Content-Based Image Retrieval
The proceedings from the Medical Computer Vision 2016 workshop, from MICCAI2016 are now available online.
The goal of the MCV workshop is to explore the use of “big data” algorithms for harvesting, organizing and learning from large-scale medical imaging data sets and for general-purpose automatic understanding of medical images.
The BAMBI workshop aims to highlight the potential of using Bayesian or random field graphical models for advancing research in biomedical image analysis.
The NVIDIA GPU grant program awarded a Titan Xp to the MEGANE PRO project.
Hand amputations are highly impairing and can dramatically affect the capabilities people. Man-machine interfaces that can control hand prostheses have been developed, but natural control methods are still only rarely applied in real life. The requested GPU will allow us to develop this research field that has high scientific and social impact. The project includes the development of highly specific data classification and fusion algorithms based on convolutional and recurrent neural networks. The algorithms will allow to control a 3D printed prosthetic hand and/or a robotic hand simulator based on virtual reality in real time.
The paper “Classification of SD-OCT images using Deep learning approach” has been accepted for oral presentation at the IEEE International Conference on Signal and Image Processing Applications (IEEE ICSIPA) 2017.
The conference will take place from September 12-14, 2017 in Kuching, Malaysia.
The ICORR 2017 submission ‘Repeatability of grasp recognition for robotic hand prosthesis control based on sEMG data’ by Francesca Palermo et al. was selected for the Rehabweek Best poster completion.
The IEEE International Conference on Rehabilitation Robotics (ICORR) 2017 will take place from July 17-20 in London, UK.
Abstract
Control methods based on sEMG obtained promising results for hand prosthetics. Control system robustness is still often inadequate and does not allow the amputees to perform a large number of movements useful for everyday life. Only few studies analyzed the repeatability of sEMG classification of hand grasps. The main goals of this paper are to explore repeatability in sEMG data and to release a repeatability database with the recorded experiments. The data are recorded from 10 intact subjects repeating 7 grasps 12 times, twice a day for 5 days. The data are publicly available on the Ninapro web page. The analysis for the repeatability is based on the comparison of movement classification accuracy in several data acquisitions and for different subjects. The analysis is performed using mean absolute value and waveform length features and a Random Forest classifier. The accuracy obtained by training and testing on acquisitions at different times is on average 27.03% lower than training and testing on the same acquisition. The results obtained by training and testing on different acquisitions suggest that previous acquisitions can be used to train the classification algorithms. The inter-subject variability is remarkable, suggesting that specific characteristics of the subjects can affect repeatability and sEMG classification accuracy. In conclusion, the results of this paper can contribute to developing more robust control systems for hand prostheses, while the presented data allows researchers to test repeatability in further analyses.
The book ‘Cloud-based benchmarking of medical image analysis’ related to the VISCERAL project can now be accessed online
This book presents the VISCERAL project benchmarks for analysis and retrieval of 3D medical images (CT and MRI) on a large scale, which used an innovative cloud-based evaluation approach where the image data were stored centrally on a cloud infrastructure and participants placed their programs in virtual machines on the cloud. The book presents the points of view of both the organizers of the VISCERAL benchmarks and the participants.
The book is divided into five parts. Part I presents the cloud-based benchmarking and Evaluation-as-a-Service paradigm that the VISCERAL benchmarks used. Part II focuses on the datasets of medical images annotated with ground truth created in VISCERAL that continue to be available for research. It also covers the practical aspects of obtaining permission to use medical data and manually annotating 3D medical images efficiently and effectively. The VISCERAL benchmarks are described in Part III, including a presentation and analysis of metrics used in evaluation of medical image analysis and search. Lastly, Parts IV and V present reports by some of the participants in the VISCERAL benchmarks, with Part IV devoted to the anatomy benchmarks and Part V to the retrieval benchmark.
This book has two main audiences: the datasets as well as the segmentation and retrieval results are of most interest to medical imaging researchers, while eScience and computational science experts benefit from the insights into using the Evaluation-as-a-Service paradigm for evaluation and benchmarking on huge amounts of data.
Together with Dr. Cai and Dr. Song from University of Sydney, Adrien organized a tutorial on Biomedical Texture Analysis at ISBI 2017 in Melbourne. The slides of the talk are available here
Together with Dr. Cai and Dr. Song from University of Sydney, Adrien organized a tutorial on Biomedical Texture Analysis at ISBI 2017 in Melbourne. The slides of the talk are available here
The paper ‘An Object Recognition System in Scene Camera Data with Semi-Automatic Training Using Gaze Tracking and Accelerometers’ by Matteo Cognolato et al. was accepted for the International Conference on Computer Vision Systems (ICVS) 2017.
The conference will take place in Shenzen, China from July 10-13 2017.
The project ‘HT4D 2: Pulmonary Hypertension – Diagnosis and Etiologic Assessment using 4D Analysis of Dual Energy CT Images’ has been accepted by the Swiss National Science foundation.
