Osmar R. Zaïane

• PhD
• Professor at University of Alberta

Recent advancements in ophthalmology foundation models such as RetFound have demonstrated remarkable diagnostic capabilities but require massive datasets for effective pre-training, creating significant barriers for development and deployment. To address this critical challenge, we propose FundusGAN, a novel hierarchical feature-aware generative fr...

Due to the domain shifts between training and testing medical images, learned segmentation models often experience significant performance degradation during deployment. In this paper, we first decompose an image into its style code and content map and reveal that domain shifts in medical images involve: \textbf{style shifts} (\emph{i.e.}, differen...

Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal understanding and reasoning. These advances have led to a surge of research integrating LLMs and VLMs into RL. In this...

Length-control summarization aims to condense long texts into a short one within a certain length limit. Previous approaches often use autoregressive (AR) models and treat the length requirement as a soft constraint, which may not always be satisfied. In this study, we propose a novel length-control decoding algorithm based on the Directed Acyclic...

Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions. Recent work applies non-autoregressive Transformers to improve the efficiency of MNMT, but requires expensive knowledge distillation (KD) processes. To this end, we propose an M-DAT approach to non-autoregressive multilingual machine t...

Graph similarity estimation is a challenging task due to the complex graph structures. Though important and well-studied, three critical aspects are yet to be fully handled in a unified framework: 1) how to learn richer cross-graph interactions from a pairwise node perspective; 2) how to map the similarity matrix into a similarity score by exploiti...

Brain functional connectivity analysis is important for understanding brain development and brain disorders. Recent studies have suggested that the variations of functional connectivity among multiple subnetworks are closely related to the development of diseases. However, the existing works failed to sufficiently capture the complex correlation pa...

Recent advancements in deep learning techniques have significantly improved multi-label chest X-ray (CXR) image classification for clinical diagnosis. However, most previous studies neither effectively learn label correlations nor take full advantage of them to improve multi-label classification performance. In addition, different labels of CXR ima...

Associative classifiers have shown competitive performance with state-of-the-art classification methods for predicting class labels. In addition to their accuracy performance, associative classifiers produce human-readable rules for classification, providing an easier way to understand their decision-making process. However, the presence of high-di...

UNSTRUCTURED Misleading information has significant implications for society but can have disastrous impact for health matters. Transformative artificial intelligence (AI) tools such as large language models (LLMs) have the potential for limitless content generation (including fake), soon making internet information impossible to assess using tradi...

Mix-up is a key technique for consistency regularization-based semi-supervised learning methods, generating strong-perturbed samples for strong-weak pseudo-supervision. Existing mix-up operations are performed either randomly or with predefined rules, such as replacing low-confidence patches with high-confidence ones. The former lacks control over...

The existing barely-supervised medical image segmentation (BSS) methods, adopting a registration-segmentation paradigm, aim to learn from data with very few annotations to mitigate the extreme label scarcity problem. However, this paradigm poses a challenge: pseudo-labels generated by image registration come with significant noise. To address this...

Recently, there has been considerable attention on detecting hallucinations and omissions in Machine Translation (MT) systems. The two dominant approaches to tackle this task involve analyzing the MT system's internal states or relying on the output of external tools, such as sentence similarity or MT quality estimators. In this work, we introduce...

This paper investigates an extremely challenging problem, barely-supervised medical image segmentation (BSS), where the training dataset comprises limited labeled data with only single-slice annotations and numerous unlabeled images. Currently, state-of-the-art (SOTA) BSS methods utilize a registration-based paradigm, depending on image registratio...

A fundamental component of user-level social media language based clinical depression modelling is depression symptoms detection (DSD). Unfortunately, there does not exist any DSD dataset that reflects both the clinical insights and the distribution of depression symptoms from the samples of self-disclosed depressed population. In our work, we desc...

One of the greatest challenges to the automated production of goods is equipment malfunction. Ideally, machines should be able to automatically predict and detect operational faults in order to minimize downtime and plan for timely maintenance. While traditional condition-based maintenance (CBM) involves costly sensor additions and engineering, mac...

Topic modeling aims to discover latent themes in collections of text documents. It has various applications across fields such as sociology, opinion analysis, and media studies. In such areas, it is essential to have easily interpretable, diverse, and coherent topics. An efficient topic modeling technique should accurately identify flat and hierarc...

Medical image analysis techniques have been employed in diagnosing and screening clinical diseases. However, both poor medical image quality and illumination style inconsistency increase uncertainty in clinical decision-making, potentially resulting in clinician misdiagnosis. The majority of current image enhancement methods primarily concentrate o...

