Abstract:

The massive growth in applications of radiological imaging and image-guided treatments has become in a worldwide shortage of trained radiologists. Therefore, several computer-based radiology training environments which combine traditional learning opportunities with advanced e-learning platforms have recently been developed with the goal of supporting the acquisition of radiological expertise. However, the use of clinical experiences arises as the main issue to ensure the success for such learning environments when training radiologists to interpret mammograms.
In this sense, the MamoDB is a research web-based application which has been customized in order to incorporate learning capabilities for training and guidance of newly employed or resident radiologists. MamoDB allows panels of experts to collaborate at different hospitals and research centers by means of integrating a Picture Archiving and Communication System (PACS) to store the DICOM files as well as a database with the eXtended Markp Language (XML) files containing the experts’ annotation for each clinical case.

Learning methodology:
We propose the use of MamoDB as a part of the problem-based learning paradigm, which in fact is an innovative and challenging approach to medical education since it is a new way of using clinical material to help radiologists in their initial professional career. As in all learning tools, two steps are required: 1) the acquisition of the clinical knowledge, and 2) the learning strategy. The former is achieved by means of the annotations issued by a panel of expert radiologists (stored in the MamoDB database), and the latter is done during the radiologist training (i.e. analyzing the clinical cases and comparing the findings with the expert annotations). Note that this learning strategy is based on facilitating and supporting skills rather than providing specific directives. Such paradigm emphasizes the application of knowledge and skills to the solution of problems instead of just recalling the facts. Thus, stated that the training process for the radiologists should include a large number of cases with multiple benign and malignant findings, MamoDB allows to test and train the radiologists ability to:
- Detect a mammographic finding.
- Properly characterize the mammographic findings according to their location, shape, size, margins, density, number and distribution.
- Issue a diagnosis according to the detection, correct identification and characterization of the mammographic findings.

System architecture:
MamoDB has been designed as a web-based application within a Zend Apache server which is also used as a MySQL database server for data storage. The application links both the PACS and the XML servers which store the clinical cases (as DICOM and annotation files). All data transmissions between the users and the web server are encrypted in order to ensure the complete confidentiality of stored data. Queries to the MamoDB are performed through a webform and provides to the user with a list of clinical cases according to the query parameters, both including the image and the annotation files.

Conclusion:
The use of MamoDB as a web-based tool to get access to a large database of mammographic cases with annotations from several experts provides a helpful tool to train unexperienced radiologists. Currently, MamoDB is being used at 3 different hospitals in the catalan Health Area.