Technology

Cardiac CT

Neurology CT

Oncology CT

Women's Health CT

Facility Management

Cardiac MRI

Neurology MRI

Oncology MRI

Women's Health MRI

Mammography

Molecular Imaging

Cardiac Ultrasound

Oncology Ultrasound

Women's Health Ultrasound

Ultrasound

Orthopedic X-Ray

X-Ray

News

All News

Blogs

Media

Around the Practice 

Between the Lines

Image IQ

Medical World News

Podcasts

Rad-View

Videos

Conferences

Conference Coverage

Conference Listing

DI Executive

Resources

CME/CE

E-books

Education

Interactive Tool Kits

Partners

Subscribe

Diagnostic Imaging serves as the connection to Radiology, including groundbreaking Imaging news and interviews with top Radiologists in multimedia formats.

Advertise

About

Contact Us

Editorial

Editorial Board

Do Not Sell My Personal Information 

Privacy

Terms and Conditions

Diagnostic Imaging - Radiology News, Imaging Expert Insights

Facebook

LinkedIn

YouTube

Spotlight

RSNA

Disease Spotlight: Prostate Cancer

Rad-View: Generic Contrast Agents 

Rad View: PSMA PET Imaging Recommendations

Unlock AI-Powered Imaging

Image IQ Quiz

Topics

View More

Electronic medical records are based on input-oriented architectures separated into laboratory, pharmacy, radiology, and other hospital divisions, but if given a choice, clinicians would reorganize the records around physiological systems.

Analysis suggests this architecture is superior, an artificial intelligence expert told a Clinical Systems audience Monday afternoon at HIMSS. Herbert Doller, Ph.D., explained how "black box" analysis can be applied to modeling physiological systems and how this analysis produces an architecture superior to the current input-oriented model.

"All pure scientists know that quality applications begin with good architecture and that bad architecture will show up at the worst possible time - the time when users are maddest and demanding you to make immediate changes," said Doller, chief of the artificial intelligence laboratory at the VA North Texas Health Care System and an assistant professor of pathology at UT-Southwestern Medical Center in Dallas. "Bad architecture, however, often stands in the way of those changes. Good architecture, on the other hand, anticipates the needs of users and allows the application to evolve."

Current database design architecture in healthcare is leading us to develop sophisticated applications on top of a large global database, according to Doller. Such an architecture leads to applications of exponential design, and that the need of these applications for computer resources also grows exponentially, eventually reaching an infinite demand. Such designs are not solvable by large databases.

"We're not talking about them being difficult to solve - they're impossible to solve once they've reached a certain size," he said. "Current data repositories are already too large for this design. This architecture is already limiting your ability to create good applications in healthcare."

In order to design sophisticated medical applications, a partitioning scheme is required. Such a design would lead to polynomial growth instead of exponential. Although this growth can be substantial, it does not lead to infinite need for computer resources, as do current designs, Doller said. What he proposed is a partitioning scheme in which the design actually models biology.

Two camps are interested in biological data: bioinformatics and medical informatics. Using genetic sequences, bioinformatics wants to say something about the health of the organism through a mechanism that will allow a change in genetic sequence to propagate throughout the organism, where it manifests itself in different symptoms, Dollar said.

At the other end of the spectrum are the physicians with their clinical data wanting to use this data to correlate with the genetic information.

"What interested us is that they're all looking at same pathway from opposite directions, and the architecture that we're proposing will actually support a single pathway working in both directions," he said.

Articles

HIMSS

Electronic medical records are based on input-oriented architectures separated into laboratory, pharmacy, radiology, and other hospital divisions, but if given a choice, clinicians would reorganize the records around physiological systems. Analysis

Clinicians propose biology-modeled database architecture

 Five years from now, will Integrating the Healthcare Enterprise-like initiatives function across all medical disciplines, paving the way for the first truly enterprise-wide electronic patient record? That is the vision of several participants in the IHE Year 2 demonstrations. 

The demos themselves suffered less-than-enthusiastic response from attendees at the RSNA and Healthcare Information Management Systems Society meetings and certain vendor factions, but medical organizations outside radiology are warming to the idea of multidiscipline systems standardization. 

