Author: dondennison

MIIT20 – Don’t Miss This Year’s Program!

dondennison Uncategorized

Now Virtual! No Travel! CE & CME Credits!

See updated info in this post!

Medical Imaging Informatics and Teleradiology (MIIT), the one-day educational meeting on imaging informatics, returns to beautiful Liuna Station in Hamilton, ON on Friday May 15, 2020. MIIT has been going for 15 years and this year has a great program with speakers from leading Canadian and U.S. institutions speaking on a range of timely topics, including hot topics like AI, multimedia reporting, change management, and building effective teams, as well as a panel discussion.

We are excited to have Drs. Tessa Cook from UPenn, Vamsi Narra from BJC, Cree Gaskin from UVa, Les Folio from the NIH, Adam Prater from Emory, as well as Michael Toland from UMMS and Dr. Christian van der Pol and Ted Scott from HHSC, providing talks in person or remotely, along with Kevin O’Donnell providing an update on the DICOM standard and MIIT’s own Britt Tomlin providing a talk on the Alberta province-wide Connect Care EMR project.

Program

Check out the full program here.

Sponsorship

Information on sponsoring MIIT is here.

Registration

To register as an attendee or sponsor, click here. All prices are in CAD$.

Standard Physician registration are $200, and healthcare professionals are $150.

Early-bird registration has two deadlines with discounts for early registration. The dates and discounted rates are:

  • Physicians: By 25-Mar-2020, $150; By 27-Apr-2020, $175
  • Healthcare Professionals: By 25-Mar-2020, $100; By 27-Apr-2020, $125

A group discount rate is available to help teams attend.

  • 3-4 registrants: 10% discount
  • 5+ registrants: 20% discount

The above discounts may be applied to the early-bird rates, resulting in big savings for groups that register early.

The registration fees make MIIT very affordable, especially considering the quality of speakers and talks available in a great, easy-to-get-to venue.

AXIS Imaging Interview: Four Options for Image-Display Architecture: A Deep Dive

dondennison Healthcare IT , , , , , , ,

How diagnostic images get from server hard drives to the screen is a topic of great interest to both industry and buyers of imaging IT solutions. Speed of image access is critical for quality of service and care, along with productivity and user satisfaction.

Different solutions take different approaches to optimize image delivery over varying networks. Many solutions combine more than one software design method to achieve the best possible performance. In many cases, industry or buyers will use jargon, like “streaming”, to apply a simple term to these sometimes complex technical methods.

In a recent article by AXIS Imaging, I describe four common techniques that are used in (and occasionally between) different imaging IT systems to maximize image display speed. The article length limit prevented coverage of additional methods and intentionally excluded IT infrastructure optimizations (for example, faster networks, CPUs, and drives) and the use of irreversible lossy image compression of the images on disk.

Important Article Corrections

Although I followed up with the author about some transcription errors they made in preparing the article language, they were not corrected (at least at the time of posting this), so I am going to note some corrections here.

  1. Where the article states “…radiology practices and departments have options when designing high-speed image display…”, it should state “…radiology practices and departments have options when choosing the solution for high-speed image display…”. Radiology practices choose a solution and that solution will use one or more of the design methods (or additional ones not listed), but the Radiologists don’t choose the methods within the solution.
  2. In subsection #3, the second bullet refers to a condition where pre-caching is typically not possible (the article states the opposite). If the worklist is a separate application from the image display application, the image display application often has no method of knowing which exams listed are in the worklist, so is unable to pre-cache the images to the workstation. This is not always true, as some worklist applications can expose this information to the image display application through an API, but this is not a universally available capability and does require that a specific integration be developed to support this across the applications.
  3. In subsection #4, where it states “visual design infrastructure”, it should instead state “virtual desktop infrastructure”. People commonly refer to it as VDI.

The State of RIS Today

dondennison Healthcare IT , , ,

A lot of attention is paid to imaging IT systems, like PACS and VNAs, and EMRs these days, but Radiology Information Systems (RIS) play a very important role in the success of the Radiology service line within an enterprise.

The industry and market for RIS has changed a lot since their introduction, with two core markets (with different needs) evolving.

I recently wrote an article for HealthCare Business News, titled A tale of two kinds of RIS solutions, on the subject. The article is here.