The HESSO Medgift group together with the University Hospitals of Geneva (HUG) will continue with the work done in the original project PH4D.
The journal article ‘3D Solid Texture Classification Using Locally-Oriented Wavelet Transforms’ is now available under the ‘Early Access’ area in IEEEXplore.
The article will appear on the April issue of the IEEE Transactions on Image Processing journal.
Abstract:
The Chapter ‘Big data in medical imaging, forensics and beyond’ by Henning Müller has now been published in the book Forensigraphie – Möglichkeiten und Grenzen IT-gestützter klinisch-forensischer Bildgebung
Info
The paper ‘Making-sense of large data sets without annotations: analyzing age-related correlations from lung CT scans’ by Dicente et al. won the Robert F. Wagner Best student paper award for the track Imaging Informatics for Healthcare, Research and Applications.
The paper can be found in our publications page.
The paper ‘3-D Solid Texture Classification Using Locally-Oriented Wavelet Transforms’ by Dicente et al. has been accepted for publication at IEEE Transactions on Image Processing.
Abstract
Many image acquisition techniques used in biomedical imaging, material analysis, or structural geology are capable to acquire 3–D solid images. Computational analysis of these images is complex but necessary, since it is difficult for humans to visualize and quantify their detailed 3–D content. One of the most common methods to analyze 3–D data is to characterize the volumetric texture patterns. Texture analysis generally consists of encoding the local organization of image scales and directions, which can be extremely diverse in 3–D. Current state–of–the–art techniques face many challenges when working with 3–D solid texture, where most approaches are not able to consistently characterize both scale and directional information. 3–D Riesz–wavelets can deal with both properties. One key property of Riesz filterbanks is steerability, which can be used to locally align the filters and to compare textures with arbitrary (local) orientations. This paper compares three local alignment criteria for higher–order 3–D Riesz–wavelet transforms. The estimations of local texture orientations are based on higher–order extensions of regularized structure tensors. An experimental evaluation of the proposed methods for the classification of synthetic 3–D solid textures with alterations (e.g., rotations, noise) demonstrated the importance of local directional information for robust and accurate solid texture recognition. These alignment methods improved the accuracy of the unaligned Riesz descriptors by up to 0.63, from 0.32 to 0.95 over 1 in the rotated data, which are better than the other techniques tested on the same database.
The paper ‘Making Sense of Large Data Sets without Annotations:Analyzing Age-related Correlations from Lung CT Scans’ by Yashin Dicente et al. is one of the finalists for the Robert F. Wagner Best Student paper Award at SPIE2017. The conference will take place from the 11-16 February 2017 in Orlando, Florida, US.
Abstract:
The analysis of large data sets can help to gain knowledge about specic organs or on specic diseases, just as big data analysis does in many non-medical areas. This article aims to gain information from 3D volumes, so the visual content of lung CT scans of a large number of patients. In the case of the described data set, only little annotation is available on the patients that were all part of an ongoing screening program and besides age and gender no information on the patient and the ndings was available for this work. This is a scenario that can happen regularly as image data sets are produced and become available in increasingly large quantities but manual annotations are often not available and also clinical data such as text reports are often harder to share. We extracted a set of visual features from 12,414 CT scans of 9,348 patients that had CT scans of the lung taken in the context of a national lung screening program in Belarus. Lung elds were segmented by two segmentation algorithms and only cases where both algorithms were able to nd left and right lung and had a Dice coecient above 0.95 were analyzed. This assures that only segmentations of good quality were used to extract features of the lung. Patients ranged in age from 0 to 106 years. Data analysis shows that age can be predicted with a fairly high accuracy for persons under 15 years. Relatively good results were also obtained between 30 and 65
years where a steady trend is seen. For young adults and older people the results are not as good as variability is very high in these groups. Several visualizations of the data show the evolution patters of the lung texture, size and density with age. The experiments allow learning the evolution of the lung and the gained results show that even with limited meta{data we can extract interesting information from large{scale visual data. These age-related changes (for example of the lung volume, the density histogram of the tissue) can also be taken into account for the interpretation of new cases. The database used includes patients that had suspicions on a chest X-ray, so it is not a group of healthy people, and only tendencies and not a model of a healthy lung at a specic age can be derived.
Prof. Henning Müller is part of the Management Committe of the approved European Cooperation in Science and Technology (COST) action European network for translational research in children’s and adult interstitial lung disease
COST Actions are a flexible, fast, effective and efficient networking instrument for researchers, engineers and scholars to cooperate and coordinate nationally funded research activities. COST Actions allow European researchers to jointly develop their own ideas in any science and technology field.
Description
Interstitial lung disease in children (chILD) is a term that describes a collection of more than 200 rare lung disorders. It is a heterogeneous group of non-neoplastic disorders resulting from damage by varying patterns of inflammation and fibrosis with the interstitium as the primary site of injury. As with other orphan diseases, chILD data is lacking on the natural course, phenotypic variability, associations with genotype, and effectiveness of treatments. The disease course is very variable, and depending on more than just the underlying cause; for example, within a given family, the phenotypic variability of chILD such as surfactant protein C mutation is huge. The rarity of individual chILDs contributes to a lack of randomised control trial data on effectiveness of treatments. Management strategies derive from other diseases or are based on physicians experience and remain controversial.