A number of medical specialties are already expressing interest in IHE, according to Chris Carr, director of informatics for the RSNA, which is in discussions with organizations representing the pathology, laboratory, ophthalmology, and cardiology communities. While such efforts are still in their infancy, the interest being shown by the lab and path groups is particularly keen, and some concrete steps are imminent. 

"The benefits that can be gained in agreeing on how data can be made available from department to department are huge," Carr said. "I don't think you can really have an electronic patient record until these issues are solved, and IHE is a potential approach to engaging with other disciplines." 

Carr speculates that in the not-too-distant future, IHE-like demos will occur at a variety of medical meetings, with the focus on the needs of each particular specialty and on moving information across the entire spectrum of care. He sees HIMSS eventually becoming the hub demo, where all the disciplines come together and the ability to share data across the enterprise is replicated. 

"I am so encouraged to see the lab, cardiology, and ophthalmology groups saying, 'We have these same problems,' and wanting to become involved in a project like this," said Gail Woods, who represents Siemens/SMS on the IHE technical committee. "In the next couple of years, we will grow and will have to figure out how to manage all these different types of specialties and vendors." 

The work of the IHE committees is already changing product development, vendor representatives say. Software developers are beginning to adopt common interfaces, and tools such as the X500 object database and CORBAmed are becoming part of the IHE framework. 

"The benefit of IHE is to decouple specific vendor software development and replace it with a framework that is a standard for everyone," said Rik Primo, director of business development at Siemens Health Services. "This improves time to market and customer confidence." 

In Year 1, the IHE focused on integrating IT systems in the radiology department to implement a basic clinical workflow. Year 2 goes beyond basic image acquisition, addressing such concerns as patient information reconciliation, nonroutine data handling, and diagnostic and care processes. 

"Years 1 and 2 have been about PACS integration with RIS and modalities," Primo said. "Now we want to expand to HIS, EMR, and clinical systems." 

For example, the 32 companies participating in the Year 2 demo at the RSNA meeting showcased the seven integration profiles that have been developed within IHE so far. In particular, the Scheduled Workflow integration profile, which forms the IHE workflow foundation, was demonstrated across a set of almost 70 imaging and information systems, including HIS, RIS, PACS, modalities, and workstations. 

"Visitors were amazed to see the ability to define independent views when multiple procedures, such as chest, abdomen, and pelvis, are grouped in a single acquisition using CT and MR," said Charles Parisot, GE Medical's representative on the IHE planning and technical committee and cochair of the technical committee. "Attendees realized that IHE is no longer a dream but a concrete capability they can expect from their vendors for both information and imaging systems." 

Challenges remain, however. Within radiology, much of the functionality required to interface RIS and PACS to enterprise information systems still needs to be made real, according to Carr. True standardized reporting, for example, which is a necessary underpinning of any electronic patient record, is still in its infancy. In addition, most IS and IT vendors are still not participating in the IHE demos. 

"IHE started in radiology and radiology's partnership with IT professionals," Carr said. "The DICOM experience helped the vendor sector that supports radiology become highly organized and set them up to cooperate very effectively, but some of the other disciplines are lagging behind in this." 

These issues have prompted the newly elected HIMSS leadership to take a more aggressive approach to IHE this year. The 2001 annual meeting program includes much more IHE material than last year. The Year 2 IHE demonstration at the HIMSS meeting has been expanded to include 

?reporting;
?broader access to images and reports throughout the enterprise;
?image presentation consistency;
?reconciliation of unknown patient data; and
?other workflow and transaction enhancements.


HIMSS has also implemented a second leg of its outreach process to more effectively reach the IT community, according to Carr. 

"HIMSS has undertaken a very serious effort to get the body of IT companies that attend its meetings to better participate in IHE and the future of the initiative, but it is still a major challenge," he said. "When we have more involvement from other specialties, it will put more pressure on the IT companies to come to the table. And the more they participate, the more incentive there will be for other specialties to become involved." 

Parisot agrees. The upcoming demonstration at HIMSS has the potential to convince IS and IT vendors and CIOs that the IHE approach is making strides where previous integration attempts have failed, he said. 