AXIS Imaging Interview: Three Tips for Setting Up Remote Reading for Radiologists

dondennison Radiology , , , ,

Remote reading is a hot topic for many working in diagnostic imaging. It is highly desirable for many Radiologists who want to telecommute like the rest of us. And, as cloud-based imaging IT solutions become more popular, the ability to read remotely (Rads won’t be going to the data center to read) will become the standard.

AXIS Imaging interviewed me to get three tips on setting up remote reading for radiologists. The article is here.

AXIS Imaging Interview: How to Prepare a Successful Vendor RFP

dondennison Healthcare IT , ,

AXIS Imaging recently interviewed me to get three tips on preparing for a Request for Proposal (RFP). The article is here. Enjoy!

There are obviously a lot more recommended practices when doing an RFP, but these three are always good to consider. I tried to provide guidance that applies to both IT and equipment purchases.

SIIM19 – Will I See You There?

dondennison Healthcare IT , , , , ,

In less than two weeks, the SIIM Annual Meeting will be taking place at the newly opened Gaylord Rockies Resort in Aurora, Colorado. I am looking forward to catching up with old friends and meeting new ones, along with learning lots of new information.

This year, I am (co-)chairing three sessions and participating in a fourth. Here is a summary (my role). All times are in local MT.

If it is your first annual meeting, I recommend you go to the First Time Attendee Meet-up on Tue 25-Jun at 6:15 pm in the Adams C/D Lobby room and attend the New Member Orientation: Intro to SIIM session on Wed 26-Jun at 9:45 am. Jim and Rick are great educators and mentors.

Also, be sure to check out the pre-conference sessions, the Hackathon and Innovation Challenge events, as well as the #AskIndustry, Learning Lab, and Scientific sessions. And be sure to put the SIIM 2019 Reception on your calendar. It is great to connect with peers and review the scientific posters.

While you are on-site, don’t forget to share information and activities (and selfies!) using the SIIM Twitter handle @SIIM_Tweets (remember to follow SIIM for great info on imaging informatics throughout the year!) and the official 2019 Annual Meeting hashtag: #SIIM19.

I hope to see you there!

MIIT 2019 – An Overview

dondennison Healthcare IT , , , , , , , , , ,

On Friday, May 10, I once again have the pleasure of co-chairing the Medical Imaging Informatics and Teleradiology (MIIT) conference at Liuna Station in Hamilton, ON.

The program for the 14th annual MIIT meeting is stellar, we have a record number of sponsors, and—thanks to lower registration fees and new group discounts—many people are already signed up to attend.

Program Highlights:

  • AI Strategy of CAR – Roger Tam will enlighten us on the Canadian Association of Radiologists’ strategy for AI.
  • Cloud Services for Machine Learning and Analytics – Patrick Kling will reveal how cloud-based solutions can address the challenge of managing large volumes of data.
  • Patient-Centered Radiology – Dr. Tessa Cook (@asset25)will provide insight into their progress on this topic at UPenn.
  • Collecting Data to Facilitate Change – Dr. Alex Towbin of Cincinnati Children’s Hospital (@CincyKidsRad) will show us how to use data to support change management.
  • Panel on the Future of DIRs in Canada – In this interactive session, we will discover what has been accomplished with Diagnostic Imaging Repositories (DIRs) in Ontario, and what’s next. I will moderate a panel with leaders from SWODIN and HDIRS.
  • Practical Guide to making AI a Reality – Brad Genereaux (@IntegratorBrad), with broad experience working in hospitals, industry, standards committees, and technology, will help attendees prepare for this new area.
  • Healthcare IT Standards – Kevin O’Donnell, a veteran of healthcare standards development and MIIT, will provide an overview of developments within the DICOM and HL7 standards, and IHE.
  • ClinicalConnect – Dale Anderson will provide an update on this application (@ClinicalConnect), used by many organizations in the local region.

If you can attend, I am sure you will find the event educational. There are lots of opportunities to interact with our speakers and sponsors. If you are not from the region, you may find a weekend getaway to the nearby Niagara on the Lake wine region enjoyable.

And don’t forget to follow MIIT (@MIIT_Canada) on Twitter!