This Action will create a pan-Europe-led network of multidisciplinary clinicians (adult and paediatric), scientists, and patients and their families with the aim of accurate and early diagnosis with structured, potentially personalised, management and therapies. The Action will stimulate and coordinate multidisciplinary research in chILD from infancy to adulthood, as well as reveal the pathophysiological commonalities between different forms ILD at the molecular level. The results of these efforts will create large incremental changes in understanding and management of chILD. Since chILD is an umbrella term for a number of conditions most of which imply more than purely medical or scientific expertise, the Action will pay due attention to the larger societal implications of chILD research.
Interstitial lung disease in children (chILD) is a term that describes a collection of more than 200 rare lung disorders. It is a heterogeneous group of non-neoplastic disorders resulting from damage by varying patterns of inflammation and fibrosis with the interstitium as the primary site of injury. As with other orphan diseases, chILD data is lacking on the natural course, phenotypic variability, associations with genotype, and effectiveness of treatments. The disease course is very variable, and depending on more than just the underlying cause; for example, within a given family, the phenotypic variability of chILD such as surfactant protein C mutation is huge. The rarity of individual chILDs contributes to a lack of randomised control trial data on effectiveness of treatments. Management strategies derive from other diseases or are based on physicians experience and remain controversial.
This Action will create a pan-Europe-led network of multidisciplinary clinicians (adult and paediatric), scientists, and patients and their families with the aim of accurate and early diagnosis with structured, potentially personalised, management and therapies. The Action will stimulate and coordinate multidisciplinary research in chILD from infancy to adulthood, as well as reveal the pathophysiological commonalities between different forms ILD at the molecular level. The results of these efforts will create large incremental changes in understanding and management of chILD. Since chILD is an umbrella term for a number of conditions most of which imply more than purely medical or scientific expertise, the Action will pay due attention to the larger societal implications of chILD research
The book ‘Cloud-Based Benchmarking of Medical Image Analysis’ by Allan Hanbury, Henning Müller and Georg Langs is now available at Springer.
This book presents the VISCERAL project benchmarks for analysis and retrieval of 3D medical images (CT and MRI) on a large scale, which used an innovative cloud-based evaluation approach where the image data were stored centrally on a cloud infrastructure and participants placed their programs in virtual machines on the cloud. The book presents the points of view of both the organizers of the VISCERAL benchmarks and the participants.
The book is divided into five parts. Part I presents the cloud-based benchmarking and Evaluation-as-a-Service paradigm that the VISCERAL benchmarks used. Part II focuses on the datasets of medical images annotated with ground truth created in VISCERAL that continue to be available for research. It also covers the practical aspects of obtaining permission to use medical data and manually annotating 3D medical images efficiently and effectively. The VISCERAL benchmarks are described in Part III, including a presentation and analysis of metrics used in evaluation of medical image analysis and search. Lastly, Parts IV and V present reports by some of the participants in the VISCERAL benchmarks, with Part IV devoted to the anatomy benchmarks and Part V to the retrieval benchmark.
This book has two main audiences: the datasets as well as the segmentation and retrieval results are of most interest to medical imaging researchers, while eScience and computational science experts benefit from the insights into using the Evaluation-as-a-Service paradigm for evaluation and benchmarking on huge amounts of data.
The papers ‘Making sense of large datasets without annotations: Analyzing age-related correlations from lung CT scans’ by Yashin Dicente Cid et al. and ‘Convolutional neural networks for an automatic classification of prostate tissue slides with high-grade Gleason score’ by Oscar Jimenez-del-Toro et al. were accepted for the SPIE Medical Imaging 2017 conference.
The conference will take place from the 11th-16th February 2017 in Orlando, Florida, United States
The article “Activity evaluation: a video-based approach to iterative prototype design” by Grace Eden et al. has now been added to the ACM Digital Library
It was originally published in the IHM ’16: Actes de la 28iéme conférence francophone sur l’Interaction Homme-Machine.
Abstract
Naturalistic prototype evaluation is an approach that can be used to assess a technology’s potential practical application in real-world settings and situations (its usefulness) and to evaluate the interface (its usability). This paper discusses our development of a novel prototype evaluation technique; the Activity Evaluation Framework (AEF). AEF is informed by a sociological orientation, Ethnomethodology and uses video in the analysis of participants’ ‘talk-in-interaction’ as they interact with technology. We discuss the use of AEF as a systematic and robust qualitative technique for the evaluation of both the usefulness and usability of prototypes.
Roger Schaer gave a demo presentation of the GoogleGlass and NinaPro projects at the Interaction Homme-Machine 2016 conference.
The conference took place from the 25-28 octobre 2016 at Fribourg, Switzerland.