"This should accelerate the extension of IHE beyond radiology to such areas as laboratory or cardiology," he said. 

Five years from now, will Integrating the Healthcare Enterprise-like initiatives function across all medical disciplines, paving the way for the first truly enterprise-wide electronic patient record? That is the vision of several participants in the IHE

IHE lays foundation for multispecialty integration

Voice recognition has found an unlikely ally: PACS. Every major imaging and PACS vendor now offers, or is on the verge of launching, digital dictation capabilities integrated with their radiology workstations. Some even go a step further and voice-enable systems to respond to spoken commands.

The goal is to help radiologists streamline workflow and improve efficiencies, and the issue of whether the technology is accurate enough seems to have become moot.

A key player in this latest image management trend is Talk Technology. In 1996, when IBM introduced MedSpeak, the first commercially available continuous speech recognition product for radiology, Talk Technology began marketing the product. But MedSpeak had its drawbacks. Recognizing an opportunity to improve on the core technology, Talk Technology licensed IBM's speech recognition engine for radiology and built its own workflow application around it.

"The value for us is in the workflow," Mardini said. "We see this as a clinical reporting solution for radiologists to help make them more efficient."

Talk Technology claims installations of its Talk Station product at more than 200 hospitals, primarily for radiology. The company has formed alliances with more than a dozen PACS and RIS firms, including Agfa, Siemens, GE, Philips, Marconi, IDX, and Sunquest. It has modified Talk Station to be engine independent and has customized the original radiology package for use in pathology and emergency medicine.

"Our vision is that Talk Station will be the de facto standard speech and reporting interface inside of PACS/RIS workstations," Mardini said. "Our PACS partners are recognizing that voice recognition and clinical reporting aren't their focus, and they see that they can embed Talk Station to handle this."

In fact, PACS vendors say the transcription savings from Talk Station can reduce the overall return on investment from five to four years, according to Mardini. Turnaround times are reduced from 24 hours to one hour.

"I can walk into any site and save them 50% of their transcription costs," he said. "On average, 75% to 80% of reports at our customer sites are done without the aid of transcriptionists." 

Numbers like these are what helped attract the attention of Talk Technology's PACS and RIS partners. Ongoing improvements in the technology and increasing pressure for radiologists to speed turnaround times have improved receptiveness among physicians as well.

"In the U.S. the focus is more on rapid turnaround of clinical decisions and getting the job done as quickly as possible," said Milan DiPiero, product manager for enterprise PACS at Philips Medical Systems. "Talk Technology has a lot of domain-specific knowledge that would take a lot of time for us to create or capture ourselves."

Philips offers Talk Station in conjunction with its own speech engine (the Speech Mike) in its PACS workstations for radiology, cardiology, and pathology. In addition, given Philips' core competencies in speech processing technologies and the strong installed base of Speech Mike among radiologists, the company is working to voice-enable its PACS workstations.

Other PACS vendors working with Talk Technology include GE Medical and Marconi Medical. GE showed a work-in-progress voice application at the last RSNA meeting that combined Talk Station with the PathSpeed workstation; the company's goal is to reduce the number of PCs sitting in the radiology viewing room and to streamline the ability to access and update images and reports.

GE is also in the early phases of integrating the Talk Technology package with Applicare's RadWorks, which is GE's lower-end PACS product. This would make the same integrated voice recognition capabilities available to smaller clinics and hospitals.

Marconi, the latest addition to Talk Technology's pool of PACS partners, is integrating Talk Station v.2 with its PACS workstations and Web-based results distribution capabilities to enable radiologists to dictate, edit, sign, and distribute coded reports in real-time or in batch mode. Marconi's results server automatically selects key images based on the report content of the dictation, eliminating the need for manual image marking.

"People will adapt to VR because of the time and cost savings associated with it and the improvements in patient care," said Vickie Sims, marketing manager for Marconi Medical. "Transcription is a very large part of the cost of the total study done on a patient. The scan lasts about 60 seconds, while the rest of the process takes two to four days."