The progression of medical image analysis methodologies has significantly assisted fundus clinical decision-making, such as disease diagnosis and lesion segmentation. However, low-quality fundus images bring a series of challenges to the automatic screening of diseases and the segmentation of lesions. Most existing methods primarily concentrate on...

Dynamic graph link prediction is a challenging problem because the graph topology and node attributes vary at different times. A purely supervised learning scheme for the dynamic graph data usually leads to poor generalization due to insufficient supervision. As a promising solution, self-supervised learning can be introduced to dynamic graph analy...

Alzheimer’s disease (AD) is a common chronic neurodegenerative disease and the accurate prediction of the clinical cognitive performance is important for diagnosis and treatment. Recently, multi-task feature learning (MTFL) methods with sparsity-inducing regularization have been widely investigated on cognitive performance prediction tasks. Althoug...

Multi-label learning has received much attention due to its wide range of application domains. Multi-label data often has high-dimensional features, which brings more challenges to classification algorithms. Feature selection based on sparse learning is one of the most important approaches, which can select discriminative features to alleviate the...

Early diagnosis and screening of diabetic retinopathy are critical in reducing the risk of vision loss in patients. However, in a real clinical situation, manual annotation of lesion regions in fundus images is time-consuming. Contrastive learning(CL) has recently shown its strong ability for self-supervised representation learning due to its abili...

The functional connectivity (FC) between brain regions is usually estimated through a statistical dependency method with functional magnetic resonance imaging (fMRI) data. It inevitably yields redundant and noise connections, limiting the performance of deep supervised models in brain disease diagnosis. Besides, the supervised signals of fMRI data...

Alzheimer’s disease (AD) is a common irreversible neurodegenerative disease among elderlies. Establishing relationships between brain networks and cognitive scores plays a vital role in identifying the progression of AD. However, most of the previous works focus on a single time point, without modeling the disease progression with longitudinal brai...

Community detection methods aim to find nodes connected to each other more than other nodes in a graph. As they explore the entire network, global methods suffer from severe limitations when handling large networks due to their time and space complexity. Local community detection methods are based on an egocentric function aiming to find only the c...

Machine learning models are ubiquitous today in most application domains and are often taken for granted. While integrated into many systems, oftentimes even unnoticed by the user, these powerful models frequently remain as black-boxes. They are black-boxes because while they are powerful predictive models, it is commonly the case that one cannot u...

Consistency regularization and pseudo labeling-based semi-supervised methods perform co-training using the pseudo labels from multi-view inputs. However, such co-training models tend to converge early to a consensus, degenerating to the self-training ones, and produce low-confidence pseudo labels from the perturbed inputs during training. To addres...

Families of individuals with neurodevelopmental disabilities or differences (NDDs) often struggle to find reliable health information on the web. NDDs encompass various conditions affecting up to 14% of children in high-income countries, and most individuals present with complex phenotypes and related conditions. It is challenging for their familie...

UNSTRUCTURED Families of individuals with neurodevelopmental disabilities or differences (NDDs) often struggle to find reliable health information on the web. NDDs encompass various conditions affecting up to 14% of children in high-income countries, and most individuals present with complex phenotypes and related conditions. It is challenging for...

The less training data and insufficient supervision limit the performance of the deep supervised models for brain disease diagnosis. It is significant to construct a learning framework that can capture more information in limited data and insufficient supervision. To address these issues, we focus on self-supervised learning and aim to generalize t...

Computer-aided lung cancer diagnosis (CAD) system on computed tomography (CT) helps radiologists guide preoperative planning and prognosis assessment. The flexibility and scalability of deep learning methods are limited in lung CAD. In essence, two significant challenges to be solved are (1) Label scarcity due to cost annotations of CT images by ex...

We present an empirical analysis of basic and depression specific multi-emotion mining in Tweets, using state of the art multi-label classifiers. We choose our basic emotions from a hybrid emotion model consisting of the commonly identified emotions from four highly regarded psychological models. Moreover, we augment that emotion model with new emo...

This work tackles the problem of unsupervised modeling and extraction of the main contrastive sentential reasons conveyed by divergent viewpoints on polarized issues. It proposes a pipeline approach centered around the detection and clustering of phrases, assimilated to argument facets using a novel Phrase Author Interaction Topic-Viewpoint model....

Modeling the dynamics characteristics in functional brain networks (FBNs) is important for understanding the functional mechanism of the human brain. However, the current works do not fully consider the potential complex spatial and temporal correlations in human brain. To solve this problem, we propose a temporal graph representation learning fram...

Medical image segmentation is a challenging task due to the high variation in shape, size and position of infections or lesions in medical images. It is necessary to construct multi-scale representations to capture image contents from different scales. However, it is still challenging for U-Net with a simple skip connection to model the global mult...

