Mednet: Computer-Aided Disease Detection and Grading from Medical Images

Posted on Fri 01 September 2023 in software

Mednet is disease classification and grading library for medical imaging based on PyTorch.

Continue reading

Sleepless: Library for sleep phase detection from polysomnographs

Posted on Tue 15 August 2023 in software

Sleepless is library for sleep phase detection from polysomnographs, based on Scikit-Learn and PyTorch.

Continue reading

Samuel Michel: Generalizable Automatic Classification of Sleep Stages

Posted on Sun 30 July 2023 in theses

This thesis develops stateless methods for sleep-phase detection from polysomnographs (PSG), while exploring techniques to improve cross-database generalisation.

Continue reading

Xiao Tan: Semantic Segmentation of Weakly Labeled Retinal Images

Posted on Tue 28 March 2023 in theses

In this thesis, we developed a technique to learn vessel segmentation from retinal fundus images using weakly-supervised methods.

Continue reading

Deepdraw: Semantic segmentation library for medical imaging

Posted on Sun 01 January 2023 in software

Deepdraw is semantic segmentation library for medical imaging based on PyTorch.

Continue reading

Maxime Délitroz: Automated Segmentation of High-content Fluorescent Microscopy Data of Developing MN in Culture

Posted on Tue 30 August 2022 in theses

In this thesis, we sought at developing precise neuron segmentation in order to support future study on the morphological phenotype of amyotrophic lateral sclerosis.

Continue reading

Driss Khalil: Multi-task Computer-Aided Segmentation for Eye Fundus Imaging

Posted on Fri 15 July 2022 in theses

Continue reading

IFI/UZH Summerschool: From Scripts to Reusable Software and Reproducible Research

Posted on Wed 29 June 2022 in courses

The course provides actionable guidelines on how to convert non-reproducible scripts with hard-coded parameters into reusable software.

Continue reading

Antonio Morais: A Bayesian approach to machine learning model comparison

Posted on Mon 28 February 2022 in theses

Performance measures are an important component of machine learning algorithms. They are useful when it comes to evaluate the quality of a model, but also to help the algorithm improve itself. When used in small data sets, these measures may not properly express the performance of the model. That is when confidence intervals and credible regions can be useful. Expressing the performance measures in a probabilistic setting allows one to develop them as distributions. One can then use those distributions to establish credible regions.

Continue reading

Is Computer-Aided Diagnosis fair towards minorities?

Posted on Thu 10 February 2022 in media

An invited talk on the subject of fairness in Machine Learning applied to Computer-Aided Diagnosis at the University of Lausanne.

Continue reading

Article: "L'IA est utile dans tous les secteurs de la médecine"

Posted on Tue 11 January 2022 in media

Short interview for a periodical publication from the COOP group in Switzerland, called Cooperation.

Continue reading

Round-Table on "AI in Health"

Posted on Thu 11 November 2021 in media

I contributed to a round table, part of the Industry Connect programme, sponsored by alp+ict, CimArk and Idiap (in French)

Continue reading

Geoffrey Raposo: Active tuberculosis detection from frontal chest X-ray images

Posted on Thu 15 July 2021 in theses

In this study, we investigate the benefits of automatic Pulmonary Tuberculosis (PTB) detection methods based on radiological signs found on frontal chest X-Ray images.

Continue reading

Swiss Digital Health Article

Posted on Tue 29 June 2021 in media

Article about my group's current work on the Swiss Digital Health Platform (in French)

Continue reading

Reproducibility in Data Sciences Why, What, and How

Posted on Thu 29 April 2021 in media

My invited talk at University of Zurich on Reproducible Research background, motivations and methodology.

Continue reading

WIP: Intepretable Classification: Chest X-Rays

Posted on Wed 14 April 2021 in research

Tuberculosis (TB) is one of the leading causes of death from a single infectious agent. In many high-burden regions around the world, which often lack specialized healthcare professionals, Chest X-Ray (CXR) exams continue to be of vital importance in the diagnosis and follow-up of the various presentations of the disease. In this context, we investigate the benefits of automatic Pulmonary Tuberculosis (PTB) detection methods from these images.

Continue reading

Semantical Segmentation: Retinography

Posted on Wed 14 April 2021 in research

Semantical segmentation of eye fundus structures, and disease detection from retinography, play a key role in mass screening using this tecnology. Despite the incredible progress in these fields, the lack of annotated images (due to cost), and rigor in the comparison of trained models has led to the conclusion larger and more dense network models provide more accurate results for such tasks. We present our findings on different architectures and databases in this context.

Continue reading


Posted on Tue 13 April 2021 in software

Bob is a signal-processing and machine learning toolbox originally developed by the Biometrics Security and Privacy Group, the Biosignal Processing Group, and the Research and Development Engineers Group at the Idiap Research Institute, in Switzerland. Bob is primarily developed through GitLab.