Ultimately, Mardini sees voice recognition playing a central role throughout the hospital. Talk Technology is developing a handheld digital dictation product for enterprise applications that should be available by next year's HIMSS meeting. 

"One thing is for sure beyond death and taxes: in the next five years, everything will use speech recognition for a large number of document creation and processing applications," Mardini said. "Three years from now, no one's going to be talking about who's got the best core engine. It will be the applications, and the enabling technologies that make it possible to build those applications."

, a biweekly business newsletter covering the medical information technology industry published by Diagnostic Imaging. 

Voice recognition has found an unlikely ally: PACS. Every major imaging and PACS vendor now offers, or is on the verge of launching, digital dictation capabilities integrated with their radiology workstations. Some even go a step further and voice-enable

PACS/RIS vendors bring voice recognition to radiology

As the annual RSNA meeting draws near, vendors are gearing up for Year 2 of the IHE (Integrating the Healthcare Enterprise) demonstration. As part of this process, some 150 software engineers and marketing/product managers from more than 30 imaging, modality, and information systems firms gathered at RSNA headquarters in Chicago in early October for the IHE "connectathon."

This week-long systems integration marathon is a trial run designed to work out connectivity and workflow kinks prior to the main IHE event in November. The 33 companies that attended brought with them a total of 68 different systems, including RIS, PACS, displays, and modalities. They performed a number of successful vendor-to-vendor connections, according to Christopher Carr, assistant director of informatics for the RSNA.

"We need to ensure that the messaging and transfer of files is consistent and reliable. The connectathon is designed as a test to ensure that the demo runs smoothly," said Tom Pacenta, industry manager for diagnostic imaging and PACS at Marconi Communications, which is donating all of the equipment to support the gigabit Ethernet networks for both the IHE demo and RSNA exhibition this year.

The long-term goal of IHE is to bring consistency to the way standards for the exchange of data and images are interpreted and implemented. In a more practical vein, the IHE initiative should eliminate the need for vendors to develop expensive proprietary interfaces that are often incomplete and must be reconfigured and separately maintained at each customer site.

Toward this end, the IHE Year 1 demonstration held during the 1999 RSNA and 2000 HIMSS meetings demonstrated that 24 vendors (representing 47 separate information and imaging systems) could share information in an integrated, open-standards environment and maintain the integrity of the data and images exchanged. Year 1 participants included Agfa, Algotec, Canon, Cedara Software, Cerner, DeJarnette, eMed, Fuji, GE, IDX, Marconi, Merge, Mitra, Philips, StorComm, Toshiba, and Vital Images.

"The primary accomplishment of Year 1 was getting the process in place," Carr said. "Representatives from major imaging and information systems vendors sat down and agreed on a framework for implementing established standards, such as DICOM and HL7."

For practical reasons, the scope of the Year 1 demo was fairly narrow, focusing on basic registration, scheduling, image acquisition, and storage procedures in the radiology department. Four simulated healthcare enterprises, each modeling a different hospital, featured patients with conditions ranging from a torn knee ligament to suspected appendicitis. Within each simulation, spectators were introduced to the patient's ailment and could watch information being entered into the hospital's records system, where it became instantly available to the radiology department. There, x-ray, ultrasound, and other images were integrated into the record.

IHE Year 2 widens the scope, with 34 vendors representing 74 distinct systems at the RSNA meeting. New features include mechanisms to deal with a patient who is incompletely identified at the time of registration, access to nonradiology information such as lab values, image consistency across disparate display systems, and structured reporting. Vertically, new transactions and greater detail will be added to the protocols within the radiology unit. IHE is also considering incorporation of horizontal integration technologies, fostering linkage between various medical specialists within the enterprise.

Concerns linger, however, about how successful IHE will be without better support from HIS vendors, most of which have dragged their feet when it comes to actually participating in the demonstrations. For example, while representatives from Eclipsys, McKesson/HBOC, and Shared Medical Systems have been on the planning committees, these companies did not participate in the Year 1 demonstrations. IDX, Mitra, and SMS are participating in the Year 2 demo at RSNA, however.