Retinal fundus images have been applied for the diagnosis and screening of eye diseases, such as Diabetic Retinopathy (DR) or Diabetic Macular Edema (DME). However, both low-quality fundus images and style inconsistency potentially increase uncertainty in the diagnosis of fundus disease and even lead to misdiagnosis by ophthalmologists. Most of the...

High-quality pseudo labels are essential for semi-supervised semantic segmentation. Consistency regularization and pseudo labeling-based semi-supervised methods perform co-training using the pseudo labels from multi-view inputs. However, such co-training models tend to converge early to a consensus during training, so that the models degenerate to...

Diabetic retinopathy (DR) is one of the most serious complications of diabetes and is a prominent cause of permanent blindness. However, the low-quality fundus images increase the uncertainty of clinical diagnosis, resulting in a significant decrease on the grading performance of the fundus images. Therefore, enhancing the image quality is essentia...

The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources. However, dialogue systems often produce unsupported utterances, a phenomenon known as hallucination. To mitigate this behavior, we adopt a data-centric solution and create FaithDial, a new benchmark for h...

The most popular topic modelling algorithm, Latent Dirichlet Allocation, produces a simple set of topics. However, topics naturally exist in a hierarchy with larger, more general super-topics and smaller, more specific sub-topics. We develop a novel topic modelling algorithm, Community Topic, that mines communities from word co-occurrence networks...

Association rule mining can be a powerful computational tool for exploring complex interactions between high-dimensional exposures and health outcomes. Given the high-dimensional nature of the data, many complex association rules may be identified. To narrow down on the most important rules for hypothesis-generating and future investigation in the...

Alzheimer’s disease (AD) is highly prevalent and a significant cause of dementia and death in elderly individuals. Motivated by breakthroughs of multi-task learning (MTL), efforts have been made to extend MTL to improve the Alzheimer’s disease cognitive score prediction by exploiting structure correlation. Though important and well-studied, three k...

PurposeFinding the biomarkers associated with autism spectrum disorder (ASD) is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatments. In essence, we are faced with two challenges (i) how to learn a node representation and a clean graph structure from original graph data with h...

Deep neural networks architecture provides a pow- erful technique for solving various problems including clas- sification. They owe their performance to the complex and layered data representation and processing built upon neural networks. The success of deep neural networks in various fields has resulted in less focus on other techniques like rule...

We describe the development of a model to detect user-level clinical depression based on a user's temporal social media posts. Our model uses a Depression Symptoms Detection (DSD) model, which is trained on the largest existing samples of clinician annotated tweets for clinical depression symptoms. We subsequently use our DSD model to extract clini...

A fundamental component of user-level social media language based clinical depression modelling is depression symptoms detection (DSD). Unfortunately, there does not exist any DSD dataset that reflects both the clinical insights and the distribution of depression symptoms from the samples of self-disclosed depressed population. In our work, we desc...

Identifying fake news is a very difficult task, especially when considering the multiple modes of conveying information through text, image, video and/or audio. We attempted to tackle the problem of automated misinformation/disinformation detection in multi-modal news sources (including text and images) through our simple, yet effective, approach i...

Recently, functional brain networks have been employed for classifying neurological disorders, such as autism spectrum disorders (ASDs). Graph convolutional networks (GCNs) have been shown to be successful in modeling applications with graph structures. However, brain network data is in general of complex structure with small sample size, and the u...

The diagnosis of chest diseases is a challenging task for assessing thousands of radiology subjects. Their diagnosis decisions heavily rely on the expert radiologists' manual annotations. It is important to develop automated analysis methods for the computer-aided diagnosis of chest diseases on chest radiography. To explore the label relationship a...

Algorithmic trading, due to its inherent nature, is a difficult problem to tackle; there are too many variables involved in the real-world which makes it almost impossible to have reliable algorithms for automated stock trading. The lack of reliable labelled data that considers physical and physiological factors that dictate the ups and downs of th...

How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent non-autoregressive translation models speed up the inference, but their quality is still inferior. In this work, we...

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some...

The most common Named Entity Recognizers are usually sequence taggers trained on fully annotated corpora, i.e. the class of all words for all entities is known. Partially annotated corpora, i.e. some but not all entities of some types are annotated, are too noisy for training sequence taggers since the same entity may be annotated one time with its...

The dynamic functional connectivity analysis provides valuable information for understanding functional brain activity underlying different cognitive processes. Modeling spatio-temporal dynamics in functional brain networks is critical for underlying the functional mechanism of autism spectrum disorder (ASD). In our study, we propose a machine lear...

Object detection is a fundamental problem in computer vision. Although impressive results have been achieved on large/medium-sized objects, the detection performance of small objects remains a challenging task. Automatic ship detection on remote sensing images is an important module in maritime surveillance system, and it is challenging due to the...