Enterprise Insight in Today’s Consolidated Enterprise

dondennison Healthcare IT , , , , ,

As health systems acquire or partner with previously independent facilities to form Consolidated Enterprises, and implement a Shared Electronic Medical Record (EMR) system, they often consolidate legacy diagnostic imaging IT systems to a shared solution. Facilities, data centers, identity management, networking equipment, interface engines, and other IT infrastructure and communications components are also often consolidated and managed centrally. Often, a program to capture and manage clinical imaging records follows.

Whether the health system deploys a Vendor Neutral Archive (VNA), an Enterprise PACS, or a combination of both, some investment is made to reduce the overall number of imaging IT systems installed and the number of interfaces to maintain. An enterprise-wide radiation dose monitoring solution may also be implemented.

While much has been written on strategies to achieve this type of shared, integrated, enterprise-wide imaging IT solution, there are several other opportunities for improvement beyond this vision.

In addition to imaging and information record management systems, enterprise-wide solutions for system monitoring, audit record management, and data analytics can also provide significant value.

Systems Monitoring

Organizations often have some form of enterprise-level host monitoring solution, which provides basic information on the operational status of the computers, operating systems and (sometimes) databases. However, even when the hosts are operating normally, there are many conditions that can cause a solution or workflow to be impeded.

In imaging, there are many transaction dependencies that, if they are not all working as expected, can cause workflow to be delayed or disabled. Often, troubleshooting these workflow issues can be a challenge, especially in a high-transaction enterprise.

Having a solution that monitors all the involved systems and the transactions between them can help detect, prevent, and correct workflow issues.

Audit Record Management

Many jurisdictions have laws and regulations that require a comprehensive audit trail to be made available on demand. Typically, this audit trail provides a time-stamped record of all accesses and changes to a patient’s record, including their medical images, indexed by the users and systems involved.

Generating this audit trail from the myriad of logs in each involved system, each with its own record format and schema, can be a costly manual effort.

The Audit Trail and Node Authentication integration profile (ATNA), part of Integrating the Healthcare Enterprise (IHE), provides a framework for publishing, storing, and indexing audit records from different systems. It defines triggering events, along with a record format, and communication protocol.

Enterprises are encouraged to look for systems that support the appropriate actors in the ATNA integration profiles during procurement of new IT systems and equipment. Implementing an Audit Record Repository with tools that make audit trail generation easy is also important.

Data Analytics

Capturing and analyzing operational data is key to identifying issues and trends. As each system generates logs in different formats and using different methods, it often takes significant effort to normalize data records to get reliable analytics reports.

Periodic (for example, daily, weekly, or monthly) reports, common in imaging departments for decades, are often not considered enough in today’s on-demand, real-time world. Interactive dashboards that allow stakeholders to examine the data through different “lenses”, by changing the query parameters, are increasingly being implemented.

Getting reliable analytics results using data from both information (for example, the EMR and RIS) and imaging (for example, modalities, PACS, VNA, and Viewers) systems often requires significant effort, tools to extract/transform/load (ETL) the data, and a deep understanding of the “meaning” of the data.

Enterprise Insight

Implementing solutions that continuously and efficiently manage the health of your systems, the records accessed, and operational metrics are important aspects in today’s Consolidated Enterprise. Evaluating any new system as to their ability to integrate with, and provide information to, these systems is recommended.

HealthDataManagement Article: Algorithms begin to show practical use in diagnostic imaging

dondennison Radiology , , , ,

For those not following me on Twitter (@DonKDennison), here is a recent article on AI adoption to which I contributed. Enjoy!

The Case for Vendor Neutral Artificial Intelligence (VNAi) Solutions in Imaging

dondennison Technology , , , , , , , ,

Defining VNAi

Lessons Learned from Vendor Neutral Archive (VNA) Solutions

For well over a decade, VNA solutions have been available to provide a shared multi-department, multi-facility repository and integration point for healthcare enterprises. Organizations employing these systems, often in conjunction with an enterprise-wide Electronic Medical Record (EMR) system, typically benefit from a reduction in complexity, compared to managing disparate archives for each site and department. These organizations can invest their IT dollars in ensuring that the system is fast and provides maximum uptime, using on-premises or cloud deployments. And it can act as a central, managed broker for interoperability with other enterprises.