"Our biggest obstacle is still the lack of participation by IS/IT vendors," Carr said. "We have been really successful in getting the imaging vendors to participate, and there is support from enough IS vendors to make things happen. But in order to achieve the real goal of IHE and go beyond radiology and start exchanging information across the enterprise, it will take more involvement from IS/IT companies."

This gap becomes even more critical in Year 2, where the goal is to broaden the integration more fully across the enterprise and to ensure that the HIS vendors share responsibility for adopting and implementing IHE requirements. During Year 1, the IHE planning and technical committees placed most of their emphasis on PACS/RIS integration. While the RIS/PACS interface is important, the full benefit of the IHE and PACS can be achieved only if the HIS and RIS also comply.

"This is a major problem," said Kees Smedema, international manager of interoperability for Philips Medical. "Standards only give benefit if we all use them. Our customers should require the same from their HIS and RIS vendors as they require from modality and PACS vendors."

One reason many IS/IT vendors may be less motivated to participate in IHE is because their primary trade show, the HIMSS meeting, has not pursued the concept of a networked show floor in the same way the RSNA has at its meetings. This lack of systems integration among vendors at the premier event for their industry has been a drawback in terms of promoting the value of open architecture systems and the need for full-scale connectivity.

Changes in the marketplace, however, are beginning to force the IS/IT community to recognize how a cooperative approach to systems integration can benefit not only the end users but the industry itself. Despite revenue projections of more than $20 billion for the healthcare IT industry, all but a handful of HIS vendors are reporting lower-than-expected sales and losses instead of profits. In addition, the increasing migration to enterprise computing and Internet-based thin-client technologies is creating a new market dynamic that favors software over hardware firms and start-ups (which can often move new products to market more quickly) over established legacy systems vendors.

Ultimately, the end-user community's growing need for enterprise access to patient information will likely drive the IS/IT vendors to embrace systems integration in the same way the imaging community already does.

"The IHE demonstration itself is only a means, not the goal itself," Smedema said. "Our customers ask for integration of information at their desktop. They want to improve the diagnostic process by having not only images and radiology reports, but also laboratory data and allergy information."

Ms. Kincade is editor of Health Networking News http://www.healthnetnews.com/, published by Diagnostic Imaging.

As the annual RSNA meeting draws near, vendors are gearing up for Year 2 of the IHE (Integrating the Healthcare Enterprise) demonstration. As part of this process, some 150 software engineers and marketing/product managers from more than 30 imaging,

PACS vendors fine-tune integration at IHE 'connectathon,' but not all information and systems technology vendors are on board

Using the polyglot of digital medical data to maximum patient advantage requires a Rosetta stone to integrate various enterprise-wide information systems -- a monumental task that is being addressed by an industry initiative called Integrating the Healthcare Enterprise, or IHE.

The IHE is spurring the information systems industry to devise methods for integrating healthcare's clinical tongues, which until now did not communicate with one another.

To demonstrate that such communication is possible, the RSNA and the Healthcare Information and Management Systems Society (HIMSS) are co-sponsoring a series of IHE showcases at their annual meetings.

At the most recent RSNA and HIMSS gatherings, IHE year-one demonstration proved that 24 vendors (representing 47 separate information and imaging systems) could indeed exchange information in an integrated, open-standards environment, while maintaining the integrity of the data and images exchanged between systems.(

See IHE demonstration proves image data can be shared; multivendor exercise not without technical glitches, DI In Review supplement, January 2000

"The primary accomplishment of year one was getting the process in place," said Christopher Carr, the RSNA's assistant director of informatics. "Representatives from major imaging and information systems vendors sat down and agreed on a framework for implementing established standards, such as DICOM and HL7."

The year-one scope was fairly narrow, focusing on basic registration, scheduling, image acquisition, and storage procedures in the radiology department.

During the demo, four simulated healthcare enterprises, each modeling a different hospital, featured patients with conditions ranging from a torn knee ligament to suspected appendicitis. Within each simulation, spectators were introduced to the patient's ailment and watched information being entered into the hospital's records system, where it became instantly available to the radiology department. There, x-ray, ultrasound, and other images were integrated into the record.