The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources. However, dialogue systems often produce unsupported utterances, a phenomenon known as hallucination. Dziri et al. (2022)'s investigation of hallucinations has revealed that existing knowledge-grounded ben...

The most common Named Entity Recognizers are usually sequence taggers trained on fully annotated corpora, i.e. the class of all words for all entities is known. Partially annotated corpora, i.e. some but not all entities of some types are annotated, are too noisy for training sequence taggers since the same entity may be annotated one time with its...

Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallucination. In this work, we investigate the underlying causes of this phenomenon: is hallucination due to the training data, or to the models? We conduct a comprehensive human study on both existing knowledge-gr...

To effectively train accurate Relation Extraction models, sufficient and properly labeled data is required. Adequately labeled data is difficult to obtain and annotating such data is a tricky undertaking. Previous works have shown that either accuracy has to be sacrificed or the task is extremely time-consuming, if done accurately. We are proposing...

Early detection and treatment of diabetic retinopathy (DR) can significantly reduce the risk of vision loss in patients. In essence, we are faced with two challenges: (i) how to simultaneously achieve domain adaptation from the different domains and (ii) how to build an interpretable multi-instance learning (MIL) on the target domain in an end-to-e...

Purpose: Accurate diagnosis of autism spectrum disorder (ASD) plays a key role in improving the condition and quality of life for patients. In this study, we mainly focus on ASD diagnosis with functional brain networks (FBNs). The major challenge for brain networks modeling is the high dimensional connectivity in brain networks and limited number...

Identifying fake news is a very difficult task, especially when considering the multiple modes of conveying information through text, image, video and/or audio. We attempted to tackle the problem of automated misinformation/disinformation detection in multi-modal news sources (including text and images) through our simple, yet effective, approach i...

Purpose Recently, functional brain networks (FBN) have been used for the classification of neurological disorders, such as Autism Spectrum Disorders (ASD). Neurological disorder diagnosis with FBN is a challenging task due to the high heterogeneity in subjects and the noise correlations in brain networks. Meanwhile, it is challenging for the existi...

Exposure to pollution in the environment is a major contributor to disease globally and is a topic of great significance. There remains, however, a dearth of knowledge about the levels and distribution of airborne pollutants in the environment, along with how exposure to complex mixtures of airborne chemicals impacts health outcomes. Recent collabo...

Twitter is used to provide location-relevant information and event updates. It is important to identify location-relevant tweets in order to harness location-relevant information and event updates from Twitter. However, the identification of location-relevant tweets is a challenging problem as the location names are not always explicit. Instead, mo...

Alzheimer's disease (AD) is a gradually progressive neurodegenerative disease affecting cognition functions. Predicting the cognitive scores from neuroimage measures and identifying relevant imaging biomarkers are important research topics in the study of AD. Despite machine learning algorithms having many successful applications, the prediction mo...

The rapid growth of research in explainable artificial intelligence (XAI) follows on two substantial developments. First, the enormous application success of modern machine learning methods, especially deep and reinforcement learning, have created high expectations for industrial, commercial, and social value. Second, the emerging and growing conce...

Accurate diagnosis of psychiatric disorders plays a critical role in improving the quality of life for patients and potentially supports the development of new treatments. Graph convolutional networks (GCNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GCNs model for brain networks faces s...

Most major events are often accompanied by misinformation on online Social Networking platforms. Due to its nature, the COVID-19 pandemic was bound to lead to an explosion of information online, much of it false or misleading. This information explosion, termed ``infodemic'' by the World Health Organization (WHO), has revealed the need for automati...

How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent non-autoregressive translation models speed up the inference, but their quality is still inferior. In this work, we...

Alzheimer's disease (AD) is a severe neurodegenerative disorder that usually starts slowly and progressively worsens. Predicting the progression of Alzheimer's disease with longitudinal analysis on the time series data has recently received increasing attention. However, training an accurate progression model for brain network faces two major chall...

Explicitly modeling emotions in dialogue generation has important applications, such as building empathetic personal companions. In this study, we consider the task of expressing a specific emotion for dialogue generation. Previous approaches take the emotion as an input signal, which may be ignored during inference. We instead propose a search-bas...

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some...

Association rule mining can be a powerful computational tool for exploring complex interactions between high-dimensional exposures and health outcomes. Given the high-dimensional nature of the data, many complex association rules may be identified. To narrow down on the most important rules for hypothesis-generating and future investigation in the...

Social network analysis encompasses the study of networked data and examines questions related to structures and patterns that can lead to the understanding of the data and the intrinsic relationships, such as identifying influential nodes, recognizing critical paths, predicting unobserved relationships, discovering communities, etc. All of these a...