Prof. Henning Müller gave a presentation for the Digital Health Connect 2020 on Connecting visual information with semantics in histopathology image analysis for learning from weak labels.
How do you interpret your machine learning models?
Our third-year Ph.D. student Mara Graziani gave a virtual tutorial at IBM Research Zurich about applying interpretability techniques.
The recording was kindly shared on the Youtube channel of our school.
This talk provides an overview of the main interpretability approaches and a glimpse of our future research directions.
Our paper on the “Effect of movement type on the classification of electromyography data for the control of dexterous prosthetic hands” by Manfredo Atzori, Elisa Rosanda, Giorgio Pajardi, Franco Bassetto and Henning Müller has been accepted for presentation at the IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob 2020). The conference is currently planned to take place 29 Nov. – 2 Dec. 2020, in New York City, NY, USA.
Our Bridging Grant 2019 application has been accepted, in collaboration with the Research Center for Molecular and Cellular Imaging in Tehran University of Medical Sciences. This work will aim at the analysis of low-grade diffuse gliomas in MRI images. A large cohort of patients with brain cancer will be imaged with modern MRI scanners and analyzed using state of the art medical image analysis methods.
Our paper on Learning-based affine registration of histopathological images, by Marek Wodzinski and Henning Müller has been accepted and will be presented at WBIR 2020, the International Workshop on Biomedical Image Registration, Portoroz, Slovenia. Updates on the conference organization are coming soon.
Henning Müller will present his invited paper on Medical Image Retrieval: Applications and Resources and will give a keynote presentation at the ACM International Conference on Multimedia Retrieval (ICMR), 26-29th October 2020 in Dublin, Ireland.
Our paper on Automatic Segmentation of Head and Neck Tumors and Nodal Metastases in PET-CT has been accepted for presentation at the international conference on Medical Imaging with Deep Learning (MIDL). The conference will be fully virtual 6-8 July. In this paper, we developed a baseline for our MICCAI challenge (HECKTOR, more information to come).
Our paper entitled “Training a Deep Neural Networks for Small and Highly Heterogeneous MRI Datasets for Cancer Grading”, by Marek Wodzinski, Tommaso Banzato, Manfredo Atzori, Vincent Andrearczyk, Yashin Dicente Cid and Henning Müller, has been accepted for presentation at EMBC 2020, the International Conferences of the IEEE Engineering in Medicine and Biology Society in conjunction with the Conference of the Canadian Medical and Biological Engineering Society.
Our paper entitled “The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping” has been accepted for publication in Radiology. It is the result of a large collaboration of researchers grouped under the name of Image Biomarker Standardization Initiative (IBSI), working towards standardizing the extraction of image biomarkers for radiomics studies.
Valentin Oreiller successfully passed his mid-thesis exam at the UNIL FBM quantitative biology doctoral school. Congratulations! His thesis is co-supervised by Prof. Adrien Depeursinge and Prof. John O. Prior.
The paper “Integrating radiomics into holomics for personalised oncology: from algorithms to bedside” by Roberto Gatta, Adrien Depeursinge, Osman Ratib, Olivier Michielin, and Antoine Leimgruber has been accepted for publication in European Radiology Experimental.
This work is the result of a collaboration between CHUV, HES-SO, and the Riviera-Chablais Hospital.
The full text is now available online at this link.
The paper on “Gaze, behavioral, and clinical data for phantom limbs after hand amputation from 15 amputees and 29 controls”, by Gianluca Saetta, Matteo Cognolato, Manfredo Atzori, Diego Faccio, Katia Giacomino, Anne-Gabrielle Mittaz Hager, Cesare Tiengo, Franco Bassetto, Henning Müller, Peter Brugger, has been accepted in Scientific Data and is now available online here.
The paper entitled “Gaze, visual, myoelectric, and inertial data of grasps for intelligent prosthetics“, by Matteo Cognolato, Arjan Gijsberts, Valentina Gregori, Gianluca Saetta, Katia Giacomino, Anne-Gabrielle Mittaz Hager, Andrea Gigli, Diego Faccio, Cesare Tiengo, Franco Bassetto, Barbara Caputo, Peter Brugger, Manfredo Atzori and Henning Müller has been accepted and published in Scientific Data, a journal from the publishers of Nature.
Don’t miss our new Medium publication page. You can find there technical tutorials, stories and insights on our research focus, and updates from conferences.
Some of our latest posts are:
How docker changed my life: deploying machine learning has never been this easy!
A simple formula for complex research: how to explain the role of AI to non- geeks
The prosthesis that everybody wants: working with amputees to design inexpensive prosthetic hands that work well
Cristina Simon-Martinez has been awarded a prestigious Individual Fellowship of the Marie Curie Actions, funded by the European Union, for the project Optimizing Vision reHABilition with virtual-reality games in pediatric amblyopia (V-HAB). The grant lasts for 2 years and offers exciting new learning opportunities, also contributing to the training, networking and research costs of the fellow. With this grant, Cristina will study the impact of vision deficits on cognition and motor control in children with pediatric amblyopia and will use virtual reality as a means to reduce those deficits.
Our Scientific Data article on “A large calibrated database of hand movements and grasps kinematics“, by Néstor J. Jarque-Bou, Manfredo Atzori and Henning Müller is now available here.
Vincent Andrearczyk presented our work on exploiting images from public biomedical literature for machine learning at the 26th international conference on MultiMedia Modelling (MMM2020) in Daejeon, Korea.
Full details of the paper: “Studying Public Medical Images from the Open Access Literature and Social Networks for Model Training and Knowledge Extraction” by Henning Müller, Vincent Andrearczyk, Oscar Jimenez del Toro, Anjani Dhrangadhariya, Roger Schaer and Manfredo Atzori.