2023-11-08

Nature Immunology (unknown)

doi.org

Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize

Ryan D'Orazio

Nicolas Loizou

Issam Hadj Laradji

Ioannis Mitliagkas

We investigate the convergence of stochastic mirror descent (SMD) under interpolation in relatively smooth and smooth convex optimization. I… (see more)n relatively smooth convex optimization we provide new convergence guarantees for SMD with a constant stepsize. For smooth convex optimization we propose a new adaptive stepsize scheme --- the mirror stochastic Polyak stepsize (mSPS). Notably, our convergence results in both settings do not make bounded gradient assumptions or bounded variance assumptions, and we show convergence to a neighborhood that vanishes under interpolation. Consequently, these results correspond to the first convergence guarantees under interpolation for the exponentiated gradient algorithm for fixed or adaptive stepsizes. mSPS generalizes the recently proposed stochastic Polyak stepsize (SPS) (Loizou et al. 2021) to mirror descent and remains both practical and efficient for modern machine learning applications while inheriting the benefits of mirror descent. We complement our results with experiments across various supervised learning tasks and different instances of SMD, demonstrating the effectiveness of mSPS.

2023-11-07

TMLR (accepted)

openreview.net

Capture the Flag: Uncovering Data Insights with Large Language Models.

Issam H. Laradji

Perouz Taslakian

Sai Rajeswar

Valentina Zantedeschi

Alexandre Lacoste

Nicolas Chapados

David Vázquez

Christopher Pal

Alexandre Drouin

The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making. Howev… (see more)er, accomplishing this task requires considerable technical skills, domain expertise, and human labor. This study explores the potential of using Large Language Models (LLMs) to automate the discovery of insights in data, leveraging recent advances in reasoning and code generation techniques. We propose a new evaluation methodology based on a "capture the flag" principle, measuring the ability of such models to recognize meaningful and pertinent information (flags) in a dataset. We further propose two proof-of-concept agents, with different inner workings, and compare their ability to capture such flags in a real-world sales dataset. While the work reported here is preliminary, our results are sufficiently interesting to mandate future exploration by the community.

2023-11-06

NeurIPS.cc/2023/Workshop/FMDM (published)

doi.org

openreview.net

The Unsolved Challenges of LLMs as Generalist Web Agents: A Case Study

Rim Assouel

Tom Marty

Massimo Caccia

Issam Hadj Laradji

Alexandre Drouin

Sai Rajeswar

Hector Palacios