The ability to standardize on the format, metadata structure, quality of data (completeness and consistency of data across records, driven by organizational policy), and interfaces for storage, discovery, and access of records is much more feasible with a single, centrally-managed system. Ensuring adherence to healthcare IT standards, such as HL7 and DICOM, for all imaging records across the enterprise is possible with a shared repository that has mature data analytics capabilities and Quality Control (QC) tools.

What is a Vendor Neutral Artificial Intelligence (VNAi) Solution?

The same benefits of centralization and standardization of interfaces and data structures that VNA solutions provide are applicable to Artificial Intelligence (AI) solutions. This is not to say that a VNAi solution must also be a VNA (though it could be), just that they are both intended to be open and shared resources that provide services to several connected systems.

Without a shared, centrally managed solution, healthcare enterprises run the risk of deploying a multitude of vendor-proprietary systems, each with a narrow set of functions. Each of these systems would require integration with data sources and consumer systems, user interfaces to configure and support it, and potentially varying platforms to operate on.

Do we want to repeat the historic challenges and costs associated with managing disparate image archives when implementing AI capabilities in an enterprise?

Characteristics of a Good VNAi Solution

The following capabilities are important for a VNAi solution.

Interfaces

Flexible, well-documented, and supported interfaces for both imaging and clinical data are required. Standards should be supported, where they exist. Where standards do not exist, good design principles, such as the use of REST APIs and support for IT security best practices, should be adhered to.

Note: Connections to, or inclusion of, other sub-processes—such as Optical Character Recognition (OCR) and Natural Language Processing (NLP)—may be necessary to extract and preprocess unstructured data before use by AI algorithms.

Data Format Support

The data both coming in and going out will vary and a VNAi will need to support all kinds of data formats (including multimedia ones) with the ability to process this data for use in its algorithms. The more the VNAi can perform data parsing and preprocessing, the less each algorithm will need to deal with this.

Note: It may be required to have a method to anonymize some inbound and/or outbound data, based on configurable rules.

Processor Plug-in Framework

To provide consistent and reliable services to algorithms, which could be written in different programming languages or run on different hosts, the VNAi needs a well-documented, tested, and supported framework for plugging in algorithms for use by connected systems. Methods to manage the state of a plug-in—from test, production, and disabled, as well as revision controls—will be valuable.

Quality Control (QC) Tools

Automated and manual correction of data inputs and outputs will be required to address inaccurate or incomplete data sets.

Logging

Capturing the logic and variables used in AI processes will be important to retrospectively assess their success and to identify data generated by processes that prove over time to be flawed.

Data Analytics

For both business stakeholders (people) and connected applications (software), the ability to use data to measure success and predict outcomes will be essential.

Data Persistence Rules

Much like other data processing applications that rely on data as input, the VNAi will need to have configurable rules that determine how long defined sets of data are persisted, and when they are purged.

Performance

The VNAi will need to be able to quickly process large data sets at peak loads, even with highly complex algorithms. Dynamically assigning IT resources (compute, network, storage, etc.) within minutes, not hours or days, may be necessary.

Deployment Flexibility

Some organizations will want their VNAi in the cloud, others will want it on-premises. Perhaps some organizations want a hybrid approach, where learning and testing is on-premises, but production processing is done in the cloud.

High Availability (HA) and Business Continuity (BC) and System Monitoring

Like any critical system, uptime is important. The ability for the VNAi to be deployed in an HA/BC configuration will be essential.

Multi-tenant Data Segmentation and Access Controls

A shared VNAi reduces the effort to build and maintain the system, but its use and access to the data it provides will require data access controls to ensure that data is accessed only by authorized parties and systems.

Cost Sharing

Though this is not a technical characteristic, the VNAi solution likely requires the ability to share the system build and operating costs among participating organizations. Methods to identify usage of specific functions and algorithms to allocate licensing revenues would be very helpful.

Effective Technical Support

A VNAi can be a complex ecosystem with variable uses and data inputs and outputs. If the system is actively learning, how it behaves on one day may be different than on another. Supporting such a system will require developer-level profile support staff in many cases.

Conclusion

Without some form of VNAi (such the one described here), we risk choosing between monolithic, single-vendor platforms, or a myriad of different applications, each with their own vendor agreements, hosting and interface requirements, and management tools.

Special thanks to @kinsonho for his wisdom in reviewing this post prior to publication.