News

A request to the Hasler Foundation has been approved for the project ELGAR PRO – Electromyography, Gaze & Artificial-intelligence for Prosthetic Robustness. The approved amount is CHF 44,460.

Prof. Henning Müller is included among the organizers of Open Science Prize projects. The Open Science Prize is a partnership between the Wellcome Trust, the US National Institutes of Health (NIH) and the Howard Hughes Medical Institute to unleash the power of open content and data to advance biomedical research and its application for health benefit.

The deepPMC project uses the Open PubMed Central content to create deep training data sets for machine learning and image analysis. The goals of this pilot project would be to
i) enrich the metadata of open access content of PMC focusing on the histopathology image data by organizing challenges for crowdsourcing of this task
ii) develop tools that give access to the data to develop cohorts for machine learning as well as to support information retrieval of images or articles based on visual and textual information.

A news report about the project Megane Pro was presented in Canal9, Switzerland. It contains a short interview with Manfredo Atzori:

http://canal9.ch/megane-pro-la-hes-so-et-le-valais-a-la-pointe-de-le-sante/

The project MEGANE PRO funded by the Swiss National Science Foundation (SNF) was launched Monday 8 February 2016 with a meeting in Sierre, Switzerland. The project is lead by Prof. Henning Müller with the collaboration of the University Hospital of Zurich, the IDIAP Research Institute and the University La Sapienza in Rome. 

The news were announced here: http://business24.ch/2016/02/09/projekt-zur-steuerung-von-handprothesen-im-wallis/

A Special Issue on Medical Information Retrieval has been published online. This issue from the Information Retrieval Journal was edited by Lorraine Goeuriot, Gareth J.F. Jones, Liadh Kelly, Henning Müller and Justine Zobel. 

‘Medical information search refers to methodologies and technologies that seek to improve access to medical information archives via a process of information retrieval (IR). Such information is now potentially accessible from many sources including the general web, social media, journal articles, and hospital records. Health-related content is one of the most searched-for topics on the internet, and as such this is an important domain for IR research. Medical information is of interest to a wide variety of users, including patients and their families, researchers, general practitioners and clinicians, and practitioners with specific expertise such as radiologists.’

Prof. Henning Müller will present ‘Medical image analysis and big data evaluation infrastructures’ at the Integrative Biomedical Imaging Informatics (IBIIS) group at Stanford. 

The presentation is part of the 2016 Seminar Series and will take place the 23rd march 2016:http://ibiis.stanford.edu/events/seminars/seminars2016.html

The paper ‘Medical information retrieval: introduction to the special issue’ by Lorraine Goeuriot, Gareth J.F. jones, Liadh Kelly, Henning Müller and Justin Zobel is now available online: http://link.springer.com/article/10.1007/s10791-015-9277-8?wt_mc=internal.event.1.SEM.ArticleAuthorOnlineFirst 

“Medical information search refers to methodologies and technologies that seek to improve access to medical information archives via a process of information retrieval (IR). Such information is now potentially accessible from many sources including the general web, social media, journal articles, and hospital records. Health-related content is one of the most searched-for topics on the internet, and as such this is an important domain for IR research. Medical information is of interest to a wide variety of users, including patients and their families, researchers, general practitioners and clinicians, and practitioners with specific expertise such as radiologists…”

Matteo Cognolato has joined the Medgift group.

Welcome to him!

The white paper “Evaluation-as-a-Service: Overview and Outlook” by Allan Hanbury et al. has now been published: http://arxiv.org/abs/1512.07454

This white paper is based on discussions at a workshop on Evaluation-as-a-Service (EaaS). EaaS is the paradigm of not providing data sets to participants and have them work on the data locally, but keeping the data central and allowing access via Application Programming Interfaces (API), Virtual Machines (VM) or other possibilities to ship executables. The objective of this white paper are to summarize and compare the current approaches and consolidate the experiences of these approaches to outline the next steps of EaaS, particularly towards sustainable research infrastructures. 

