The SICAS Medical Image Repository

The SICAS Medical Image Repository is the place for you to store medical research data.

Join Demo

ISLES 2017 CHALLENGE

The ISLES challenge is a medical image segmentation challenge with the aim to compare different methods for ischemic stroke lesion segmentation from multi-spectral MRI images. ISLES is part of MICCAI 2017 conference!

Take me to the ISLES challenge

Brain Tumor Image Segmentation Challenge

Segmentation of brain tumors is a critical step in treatment planning and evaluation of response to therapy. It is also one of the most challenging tasks in medical image analysis, due to the variable shape and heterogeneity of such tumors. Multicenter data will be used for segmentation of four tumor subregions, while inter-reader agreement from clinicians will be used as a benchmark for comparing the algorithm.

Take me to the BRATS challenge

mTOP 2016

Welcome to the Mild Traumatic Brain Injury Outcome Prediction (mTOP) challenge. Its aim is to create a common ground to compare methods to find predictive MRI features, which help to characterise and distinguish mild traumatic brain injury patients from each other and healthy subjects.

Take me to the mTOP 2016 page

SHAPE 2015 Challenge

Obtain a set of 47 training liver data as binary images and a set of 10 triangle meshes of partial liver shapes. The goal of the challenge is to obtain the best possible reconstruction (shape completion) for the 10 given partial livers.

Take me to the SHAPE challenge

Visceral.eu Anatomy Benchmark

The Benchmark tasks will be organ identification and the segmentation of bones, inner organ and relevant substructures. The VSD-SMIR is hosting the benchmark data.

Take me to the VISCERAL page

Computational Horizons In Cancer (CHIC)

Developing Meta- and Hyper-Multiscale Models and Repositories for In Silico Oncology: After passing through the de-identification and (pseudo)-anonymization processes all the relevant medical data including imaging, clinical, histological and gentetic data for each patient will be hosted by the clinical data repository.

CHI-EU page

Features

Flexible Structure

The datasets are presented in a searchable list instead of predefined project structure.

Semantic Search

Use the semantic search to find datasets you need.

Organize and Sharing

Create folders and produce a data structure you like. Share it and collaborate.

Controlled Access

Choose the access level for each dataset individually.

Application Ready

Use the full featured API to connect to the repository from your software.

Standard File Formats

DICOM, ITK images, CDISC, STL, Statismo and ontology based meta-data.

Recommended by

Scientific Data

Scientific Data is an open-access, online-only publication for descriptions of scientifically valuable datasets

PLOS

List of the biological repositories and standards recommended by the PLOS publishing group journals

bioCADDIE

Offers a joint publisher-curated list of appropriate data deposition repositories in the field of life sciences

Our Competences

Storing medical image data requires special knowledge. SICAS offers a unique combination of competence in acquiring and storing medical images, in processing and visualising data for research and applications in medicine.

Anonymisation

Anonymisation of patient information and image features like face soft tissue.

Data Storage

Certified, efficient, and innovative data center based in Switzerland.

Research expertise

Sound expertise and broad experience in research support and collaboration management.

Acquisition

Acquisition of high quality image data and curation by experts.

Controlled

Controlled distribution of medical image data.

Anatomy

Anatomy based search to find the correct images.

Get Started

With the Website

Upload

Go the to the Upload Page and add a dataset to the upload queue

View

Unpublished Data

After upload, your dataset is listed on the unpublished page

View

Modifiy Meta-Data

Add value to your data by adding meta-data

View

Publish

Follow the steps and set meta-info, permission and related data to publish the data

View

Published Data

After uploading and publishing your dataset is listed on the published data page

View

Search For Data

Use -Symbol (@Body) to find anatomical structures

View

Organize by Folder

Copy data into your folder structure

View

Download a Folder

Select the folder to retrieve your collected data

View

With the API

Please consider developing on the demo (https://demo.smir.ch) server before you interact with the live system.

API Reference Python 3 API Connector Scala (JAVA) API Connector

Chunked file upload

Python code

## import libs
from pathlib import Path
from vsdConnect import connect
## connect to demo
api = connect.VSDConnecter()
## define filepath
fp = Path('C:' + os.sep, 'test', 'test.nii')
## Define chunk size to eg. 8 MB if you dont want to use the default 4MB
chunk = 1024 * 4096 * 2
## upload using the chunkFileUpload
obj = api.chunkFileUpload(fp, chunksize = chunk)
## print the selfUrl of the generated object
print(obj.selfUrl)

Console output

uploading part 1 of 3
uploaded part 1 of 3
uploading part 2 of 3
uploaded part 2 of 3
uploading part 3 of 3
uploaded part 3 of 3
https://demo.smir.ch/api/objects/1

Download a folder

Python code

from pathlib import Path
from vsdConnect import connect

# connect to the demo API
api = connectVSD.VSDConnecter()
## search for the test folder and retrieve the folder object
folder = api.getFolderByName('One')
for obje in folder.containedObjects:
    ## get each object in the folder
    obj = api.getObject(obje.selfUrl)
    ## Download directory
    home_dir = Path('/Home/User/Downloads')
    obj.download(api, working_dir=home_dir,)

The SICAS Medical Image Repository