"It's hard to underestimate the importance of the year-one IHE demonstrations," said Dr. R. Gilbert Jost, interim head of the Mallinckrodt Institute in St. Louis, and a member of the RSNA board of directors. 

Without this consensus, vendors are forced to develop expensive proprietary interfaces that are often incomplete and must be reconfigured and separately maintained at a customer's site.

"The eventual goal is to provide better methods for computers to interoperate in a vendor-neutral fashion across the entire healthcare enterprise," Jost said.


Philips Medical Systems attended the IHE year-one demonstration with its PACS and x-ray angio modality. The company's participation allowed it to identify problems in workflow during interactions with clinicians and other vendors, said Kees Smedema, Philips' international manager for interoperability.

"We now have an increasing number of modalities and PACS solutions that comply with IHE year one," he said.

One year-one milestone addressed the perplexing RIS/PACS modality loop.

"That's significant," Carr said. "The standards provide mechanisms for that but actually doing it in a given implementation is a complex process. IHE simplifies it."

The RIS/PACS interface is important, experts say, because the full benefit of the IHE and PACS can be achieved only if the HIS and RIS also comply. In a number of cases, however, radiologists put IHE requirements on the modality vendor but not on their RIS and HIS vendors.

"This is a major problem," Smedema said. "Standards only give benefit if we all use them. Our customers should require the same from their HIS and RIS vendors as they require from modality and PACS vendors."

The IHE addresses integration of systems through messages between the systems, a robust method relying on standards developed primarily for the medical domain. 

"This type of integration is necessary, but not sufficient," Smedema said. "Our customers ask for integration of information at their desktop. They want to improve the diagnostic process by having not only images and radiology reports, but also laboratory data and allergy information."

Therefore, he said, the IHE should start to include other standards that were developed for desktop integration, such as XML, a language used in Web-based communication.

"The demonstration itself is only a means, not the goal itself," Smedema said. "IHE currently addresses only the precise definitions related to DICOM and HL7, but this will have to evolve to include other standards."


IHE year two widens the scope, expanding to include 33 vendors representing 74 distinct systems at the RSNA meeting.

New features include mechanisms to deal with a patient who is incompletely identified at the time of registration, access to nonradiology information such as lab values, image consistency across disparate display systems, and structured reporting.

"Year one showed that this process for achieving coordinated integration by a group of vendors could be done," Carr said. "In year two that process is used to make real gains for users in terms of functionalities available in these systems. It advances the state of integration."

Vertically, new transactions and greater detail will be added to the year-one protocols within the radiology unit.

IHE is also considering incorporating "horizontal integration" technologies, fostering linkage between various medical specialists within the enterprise. 

Vendors themselves have increased their activities for year two. Agfa, for instance, has expanded its role and is participating in four ways: as an image manager and an order filler with its IMPAX product, a CR modality, and a print server.

"Part of Agfa's goal this year is to actually demonstrate IHE in our booth at RSNA and HIMSS, to show demonstrators what it is that the IHE effort means to customers," said Dean Kaufman, director of strategic marketing for Agfa's IMPAX Solutions. "A lot of customers are asking about IHE and starting to look for evidence of IHE integration and what it means."

Customers seeking IHE benefits in the year-one demonstrations were sometimes disappointed. Last year's goals were presented in more abstract terms and it was a bit more difficult to understand the implication and the effect of IHE on the end user, Kaufman said.

"This year, IHE is bringing us to the next level of interoperability, which is important because last year was just an initial step," he said.

Smedema agreed that the year-one demonstration was too technical.

"Many visitors did not get the message and left wondering what problem was solved," he said.