Continue reading

Open Science and Ethics

Posted on Tue 13 April 2021 in courses

This is an introductory course on Ethics and Reproducibility in Artificial Intelligence (AI). The course is composed of two parts. The first part covers ethical aspects of AI, while the second, practical aspects on building AI systems so they are continuously reproducible and extensible. It is given to master students at the Master in AI by the Idiap Research Institute, Switzerland.

Continue reading

Fundamentals of Machine Learning

Posted on Tue 13 April 2021 in courses

This course, divided in two trimesters (modules M06 and M08), presents fundamental tools used in machine learning ranging from the most basic to more advanced. It is given to master students at the Master in AI by the Idiap Research Institute, Switzerland.

Continue reading

Fundamentals of Statistical Pattern Recognition

Posted on Tue 13 April 2021 in courses

This course (EE-612) presents fundamental tools used in Machine Learning ranging from the most basic to more advanced. It is given to post-grad (Ph.D.) students at the École Polytechnique Fédérale de Lausanne, Switzerland.

Continue reading

Colombine Verzat: Machine Learning for Adverse Event Detection in Latent Tuberculosis Infection Treatment

Posted on Wed 15 July 2020 in theses

The goal of this study is to identify whether it is possible to predict the occurrence of adverse events in patients based on their clinical data.

Continue reading

Reproducible Research

Posted on Wed 01 January 2020 in research

Reproducible research not only leads to proper scientific conduct but also provides other researchers the access to build upon previous work. Most importantly, the person setting up a reproducible research project will quickly realize the immediate personal benefits: an organized and structured way of working. The person that most often has to reproduce your own analysis is your future self!

Continue reading

WIP: Vital Sign Analysis: Decompensation

Posted on Fri 20 September 2019 in research

Early and accurate prediction of decompensation (functional deterioration) in patients in domestic settings may help prevent deaths. Based on values that can be measured from portable devices such as heart rate, blood oxygen saturation, systolic blood pressure, temperature, and age, we study the prediction capability of machine learning algorithms to determine patient decompensation (death) in the next 24 hours.

Continue reading

Remote Photoplethysmography

Posted on Tue 20 November 2018 in research

We address the problem of reproducible research in remote photo-plethysmography (rPPG). Most of the work published in this domain is assessed on privately-owned databases, making it difficult to evaluate proposed algorithms in a standard and principled manner. As a consequence, we present a new, publicly available database containing a relatively large number of subjects recorded under two different lighting conditions. Also, three state-of-the-art rPPG algorithms from the literature were selected, implemented and released as open source free software. After a thorough, unbiased experimental evaluation in various settings, it is shown that none of the selected algorithms is precise enough to be used in a real-world scenario.

Continue reading

Computer Vision and Deep Learning for Biometrics

Posted on Tue 01 May 2018 in research

I have actively worked in computer vision and deep learning (mostly) associated to biometric recognition, with potential application to various other tasks. Contributions range from the collection of datasets, the exploration of different methods to address and assess biometric recognition vulnerabilities, domain adaptation, and remote photoplethysmography.

Continue reading

Talk at Valais/Wallis AI Workshop - Reproducibility in research

Posted on Fri 24 March 2017 in media

My talk at the Valais/Wallis AI workshop on reproducible research

Continue reading

Interview for Télévision Suisse-Romande (TSR), 12h45

Posted on Tue 22 November 2016 in media

I was interviewed for a document on biometric vein recognition in the Swiss's RTS 12h45 news

Continue reading

The BEAT Platform

Posted on Wed 16 March 2016 in software

The BEAT platform is a European computing e-infrastructure for Open Science proposing a solution for open access, scientific information sharing and re-use including data and source code while protecting privacy and confidentiality.

Continue reading

Overview of the BEAT Platform

Posted on Wed 16 March 2016 in media

Introductory video to the BEAT Platform for Open Science and Reproducible Research

Continue reading

Reproducible Research for Pattern Recognition

Posted on Wed 22 July 2015 in courses

This is a course on Reproducible Research (RR) for research engineers working with software applications in Pattern Recognition (PR) and Machine Learning (ML). It motivates and explains concepts behind RR, an increasing trend in scientific publications in this niche, its implications and tools for implementing it on an individual or group levels. It is a hands-on course in the sense students will be required to create their own workflows for selected problems in ML and PR. By the end of this course, students should understand the basic concepts of reproducibility, its importance on their daily practice and how to achieve it with freely available tools and environments.

Continue reading

Interview for Jornal Nacional

Posted on Wed 10 September 2008 in media

I was interviewed for a document in Jornal Nacional, one of the most viewed brazilian 20h00 news program.

Continue reading