Medical Image Processor and Repository ( MIPAR) Benjamin Aribisala – Lagos State University - Nigeria (Benjamin.Aribisala@lasu.edu.ng)

Catania- July 2016 The e-Research Summer Hackfest was held at the Department of Physics and Astronomy, University of Catania, Italy the first edition on July, 4-15, 2016 and the second on July, 18-29, 2016 10 instructors and 36 participants from 9 countries (4 African and 5 European) attended the two editions co-sponsored by the SCI-GAIA, INDIGO-DataCloud and COST ENeL The focus of the Hackfest was to train participants on technologies that could help them put their tools on the web as services to users Participants were trained on the following tools – FutureGateway, gLibrary, Kepler, Invenio, OAI-PMH, OneData and Ophidia

Use Cases from Africa TANZANIA 2. NIGERIA 3. KENYA 4. SOUTH AFRICA Stephen Mgaya, Tanzania Education and Research Network, - Bioinformatics SG (WEKA Data mining tool) Aron Kondoro, University of Dar es Salaam , iGrid Portal Diana Rwegasira, University of Dar es Salaam, Technology Transfer Alliance Collaboration Platform Damas Makweba, Dar es Salaam Institute of Technology, The Weather Research and Forecasting (WRF) Model for the WIMEA-ICT project Triphonia Ngailo, Dar es Salaam Institute of Technology, The Weather Research and Forecasting (WRF) Model for the WIMEA-ICT project 2. NIGERIA Benjamin Aribsala, Lagos State University, Medical Image Analyser 3. KENYA Dennis Muoki Kimego, Egerton University, Public Health Gateway in Kenya Charles Muiruri Njaramba, Egerton University, Public Health Gateway in Kenya 4. SOUTH AFRICA David Risinamhodzi, Northwest University, Reproducible Automatic Speech Recognition workflows

Lagos Hackfest OBAFEMI AWOLOWO UNIVERSITY 2. COVENANT UNIVERSITY Segun Oyeyiola, A Near Real-Time Meterological Data Repository for Atmospheric Research in Africa 2. COVENANT UNIVERSITY Falola Damilare, Development of an interactive pipeline for Genome wide Association Mosaku Abayomi, IBIS, A Framework For the Interoprability of Bio-repository Information System Trust Odia, HPC for Large NGS Data: Microbial Diversity Analysis 3. UNIVERSITY OF IBADAN Olawale Olayide, Valorization of Open Data Archive and Documentation of Research Metadata 4. LAGOS STATE UNIVERSITY Oluwatoyin Enikuomehin, Web-Based Predictive Defuzzifier Olusola Olabanjo, MIPAR Extension 5. EDUCATION EDUCATIONAL RESEARCH NETWORK Yoseph Abate, Education Elibrary and Repository 6. FEDERAL UNIVERSITY OF AGRICULTURE, ABEOKUTA Olutayo Ajayi, An Adaptive e-Service Communication Model for Rural Agricultural Extension 7. UNIVERSITY OF NSUKKA Collins Udanor, Development of a SGW-Based Plant Tissue Culture Micropropagation Yield Forecasting Application, Plantisc2

Medical Image Processor and Repository

Background Medical images are images acquired from humans or animals Medical images are used for clinical diagnosis, treatment and patient management. There are many methods of acquiring medical images. Each method has specific use, strengths or weaknesses Medical Image analysis and computer vision provides a platform for developing computational techniques for converting the raw images to meaningful information.

Scientific Problem Some of the challenges in the field of medical image analysis Imaging equipment are very expensive Image acquisition is very expensive There are limited availability of medical image analysts in Africa Limited collaboration efforts and ability to share expertise amongst clinical experts The advancements in internet technology, data communication and reduction in hardware cost has led to the birth of Science Gateway Science Gateway can help in solving medical image analysis problems by offering tools for Creating of image repository Making image analysis tools available Making workflow available Adapting some of the tools to make them intelligent Science Gateway is in top gear in the developed world but very sluggish in Africa In particular, there is no platform for image analysis in Africa

Medical Image Processor and Repository Medical Image Processor and Repository (MIPAR) is an e-infrastructure for sharing and analyzing medical images The web address of MIPAR is https://mipar.sci-gaia.eu MIPAR is one of the products of the collaboration between Lagos State University and SCI-GAIA For More information, contact us at Benjamin.aribisala@lasu.edu.ng

When Can I Use MIPAR? You need MIPAR if you need medical images for your research have medical images to share have a case study to share need an expert to process your medical images How much will you pay for any of the services above? Everything is free I want to collaborate with your team Just send an email to Benjamin.aribisala@lasu.edu.ng

System Analysis and Design Donate Images Process Images Download outputs Download Free Images Registered user Analyze Images Image Types CT MRI Doppler Ultrasound Anatomy Brain Liver Lung Chest Image Format .hdr/.img .nii .nii.gz (.zip) Processes Brain Extraction Image Segmentation Image registration

System Requirements Software Tools Used for Development Futuregateway OAR PHP JSON WAMP Software Requirement for users Web browser Internet Windows operating system or mac Hardware Requirement for users Pentium 4, 4GB RAM, 500 GB disk space

Modules of MIPAR Registration Process Analyze Donate Images Download Images Process Images

Medical Image Processor and Repository Home Page https://mipar.sci-gaia.eu

Access through Federated Identity Choose catch-all if in doubt

Registration using Federated Identity

MIPAR – Image donation (https://mipar.sci-gaia.eu)

MIPAR – Image search & download

MIPAR – Image search & download & visualise

MIPAR – Image processing (brain extraction, segmentation, etc.)

MIPAR – Processed Images (e.g. brain extraction and segmentation)

Analyze Module Perform Regression Compute correlation Compare two groups within a dataset Compare two measurements within a dataset

Future Plans and Conclusions We are currently seeking funds to: publicize MIPAR get data into MIPAR MIPAR was tested with Brain MRI Data, we need to include other imaging modalities We also need to include other anatomies Catania Hackfest was very productive Opportunity to learn about Science gateway tools Gave Birth to MIPAR and to Lagos Hackfest With MIPAR you can share, process and analyse medical images Conclusions

The Team Appreciations A big appreciation to the co-funders - SCI-GAIA, INDIGO-DATACLOUD AND ENEL We appreciate Eko-Konnect and WACREN for establishing a link between Lagos State University and SCI-GAIA The Team Roberto Barbera, sci-gaia Simon Taylor, sci-gaia Benjamin Aribisala Bruce Becker, sci-gaia Olabanjo Olusola Mario Torris Rita Ricceri Riccardo Bruno