European radiologists launch integration initiative 

The information page for the European IHE

X-ray vision: IHE initiative could become another Y2K nonevent 

HIMSS and RSNA dress up their joint technology project 

Project aims to get PACS and HIS systems talking to each other 

The RSNA Web site provides detailed technical information about the IHE and its objectives. You'll need an Acrobat Reader to view many of the files. Here's some of what you'll find:

Index and opening page. Includes a search mechanism

A 26-page concept document provides an overview of the project, including objectives, operating structure, technical framework, and timelines 

Vendor rules of participation and commentaries by participating vendors

A 197-page year-two IHE technical framework document identifies components of the healthcare enterprise and describes, in considerable detail, how they will interact

IHE Year Two demo participants table, RSNA 2000 (Source: the RSNA)

Direct Radiography Corp., a Hologic company

Using the polyglot of digital medical data to maximum patient advantage requires a Rosetta stone to integrate various enterprise-wide information systems -- a monumental task that is being addressed by an industry initiative called Integrating the

The IHE demonstrations: Carving healthcare's Rosetta stone

Women with a history of biopsy-proven lobular carcinoma in situ (LCIS) appear to benefit from the addition of MRI to mammography for annual breast cancer screening. A retrospective study from Memorial Sloan-Kettering Cancer Institute presented Sunday at the 2010 RSNA meeting indicates the application of screening MRI for this at-risk population can double the cancer detection rate. 

LCIS is associated with a 7% to 12% increased relative risk of developing breast cancer, according to the study’s presenter, Dr. Janice Sung. Its presence increases the lifetime risk from 20% to 30%. The time between the original diagnosis of LCIS and subsequent cancer can be long; it’s more than 15 years in half of all susceptible patients.

Few studies have investigated the efficacy of breast MRI screening in this population, however. American Cancer Society guidelines state there is not enough evidence to recommend for or against MRI screening for this population, Sung said.

The Memorial Sloan-Kettering study evaluated the diagnostic history of 226 women with LCIS who underwent annual screening breast MRI and screening mammography at the institute between 2003 and 2008. Of 860 breast MRI procedures performed on the study population, 693 were screening exams.

About one-third of the subjects had an additional risk factor. These included 28% with a family history of breast cancer and six patients with a personal history of breast cancer. Ages of the subjects ranged from 25 to 76 years, with a median age of 47 years. The median time from diagnosis of LCIS to the first MR screening exam was two years with a range of less than one year to 19 years.

Overall, 17 cases of cancer were detected in 14 patients. Twelve were detected on MRI only, representing a 4.4% malignancy detection rate for the modality, Sung said. Five were detected on mammography only, and no malignancy was identified on both modalities.

Of the 12 cancers in 10 patients detected on MRI, four represented incidental cancers seen first on screening breast MR. The patients ranged in age from 39 to 59 years at the time of diagnosis, with a mean of 52 years. Two of the 10 patients diagnosed with breast cancer had an additional risk factor for the disease. In both instances, the additional risk factor was a family history of breast cancer. Mean time interval from the original diagnosis of an LCIS to the detection of a malignancy was five years.

The invasive cancers detected with MRI were small, ranging in size from 0.05 to 1.3 cm with a mean of 0.9 cm. Three patients had axillary nodal involvement.

Calcifications were present in all five cases missed with screening MRI. Three of the five had an additional, family history, risk factor for breast cancer. And the mean time interval from original diagnosis of LCIS to the detection of cancer was four years.

More biopsies were recommended on the basis of suspicious findings on MRI than on mammography. During the study period, more than 25% of patients had a recommendation for a biopsy at some point.

The positive predictive value of biopsy was similar between the two groups. The sensitivity of MRI was higher than mammography’s (70% versus 35%). But MRI had a lower specificity rate. This pattern of higher sensitivity and lower specificity has been seen previously in studies examining MRI’s value for screening general populations, Sung said.

In response to a question from moderator Dr. Jay A. Baker, division chief of breast imaging at Duke University, Sung admitted to possible patient selection bias to explain the high cancer rate among women with a history of LCIS participating in the study. Despite this limitation and the need for more studies, the findings suggest to Sung and her colleagues that screening breast MRI should be considered for women with a history of LCIS.

Women with a history of biopsy-proven lobular carcinoma in situ (LCIS) appear to benefit from the addition of MRI to mammography for annual breast cancer screening. A retrospective study from Memorial Sloan-Kettering Cancer Institute presented Sunday at the 2010 RSNA meeting indicates the application of screening MRI for this at-risk population can double the cancer detection rate.

Latest Conference Articles