MedSeg

We ❤️ innovation in radiology.
MedSeg is a free online segmentation tool with AI.

Why MedSeg


MedSeg allows free and simple volume segmentation of organs, tissue and pathologies in radiological images. You can segment the images manually, or let our AI models do it for you.

Web-based

No installation needed. Runs locally, so patient data does not need to leave the computer. Works best with Google Chrome on a GPU-powered computer.

User-friendly

Easy-to-use tool for segmentation of radiology images with modern AI-based segmentation algorithms. Gaming and radiology-inspired controls.

Fast

Written in "vanilla JavaScript" for speed optimization. GPU hardware acceleration through Canvas and WebGL.

Launch MedSeg

Other Services


Segmentation service

We offer request-based radiologist-validated segmentations of CT or MRI datasets for a price. With modern and custom AI models, we can annotate precisely and effectively. The result can be masks, volumes or 3D models/meshes of any file format.

Research

We are very open to research collaboration. To facilitate research in this field, we are creating open-access segmentations whenever we find the time.

Learn More

Training AI-models

You can contribute by letting us train models on your data. These models would be shared with everyone in MedSeg. Another way to contribute is to do segmentations and help us grow the open-access database.

Database


External databases


Datasets available for download

Datasets available for download

Here follows a list of image sources that are open and available for commercial use. These are well suited for AI-model development and sharing of segmentations. Please read the licencing details at the source. If you are interested in converting Jpgs/PNGs or similar images back into radiological images you can follow our method here: shorturl.at/kqLM7 

General databases

NameTypeContentLicenceDownload
CTs, MRIs
10 various datasets with segmentations
CC-BY-SA 4.0
Various, mostly MRI Head
400 different neuro datasets
Various, please check. Primarily CC0
MosMedCTs1110 COVID-19 cases, 50 cases with segmentationsCC BY-NC-ND 3.0
Here
(Register to obtain link)
Heart MRIs
45 Cine-MRIs with segmentations
Brain MRIs
Several datasets, one with 20 normal subjects
Free For Non-Commercial Use Only
CT Head
491 Head bleed scans
MRI Head
110 cases of healthy volunteers

Attribution wanted

CT Head
35 cases with head bleed
CT/MRI Abdomen
40 CT-cases where 20 has segmentations. 
40 MRI-cases where 20 has segmentations.
Test set here
Train set  here.
CTs
48 Head and neck CTs
No licence given 

Attribution wanted

CTs
40 Computed Tomography Pulmonary Angiograms (CTPA)
Research only.

Attribution wanted

Read More

TCIA

Very useful source with large collection of various cancer types and modalities. To download the images you need to install the NBIA Data retriever. See the installation guide here: shorturl.at/fvEVX

