Medical image analysis, retrieval and evaluation infrastructures

Post on 22-Feb-2017

657 views 2 download

transcript

Medical image analysis, retrieval and evaluation infrastructures

Henning MüllerHES-SO VS &

Martinos Center

Overview

• Medical image retrieval projects• Image analysis and 3D texture modeling

• Data science evaluation infrastructures– ImageCLEF– VISCERAL– EaaS – Evaluation as a Service

• What comes next?

Henning Müller• Studies in medical informatics in

Heidelberg, Germany– Work in Portland, OR, USA

• PhD in image processing in Geneva,focus on image analysis and retrieval– Exchange at Monash Uni., Melbourne, Australia

• Prof titulaire at UNIGE/HUG in medicine (2014)– Medical image analysis and retrieval for decision

support• Professor at the HES-SO Valais (2007)

– Head of the eHealth unit• Sabbatical at the Martinos Center, Boston, MA

Medical image retrieval (history)

• MedGIFT project started in 2002– Global image similarity

• Texture, grey levels– Teaching files– Linking text files and

image similarity• Often data not available

– Medical data hard to get– Images and text are

connected in cases• Unrealistic expectations, high quality vs. browsing

– Semantic gap

Medical imaging is big data!!

• Much imaging data is produced• Imaging data is very complex

– And getting more complex• Imaging is essential for

diagnosis and treatment • Images out of their context

loose most of their sense– Clinical data are necessary– Diagnoses often not precise

• Evidence-based medicine & case-based reasoning

Decision support in medicine

• Mixing multilingual data from many resources and semantic information for medical retrieval– LinkedLifeData

The informed patient

Integrated interfaces

Texture analysis (2D->3D->4D)

• Describe various medical tissue types– Brain, lung, …– Concentration on 3D and 4D data– Mainly texture descriptors

• Extract visual features/signatures– Learned, so relation to deep learning

Adrien Depeursinge, Antonio Foncubierta–Rodriguez, Dimitri Van de Ville, and Henning Müller, Three–dimensional solid texture analysis and retrieval: review and opportunities, Medical Image Analysis, volume 18, number 1, pages 176-196, 2014.

Database with CT image of interstitial lung diseases

• 128 cases with CT image series and biopsy confirmed diagnosis

• Manually annotated regions for tissue classes (1946)– 6 tissue types of 13 with a larger number of examples

• 159 clinical parameters extracted (sparse)– Smoking history, age, gender,

hematocrit, …

• Available after signature of a license agreement

Learned 3D signatures

• Learn combinations of Riesz wavelets as digital signatures using SVMs (steerable filters)– Create signatures to detect small local lesions

and visualize them

Adrien Depeursinge, Antonio Foncubierta–Rodriguez, Dimitri Van de Ville, and Henning Müller, Rotation–covariant feature learning using steerable Riesz wavelets, IEEE Transactions on Image Processing, volume 23, number 2, page 898-908, 2014.

Learning Riesz in 3D

• Most medical tissues are naturally 3D• But modeling gets much more complex

– Vertical planes

– 3-D checkerboard

– 3-D wiggledcheckerboard

Aiding clinical decisions

• Benchmark on multimodal image retrieval– Run since 2003, medical task since 2004– Part of the Cross language evaluation forum

• Many tasks related to image retrieval– Image classification– Image-based retrieval– Case-based retrieval– Compound figure separation– Caption prediction– …

• Many old databases remain available, imageclef.org

Test

Resources available

Test DataTraining Data

Participants Organiser

Participant Virtual MachinesRegistration

System

Annotation Management System

Analysis System

Annotators (Radiologists)

Locally Installed Annotation Clients

Microsoft Azure Cloud

Test Data

Evaluation as a Service (EaaS)

• Moving the algorithms to the data not vice versa– Required when data are: very large, changing

quickly, confidential (medical, commercial, …)• Different approaches

– Source code submission, APIs, VMs local or in the cloud, Docker containers, specific frameworks

• Allows for continuous evaluation, component-based evaluation, total reproducibility, updates, …– Workshop March 2015 in Sierre on EaaS– Workshop November 2015 in Boston on cloud-

based evaluation

Sharing images, research data• Very important aspect of research is to have solid

methods, data, large if possible– If data not available, results can not be reproduced– If data are small, results may be meaningless

• Many multi-center projects spend most money on data acquisition, often delayed no time for analysis– IRB takes long, sometimes restrictions are strange

• Research is ineternational!• NIH & NCI are great to push data availability

– But data can be made available in an unusable way

Political support for research infrastructures!

Sustaining biomedical big data

Microsoft Azure

Intels CCC

Institutional support (NCI)

• Using crowdsourcing to link researcher and challenges

Business models for these links• Manually annotate large data sets for challenges

– Data needs to be available in a secure space• Have researcher work on data (on infrastructure)

– Deliver code• Commercialize results and share benefits

Future of research infrastructures• Much more centered around data!!

– Nature Scientific Data underlines the importance!• Data need to be available but in a meaningful way

– Infrastructure needs to be available and way to evaluate on the data with specific tasks

• More work for data preparation but in line with IRB– Analysis inside medical insitutions

• Code will become even more portable– Docker helps enormously and develops quickly

• Public private partnerships to be sustainable• Total reproducibility, long term, sharing tools

• Much higher efficiency

• Part of QIN – Quantitative Imaging Network (NCI)• Create challenges for QIN to validate tools• Use Codalab to run project challenges

– Run code in containers (Docker), well integrated• Automate as much as possible

– Share code blocks across teams, evaluatecombinations

Conclusions

• Medicine is (becoming) digital medicine– More data and more complex links (genes, visual,

signals, …)• Medical data science requires new infrastructures

– Use routine data, not manually extracted, curateddata, curate large scale, accommodate for errors

– Use large data sets from data warehouses– Keep data where they are produced

• More “local” computation, so where data are– Secure aggregation of results

• Sharing infrastructures, data and more

Contact

• More information can be found at – http://khresmoi.eu/– http://visceral.eu/– http://medgift.hevs.ch/– http://publications.hevs.ch/

• Contact:– Henning.mueller@hevs.ch