Henning Müller is currently a visiting professor at the Martinos Center, Harvard Medical School: https://www.nmr.mgh.harvard.edu/
Prof. Müller’s publications can be found at our publications page.
Program for Biomedical Texture Analysis tutorial at MICCAI 2015 online
The program of our tutorial Biomedical Texture Analysis (BTA) at MICCAI 2015 is now online: https://sites.google.com/site/btamiccai2015/.
We have already 48 registrants and you can still register on https://www.events.tum.de/frontend/index.php?page_id=382
Google Glass for paramedics presented in Valais festivities
The project Google Glass for Paramedics was presented by Antoine Widmer to the Swiss Federal Councillor Johann Schneider-Ammann during the festivities for the Valais canton bicentenary.
The stand from The Ark was part of the ‘Valais technologique’ presentation in the presence also of the President of the Valais government Jacques Melly.
Medical Image Retrieval paper now published in Cancer Informatics journal
The paper ‘Medical Image Retrieval: A Multimodal Approach’ has now been published in Cancer Informatics: http://www.la-press.com/medical-image-retrieval-a-multimodal-approach-article-a4957-abstract?article_id=4957. The authors of the paper are Yu Cao, Shawn Steffey, Jianbiao He, Degui Xiao, Cui Tao, Ping Chen and Henning Müller.
Abstract
Medical imaging is becoming a vital component of war on cancer. Tremendous amounts of medical image data are captured and recorded in a digital format during cancer care and cancer research. Facing such an unprecedented volume of image data with heterogeneous image modalities, it is necessary to develop effective and efficient content-based medical image retrieval systems for cancer clinical practice and research. While substantial progress has been made in different areas of content-based image retrieval (CBIR) research, direct applications of existing CBIR techniques to the medical images produced unsatisfactory results, because of the unique characteristics of medical images. In this paper, we develop a new multimodal medical image retrieval approach based on the recent advances in the statistical graphic model and deep learning. Specifically, we first investigate a new extended probabilistic Latent Semantic Analysis model to integrate the visual and textual information from medical images to bridge the semantic gap. We then develop a new deep Boltzmann machine-based multimodal learning model to learn the joint density model from multimodal information in order to derive the missing modality. Experimental results with large volume of real-world medical images have shown that our new approach is a promising solution for the next-generation medical imaging indexing and retrieval system.
Eurostars project with Contextvision has been accepted
Eurostars project with Contextvision has been accepted with an overall budget of 1.3 Mio and 580’000 euros for the MedGIFT group.
Other MedGIFT projects can be found here.
VISCERAL project video available online
The video ‘The VISCERAL Project: Helping Structuring Medical Imaging Data’ can be seen at https://vimeo.com/129685434
The project’s goals and insight comments are addressed in the video. To know more about the project go to http://www.visceral.eu
MICCAI accepted paper obtained Student Travel Award
The paper ‘Anaplastic Medulloblastoma tumor differentiation by combining Unsupervised Feature Learning and Riesz wavelets for histopathology image representation’ by Sebastian Otálora et al. accepted at MICCAI 2015, was selected for the Student Travel Award.
This work was performed under the supervision of Henning Müller, Adrien Depeursinge and Manfredo Atzori.
Henning Müller presentation at DICOM meeting
Prof. Henning Müller presented at the KIS-RIS-PACS und DICOM-TREFFEN in Mainz, Germany the 18 june 2015.
The title of his talk was ‘Bildanalyse und Datenauswertung für die Forschung’.
Medical grids paper now available online
The paper ‘A review of medical grids and their direction – A Swiss/Japanese perspective’ by Toshiharu Nakai, Henning Müller et al. is now available online.
The workshop paper from the International Journal of Research Studies in Computing is available here: http://consortiacademia.org/10-5861ijrsc-2015-1109/
Abstract
This paper presents a general and comparative review of the advances of grid technologies in medical sciences since 2000, with a special emphasis on Europe and Japan. The EU has over the years funded several big projects in the Grid and now the cloud area, covering besides the high energy physics domain also bioinformatics and medical applications as in image analysis. Bioinformatics and pharmaceutical design have been the major targets of grid applications in Japan. Grids and clouds share many of the same goals and techniques, although clouds are more commercially oriented and privately provided services and grids are rather publicly initiated resource sharing platforms between institutions without strong economic objectives. In the future, merging these two may potentially solve inter-operation problems of grids, which have been limiting the propagation of biomedical grids.
Adrien Depeursinge invited talk at GdR ISIS in Paris
Prof. Adrien Depeursinge will give an invited talk at the GdR Information Signal Image Vision (ISIS) meeting in Paris.
The meeting will take place the 23 and 24 june 2015 at the Université Paris-Descartes, Paris, France. The title of the ‘Texture-Based Computational Models of Tissue in Biomedical Images: Initial Experience With Digital Histopathology’
Paper on feature learning and texture in histopathology images accepted at MICCAI2015
The paper ‘Anaplastic Medulloblastoma tumor differentiation by combining Unsupervised Feature Learning and Riesz wavelets for histopathology image representation’ by Sebastian Otálora et al. was accepted at the 18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015.
The conference will take place from October 5th to 9th 2015 in Munich Germany.
This and other publications can be found at our Publications webpage.
Two new journal papers now available online
The paper ‘User-oriented evaluation of a medical image retrieval system for radiologists’ by Dimitrios Markonis et al. can now be found online at: http://www.sciencedirect.com/science/article/pii/S1386505615000829
The paper ‘Comparing image search behaviour in the ARRS GoldMiner search engine and a clinical PACS/RIS’ by Maria De-Arteaga et al. can now be found online at: http://www.sciencedirect.com/science/article/pii/S1532046415000878. You can access this paper free for a limited time in the following link: http://authors.elsevier.com/a/1R9v05SMDQM7Kk
All MedGIFT publications can be found at our publication webpage.