The proceedings from the First International Workshop Multimodal Retrieval in the Medical Domain (MRMD) 2015, Vienna Austria, March 29, 2015, are now available online: http://www.springer.com/us/book/9783319244709. 

The workshop was held in connection with ECIR 2015. The 14 full papers presented, including one invited paper, a workshop overview and five papers on the VISCERAL Retrieval  Benchmark, were carefully reviewed and selected from 18 submissions. The papers focus on the following topics: importance of data other than text for information retrieval; semantic data analysis; scalability approaches towards big data sets.

The paper ‘Control Capabilities of Myoelectric Robotic Prostheses by Hand Amputees: A Scientific Research and Market Overview’ by Manfredo Atzori and Henning Müller has been published in Frontiers in Systems Neuroscience. 

To view the online publication, please click here: http://journal.frontiersin.org/article/10.3389/fnsys.2015.00162/full?utm_source=Email_to_authors_&utm_medium=Email&utm_content=T1_11.5e1_author&utm_campaign=Email_publication&field=&journalName=Frontiers_in_Systems_Neuroscience&id=162387

“Hand amputation can dramatically affect the capabilities of a person. Cortical reorganization occurs in the brain, but the motor and somatosensorial cortex can interact with the remnant muscles of the missing hand even many years after the amputation, leading to the possibility to restore the capabilities of hand amputees through myoelectric prostheses. Myoelectric hand prostheses with many degrees of freedom are commercially available and recent advances in rehabilitation robotics suggest that their natural control can be performed in real life. The first commercial products exploiting pattern recognition to recognize the movements have recently been released, however the most common control systems are still usually unnatural and must be learned through long training. Dexterous and naturally controlled robotic prostheses can become reality in the everyday life of amputees but the path still requires many steps. This mini-review aims to improve the situation by giving an overview of the advancements in the commercial and scientific domains in order to outline the current and future chances in this field and to foster the integration between market and scientific research.”

Information regarding the “Digital Health 2016 – Early Diagnosis & Prevention – Professional & Scientific Summer School”, June 22-24 2016 in Geneva, Switzerland, is now on the website: www.hesge.ch/heds/summer-school-digital-health-2016.

A descriptive text, flyer and registration/ payment methods form can be found in the website. 

Each day a specific subject will be addressed, consisting of morning lectures and afternoon practical workshops and lab visits:
1. Electronic sensors for health monitoring, 
2. Medical imaging and image processing, 
3. Processing of big data in health. 
The theoretical morning sessions will introduce diverse applications of digital health devices for science and healthcare, but also provide critical views on the risks and other caveats of these innovative approaches. Apart from theoretical and practical aspects of data collection and processing, and their use in the context of early diagnosis and prevention, ethical aspects of digital health will be considered.
Hands-on workshops using established software for data processing, as well as collecting data and laboratory visits are scheduled during the afternoons.
A social program, important to reinforce national and international networking, is foreseen for the evenings.

Information regarding the “Digital Health 2016 – Early Diagnosis & Prevention – Professional & Scientific Summer School”, June 22-24 2016 in Geneva, Switzerland, is now on the website: www.hesge.ch/heds/summer-school-digital-health-2016.

A descriptive text, flyer and registration/ payment methods form can be found in the website. 

Each day a specific subject will be addressed, consisting of morning lectures and afternoon practical workshops and lab visits:
1. Electronic sensors for health monitoring, 
2. Medical imaging and image processing, 
3. Processing of big data in health. 
The theoretical morning sessions will introduce diverse applications of digital health devices for science and healthcare, but also provide critical views on the risks and other caveats of these innovative approaches. Apart from theoretical and practical aspects of data collection and processing, and their use in the context of early diagnosis and prevention, ethical aspects of digital health will be considered.
Hands-on workshops using established software for data processing, as well as collecting data and laboratory visits are scheduled during the afternoons.
A social program, important to reinforce national and international networking, is foreseen for the evenings.

