FAQ

Our FAQs are that nifty sections of our projects where we will find answers to recurring the project questions. For our BreastScreening (FAQ), MIDA (FAQ) and MIMBCD-UI (FAQ) projects, they guide us to perform common actions, such as typical configurations or fixing some issues. Please, follow the respective FAQ for each project, as it may have different Questions/Answers.

Index

• Datasets

• FAQ

• Prototypes

Medical Imaging

Medical Imaging refers to several different technologies that are used to view the human body in order to diagnose, monitor, or treat medical conditions. The number of applications of these technologies for detecting disease in various organs continues to expand, including breast tumors and assessing the effects of disruption agents on cancer tumors.

What format did we choose for this project?

For all BreastScreening, MIDA and MIMBCD-UI projects, we choose the .dcm extension format for our medical images. The extension means that we are using the DICOM format that is a slightly unique format as it does not only store the image pixel data (as a special attributes) but also Datasets, which are made up of attributes. These Datasets contain critical information that must be kept within the file to ensure they are never separated from each other.

What does DICOM means?

DICOM stands for Digital Imaging and Communications in Medicine and is a worldwide standard that defines how to store, exchange and transmit medical images. For instance, image devices including: (i) X-Rays, e.g., MammoGraphy (MG); (ii) UltraSound (US); and (iii) Magnetic Resonance Imaging (MRI); utilize this standard and are the three modalities used by these projects. The standard (originally named ACR/NEMA 300) was created to serve the purpose of medical practitioners that wanted to decode images in order to dose-plan for radiation therapy. The standard was not perfect from the get-go.

Digital Imaging and Communications in Medicine (DICOM) is a standard for handling, storing, printing, and transmitting information in medical imaging. It includes a file format definition and a network communications protocol. The communication protocol is an application protocol that uses TCP/IP to communicate between systems.

Hu, Zhanli, Hairong Zheng, and Jianbao Gui. "A novel interactive image processing approach for DICOM medical image data." 2009 2nd International Conference on Biomedical Engineering and Informatics. IEEE, 2009.

How to get the project's medical images?

We have two ways to download, or access, our available medical images:

1. Cloning the dataset-dicom-images repository to a local machine;

2. Following the Orthanc Book of the Downloading images section;

How to clone the dataset-dicom-images repository?

1.1. Clone the project repository:

git clone git@github.com:BreastScreening/dataset-dicom-images.git

1.2. Go inside the project folder:

cd dataset-dicom-images/

How to download via Orthanc Book solution?

Follow this example of our own project:

curl http://breastscreening.isr.tecnico.ulisboa.pt:8042/instances/84c8a18c-f915cb76-25281dec-844c3480-c5a75279/file > Instance.dcm

Datasets

Our datasets are a collection of data regarding several breast information acquired from patients of the Hospital Fernando Fonseca (HFF), a Portuguese (EU) health institution. By working next to the Medical Imaging Department of HFF we achieve a highly complete and important list of Datasets, which we can work now supporting our Machine Learning algorithms, a well-known topic related to Artificial Intelligence.

Where to start knowing about how to manipulate the project's datasets?

We have two sources of information that are important to start understanding how query our datasets' information. Start from the Technical Wiki of the dataset-mamo-patients repository and then jump to the other Technical Wiki of the finders-datasets repository. That might help you with this.