Friday, December 20, 2013
Friday, December 6, 2013
Radiology currently is primarily concerned with pattern recognition with some linear measurments. Therefore, the demand for quantitative tools is little in radiology. Residents should be trained in using 3d software and planning during their regular rotations. To determine the correct measurements validation datasets are needed. What is required:
1. Better tools to create measurements are required with integration into the PACS to integrate into the regular workflow.
2. Better tools for representing the results (DICOM SR and AIM are available but adoption by vendors is slow).
4. Validation datasets. How to use existing tools and how not to mis-use them.
The main immediate informatics challenge is that the workflow for 3D postprocessing is poor.
QIBA is trying to streamline the process of obtaining quantitative imaging biomarkers. Using standards is a prerequisite in this effort.
Wednesday, December 4, 2013
The RSNA Image Share Network: 20 Month Follow-up Results from a Pilot SiteAn interesting presentation covered automatic rule-based deletion of data in PACS. Based on regulations and actual measurement of the use of older data (retrievel of data >1 yo was less then 5%) they deviced rule based deletion to free up space in PACS and reused the free space. This avoids vast growth of the PACS database and saves money in the long run.
Strategies for Foreign Study Ingestion by a PACS Interfaced to a XDS Affinity Domain
Quebec (canada) has a regional XDS environment connecting all hospitals and clinics with a single registry for the whole province. There are three repositories with multiple hospitals pushing data to each of the repositories. The repositories take care of the central registration in the registry.
Problem they ran into was the lack of XDS-I consumer support by the PACS providers. Each hospital is fitted by a proxy which queries the registry and get the images from the repository. Subsequently data coercion (pat ID and acc nr correction) is performed and data stored in local PACS.
From the second presentation in this session the most usefull tools were:
Glassboard for a dedicated group to share information. It's a private form of Facebook with groups on invitation only. All communication stays within the private group.
Pdfpen scan+ allows taking a picture of a piece of text and it does OCR on it to use it on you device.
Collecting bookmarks to websites into your pocket for later acces on any device.
- PDF readers
Examples are GoodReader, iAnnotate PDF, expert PDF. They allow reading and annotation of different files. However, they all are paid apps.
- Educational tools
Audience response apps are Poll everywhere (over 40 respondents requires a monthly payment), Poll runner ($10 per year), socrative (free and easy to use but a bit simple compared to others)
Baiboard collaborative whiteboard allowing multiple users that can join a board.
- technology tools
Editorially.com is a website to cooperate on writing a paper. It includes a full version tracking. This is a free tool.
Udutu online course authoring tool. Pre designed course templates can be used to design and share courses. Sharing either by webpage or by building a zip.
Udemy has a simpler GUI with less style which is also free to use.
Dropbox alternatives that can be used are Spideroak. Drawback is that it does not provide sharing. However, the data security level is higher than when using dropbox.
Tuesday, December 3, 2013
RSNA 2013 - RC326 - Quantitative Imaging: A Revolution in Evolution (In Association with the Society for Imaging Informatics in Medicine)
Vendors provide easy tools to perform quantitative imaging but the question is how reliable and repeatable this quantification is.
Many clinical examples can already be listed where quantitative imaging is used in clinical practice. Such as carotid stenosis, coronary artery stenosis, calcium scoring, pulmonary nodules, renal donor evaluation, liver and tumor volumetry, brain perfusion, emphysema quantification.
Each of these show good results in literature and could be applied in clinical practice.
However, the question is whether the numbers we get out of the software are usefull and what is reality. Different vendors provide different results in the same patient and even within one software system measurements are influenced by postprocessing choices but also by decisions during the acquisiiton.
One of the things that can be done to get proper quantification we should provide reference datasets.
QIBA is ran by a group of stakeholders to improve quantitative imaging. They define profiles to get precise, repeatable measurements. QIBA has setup a imaging data warehouse (QIDW) including standard datasets that can be used to validate quantitative imaging algorithm.
The QIDW is free, open source, modular software based on MIDAS.
In conclusion tagging of the image data in radiology is essential to allow computers to work with the information. The quantification is part of this tagging. Developments like AIM are trying to cover this and allow export in XML or DICOM SR, however current PACSs and EMRs do not yet support these kind of measurement. When the storage and data mining of all the information available in the images becomes possible it will provide the key information to get to personalized diagnosis and treatment.
Top five forces to medical imaging are defined to be:
1. Cost reduction
2. Daunting PACS migration
3. Silos of imaging sources
4. Complexity of effective image sharing
5. Leverage health IT best practices
The road to effective image sharing by implementing Vendor Neutral Archive (VNA) taking care of access consolidation. Access consolidation requirements are:
1. Integrated clinical systems
5. Content accessible
IHE profiles are there to break the vendor neutral consolidation barriers.
IHE XDS provides the profiles to allow content (vendor) neutral archive. Several profiles are defined to describe the required capabilities within an XDS affinity domain such as PIX (patient identity cross referencing) , BPPC (basic patient privacy and concent) and XUA (cross enterprise user authentication).
The XDS environment can be setup as a federated, centralized or hybrid environment.
Monday, December 2, 2013
In an interesting session the prerequistes for 3D printing were shown as well as an overview of the available techniques for 3d printing. One clear message was that the integration into the normal workflow is not achieved as of yet. Furthermore, reimbursement of 3D printing is not available yet thus hampering its wide scale application.
Basically great potential was show for 3d printing in education, training, intervention planning, and evalution using patient specific phantoms for for example flow measurement. Although 3d printing is not yet into mainstream in radiology and medicine the near future will show an increased use of this new feature.
Mobile is the single largest disruptive technology for the next decade. While desktop PCs are reducing in number the number of tablets is rising steadily. The number of smartphones is exploding right now showing an enormous increase (half of the facebook users are mobille only).
Eighty percent of smartphones shipped today are running android. This shows that android is starting to takeover apple iOS. This is also shown in tablets where android is also more sold nowadays than the iPad while the iPad currently still is the most used tablet based on network traffic measurements.
In terms of security, android shows a higher number of malware apps than apple iOS. Also in terms of enterprise security policies, VPN handling, etc, iOS is way ahead of android with for example enterprise single sign on and VPN per app.
The iOS first approach to develop an app seems to be the way to go in radiology because of the wider acceptance and use of apple devices.
To develop an app the steps to take are identify concept, user interface design, programming, construct app, and finally polish the app.
Sunday, December 1, 2013
A crucial point in quality metrics is the choice of the right measures. These measures should be selected such that they can be used to identify problems, not making the department look good. Metrics that are repeatedly in range should be droppen since they are not providing information to improven. The national quality forum can help to identify the radiology measures for quality. However they only include 2 dedicated radiology metrics.
Employee engagement is very important to succesfully improve quality. An example was given showing that metrics were used to stimulate radiologists to meet them by connecting the number of metrics met to a financial reward. This worked remarkably showing a much better quality performance after this reward was implemented.
Another vital part of quality improvement is root cause analysis. Just recording problems and fixing them does not improve quality, taking the time to get to the root cause and solving it does.