The paper ‘How users search and what they search for in the medical domain: Understanding laypeople and experts through query logs’ by João Palotti, Allan Hanbury, Henning Müller and Charles E. Kahn Jr. is now available online: http://link.springer.com/article/10.1007/s10791-015-9269-8  

Abstract
The internet is an important source of medical knowledge for everyone, from laypeople to medical professionals. We investigate how these two extremes, in terms of user groups, have distinct needs and exhibit significantly different search behaviour. We make use of query logs in order to study various aspects of these two kinds of users. The logs from America Online, Health on the Net, Turning Research Into Practice and American Roentgen Ray Society (ARRS) GoldMiner were divided into three sets: (1) laypeople, (2) medical professionals (such as physicians or nurses) searching for health content and (3) users not seeking health advice. Several analyses are made focusing on discovering how users search and what they are most interested in. One possible outcome of our analysis is a classifier to infer user expertise, which was built. We show the results and analyse the feature set used to infer expertise. We conclude that medical experts are more persistent, interacting more with the search engine. Also, our study reveals that, conversely to what is stated in much of the literature, the main focus of users, both laypeople and professionals, is on disease rather than symptoms. The results of this article, especially through the classifier built, could be used to detect specific user groups and then adapt search results to the user group.

The proceedings from the ‘Multimodal Retrieval in the Medical Domain (MRMD) 2015’ workshop are now available online.

This book constitutes the proceedings of the First International Workshop on Multimodal Retrieval  in the Medical Domain, MRMD 2015, held in Vienna, Austria, on March 29, 2015. The workshop was held in connection with ECIR 2015.
The 14 full papers presented, including one invited paper, a workshop overview and five papers on the VISCERAL Retrieval  Benchmark, were carefully reviewed and selected from 18 submissions. The papers focus on the following topics: importance of data other than text for information retrieval; semantic data analysis; scalability approaches towards big data sets.

The project SLDESUTO-Box has now an information webpage in the following link: http://www.hevs.ch/fr/rad-instituts/institut-informatique-de-gestion/projets/sldesuto-box-10060

The purpose of SLDESUTO-BOX is to use unique technology and knowledge within image analysis and based on market demand, develop a Decision Support Toolbox (DST). The DTS will support the pathologists in their challenging task to diagnose and evaluate the prognosis of different types of cancer. The DST will consist of a variety of tools that will be based on learning models for image analysis, trained according to different sub-specialties within pathology. Furthermore, we will also build a reference database, enabling pathologist access to verified reference cases with known clinical outcome.

A workshop around the topic Evaluation as a Service and the reproducibility of scientific results is being organized by Henning Müller.

The workshop will include funding bodies, researchers and companies that provide the infrastructure and organize challenges, as well as scientist that have studied the scial aspects of challenges including participant motivation and incentivization.

More info can be found at the workshop webpage.

A Khresmoi project booth was present at ICT 2015 – Innovate, Connect, Transform, 20-22 October 2015 in Lisbon, Portugal, organised by the European Commission.

The SLDESUTO-BOX Eurostars sponsored Project kick-off meeting took place in Boston, USA. 

“The purpose of this project is to use unique technology and knowledge within image analysis and based on market demand, develop a Decision Support Toolbox (DST). The DTS will support the pathologists in their challenging task to diagnose and evaluate the prognosis of different types of cancer. The DST will consist of a variety of tools that will be based on learning models for image analysis, trained according to different sub-specialties within pathology. Furthermore, we will also build a reference database, enabling pathologist access to verified reference cases with known clinical outcome.”

More info can be found at the ContextVision webpage

The paper ‘Combining Unsupervised Feature Learning and Riesz Wavelets for Histopathology Image Representation: Application to Identifying Anaplastic Medulloblastoma’ by Sebastian Otálora et al. was presented at the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI2015 in Munich, Germany. 

This and other MedGIFT publications can be found at our publications page