Four papers accepted at EMBC2015
Four papers from the medGIFT group were accepted at the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2015. The conference will take place in Milan, Italy August 25-29 2015.
The accepted papers are the following:
- Manfredo Atzori and Henning Müller, The Ninapro database: a Resource for sEMG Naturally Controlled Robotic Hand Prosthetics
- Manfredo Atzori, Anne-Gabrielle Mittaz Hager, Simone Elsig, Giorgio Giatsidis, Franco Bassetto and Henning Müller, Effects of Prosthesis Use on the Capability to Control Myoelectric Robotic Prosthetic Hands
- Pol Cirujeda, Henning Müller, Daniel Rubin, Todd Aguilera, Billy W Loo, Maximilian Diehn, Xavier Binefa, Adrien Depeursinge, 3D Riesz-wavelet based Covariance descriptors for texture classification of lung nodule tissue in CT
- Roger Schaer, Fanny Salamin, Oscar Alfonso Jiménez del Toro, Henning Müller and Antoine Widmer, Live ECG Readings using Google Glass in Emergency Situations
AuntMinnieEurope published article focused on the Khresmoi system
The article ‘Specialist imaging search tool shows promise‘ published by the website AuntMinnieEurope refered to the Khresmoi system and its ‘high degree of accuracy for finding images and cases’.
The complete article can be found here.
Adrien Depeursinge is co-organizing a tutorial at MICCAI 2015 on Biomedical Texture Analysis
Adrien Depeursinge is co-organizing a tutorial at MICCAI 2015 on Biomedical Texture Analysis with J Ross Mitchell from Mayo Clinic. The tutorial will take place October 5th, in Munich, Germany.
Here is the outline of the tutorial:
Texture-based imaging biomarkers complement focal, invasive biopsy based biomarkers by providing information on tissue structure over broad regions, non-invasively, and repeatedly across multiple time points. Texture has been used to predict patient survival, tissue function, disease subtypes and genomics (imagenomics and radiogenomics). Nevertheless, several challenges remain, such as: the lack of an appropriate framework for multi-scale, multi-spectral analysis in 2D and 3D; localization of the uncertainty of texture operators; validation; and, translation to routine clinical applications.
Henning Müller participates in a discussion on medical apps
Prof. Henning Müller participated in the discussion ‘Health Apps – Opportunity or Risk?’ from santemedia.ch:
Health Apps – Opportunity or Risk?
04/23/2015
Health Apps and Wearables manage their own health and affect the behavior of the users. The interest in health data is large. What happens to own data, users do not usually know. Who determines who is allowed to see or use the data? Are there guidelines for providers? What users need to pay attention to health apps? What is happening to our health?
Staying with David Staudenmann are next to Dr. med. Urs Stoffel, Member of Corporate Executive Medical Association FMH Prof. Henning Müller, e-health expert and FH lecturer Institute of computer science, HES-SO Valais Wallis and Dr. iur. Michael Isler, lawyer, Walder Wyss AZurich.
‘Health apps and wearables manage personal health and affect the behavior of the users. The interest in health data is large. Users usually don’t know what happens to their data. Who determines who is allowed to see or use the data? Are there guidelines for providers? What users need to pay attention in health apps? What is happening to our health service?
Staying with David Staudenmann are next to Dr. med. Urs Stoffel, Member of Corporate Executive Medical Association FMH Prof. Henning Müller, e-health expert and FH lecturer at the Institute of computer science, HES-SO Valais Wallis and Dr. iur. Michael Isler, lawyer, Walder Wyss AG Zurich.’
Three medGIFT papers presented at ISBI 2015
The medGIFT group was present in this year’s International Symposium on Biomedical Imaging (ISBI): From Nano to Macro 2015 in New York, USA. The symposium took place from the 16 to 19 April 2015.
The poster ‘Optimal wavelet bandwidth for rotation-covariant texture analysis of lung tissue in 3-D CT: Classification of usual interstitial pneumonia’ by Adrien Depeursinge et al. was presented during the ISBI poster session.
Two papers were presented at the VISCERAL Grand Challenge workshop: ‘Efficient and fully automatic segmentation of the lungs in CT volumes’ by Yashin Dicente Cid et al. and ‘Hierarchic Anatomical Structure Segmentation Guided by Spatial Correlations (AnatSeg-Gspac): VISCERAL Anatomy3’ by Oscar A. Jiménez del Toro et al.
Two medical case-based retrieval papers presented at MRMD 2015
The MedGIFT group presented two papers at the Multimodal Retrieval in the Medical Domain (MRMD) 2015 workshop. The workshop was held as part of the 37th European Conference on Information Retrieval (ECIR) 2015 in Vienna, Austria the 29th March 2015.
The presented papers are:
- ‘Using Semi–Supervised Learning for Image Modality Classification as a Filter for Medical Case Retrieval’ by Alba García Seco de Herrera et al.
- ‘RadLex terms and local texture features for medical multimodal similar case retrieval’ by Oscar A. Jiménez del Toro et al.
eHealth group and projects highlighted in Valais radio station
The Radio Rottu Oberwallis station interviewed Prof. Henning Müller and Ivan Eggel and published the note in their website: http://www.rro.ch/cms/das-institut-wirtschaftsinformatik-an-der-hes-so-valais-wallis-beteiligt-sich-an-anwendungsorientierten-forschungsprojekten-so-auch-im-gesundheitsbereich-77526
Shangri-La demo available online
Shangri-La is a web-based interface for medical case-based retrieval.
The web interface can be accessed in the link http://shangrila.khresmoi.eu/