Name
Image type
Content
Licence
Download
Abdominal
Stomach Adenocarcinoma
CTs46 cases with clinical data, tissue images and moreCC BY 3.0 Attribution needed
Here
Colon adenocarcinoma
CTs32 cases with clinical data, tissue images and more
CC BY 3.0 Attribution needed
Here
Rectum Adenocarcinoma
CTs/MRIs4 cases with clinical data, tissue images and moreCC BY 3.0 Attribution needed
Here
CT ColongraphyCTs825 cases with metadata and descriptions of findingsCC BY 3.0 Attribution needed
Here
Stomach adenocarcinomaCTs308 cases with clinical data, tissue images and moreCC BY 3.0 Attribution neededHere
Pancreas CTCTs82 cases with segmentationsCC BY 3.0 Attribution neededHere
Pancreatic Ductal Adenocarcinoma
Various640 cases with clinical data and tissue imagesCC BY 3.0 Attribution needed
Here
Rectum Adenocarcinoma
CTs/MRIs4 cases with clinical data, tissue images and moreCC BY 3.0 Attribution needed
Here
Esophageal Carcinoma
CTs17 cases with clinical data, tissue images and more
CC BY 3.0 Attribution needed
Here
CT abdominal lymph nodesCT176 cases with segmentationsCC BY 3.0 Attribution needed
Here
Thorax and ENT
Lung Image Database
Various, many CTs
1308 cases with segmentations and much more informationHere
Lung adenocarcinomaCTs624 cases with clinical data, tissue images and moreCC BY 3.0 Attribution needed
Here
Thyroid cancer
CTs/PET-CTs
7 cases with clinical data, tissue images and moreCC BY 3.0 Attribution needed
Here
Genitourinary system
Uterine Corpus Endometrial Carcinoma
Various105 cases with tissue images and clinical dataCC BY 3.0 Attribution needed
Here
Clear Cell Renal Cell Carcinoma
Various82 cases with clinical data,  tissue images and moreCC BY 3.0 Attribution needed
Here
NaF ProstatePET/CT44 cases with metadataCC BY 3.0 Attribution needed
Here
Papillary Renal Cell Carcinoma
Various276 cases with clinical data, tissue images and more
CC BY 3.0 Attribution needed
Here
Ovarian CancerCTs332 cases with clinical, tissue images and more
CC BY 3.0 Attribution needed
Here
Kidney Renal Clear Cell CarcinomaVarious439 cases with clinical data, tissue images and moreCC BY 3.0 Attribution neededHere
Urothelial Bladder CarcinomaVarious192 cases with clinical data, tissue images and moreCC BY 3.0 Attribution neededHere
Uterine Corpus Endometrial CarcinomaVarious226 cases with clinical data, tissue images and moreCC BY 3.0 Attribution neededHere
Cervical Squamous Cell Carcinoma and Endocervical AdenocarcinomaMRIs57 cases with clinical data, tissue images and moreCC BY 3.0 Attribution neededHere
Prostate Adenocarcinoma
Various20 cases with clinical data, tissue images and moreCC BY 3.0 Attribution needed
Here
PROSTATEx Challenges
MRIs349 cases with k-trans imagesCC BY 3.0 Attribution neededHere
Neuro and miscellaneous
Lowgrade glioma
MRIs224 cases with clinical data, tissue images and moreCC BY 3.0 Attribution needed
Here
SarcomasVarious6 cases with clinical data, tissue images and moreCC BY 3.0 Attribution neededHere


Read More

Get in touch with us

COVID-19


COVID-19 CT segmentation dataset

Still available at our old site, find it here.
COVID-19

About


Segmentation in radiology
Segmentation of radiological images is important in many fields. Volumetry, visualization including VR/AR, 3D printing, radiotherapy, (co-)registration, and many other post-processing tools are some examples that often rely on segmentation.
Unfortunately, segmentation is still generally regarded as laborious and uninteresting by many. However recent progress in the field of computer vision has enabled the use of AI for both automated and interactive segmentation. For radiology, we hope that these new developments will hasten broad clinical adoption of volumetry to replace the subjective ruler-based distance measurements that are still the current clinical standard.

About us and our vision
We are two radiologists based in Oslo, Norway who crave more AI-enhancement in our daily practice. It is our belief that AI-based segmentation is technologically ready for broad clinical implementation. Although MedSeg is not meant for direct clinical use, we hope that it, together with our open-access segmentation database, will facilitate faster development of clinically validated models. Radiological segmentation should be simple, fun and accessible for everyone.

We are proud that MedSeg is beginning to be used by several research projects and we ourselves find it increasingly useful for effective high quality segmentation. If you are a radiologist, we hope that you share our vision and would consider helping us with annotating more data (CT and MRI). This data is made freely available so that anyone can download and develop tools that we believe can enhance radiology in general. If you are interested, please get in touch with us. We can provide openly accessible data that can be used for this purpose.

MedSeg is based on the following openly available tools and resources:
DICOM reader: https://github.com/rii-mango/Daikon
Nifti reader: https://github.com/rii-mango/NIFTI-Reader-JS
Deep learning (DL) in browser: https://www.tensorflow.org/js
Development of DL models: https://keras.io/ + https://www.tensorflow.org/
DeepGrow module: https://arxiv.org/abs/1903.08205
Ideas and experience from a Python-based segmentation tool with AI-capabilities. RILContour: https://link.springer.com/article/10.1007/s10278-019-00232-0
Another great advanced application with many post-processing tools, 3D Slicer: https://www.slicer.org/
Overview of web-based DICOM viewers: https://medevel.com/14-best-browser-web-based-dicom-viewers-projects/

Team


Tomas Sakinis

C.E.O.

Co-founder, developer. Radiologist.

Håvard Bjørke Jenssen

Deputy C.E.O.

Co-founder. In charge of business relations. Radiologist.

Forum


Visit our forum for FAQ, feedback and other useful information
Forum