D I G I TA L
H E A LT H
day Elsa’s here on official business and she’s about to see something quite remarkable.
Below the observation dome behind us is Dr. Jean Boudrou. He’s the head of our inter- ventional services. He’s from France. A real sweetie. Today he’s going to perform the first- ever replacement of a mitral valve using re- motely controlled catheters. Normally, the mi- tral valve allows blood to flow in only one direction from one atrium to the adjoining ventricle in the heart. But in some patients it leaks so badly that it has to be replaced. It’s still a fairly common condition. Up until now, valve replacement meant opening the chest and the heart – not exactly minor surgery. This patient will be different.
As I told Elsa, the patient is an interesting guy. He’s Prof. Alan Carnadine, the head of the Center for Living Memory. We even had lunch together a few times back when the Center was preparing for its grand opening.
Over the last few days Jean – I mean Dr. Boudrou – examined him thoroughly. Carna- dine’s digital health card indicated that he had had a mild case of rheumatic fever as a child and was on anti-depressants following a recent “personal event.” He was also suffering from dizzy spells.
A digital audio analysis of his heart picked up a murmur and identified the sound as a mitral valve defect. A clinical decision support application not only analyzed all of Carna- dine’s available imaging data to quantify ex- actly how much blood was being regurgitated with each heart beat, but also provided treat- ment recommendations.
By the time I had finished explaining the clinical situation to Elsa, the patient had been sedated, prepped for catheterization, and had undergone a combined computed tomogra- phy, magnetic resonance, and positron emis- sion tomography (PET) analysis. We could see on the observation deck monitors that the CT scan had turned up no anatomical abnormal- ities – except for the mitral valve defect – and that the PET scan had found the entire my- ocardium to be healthy. In both cases, intelli- gent software applications automatically ran through all the data and provided Dr. Boudrou
and the patient’s electronic file – with the
Dr. Boudrou proceeded to examine the pa- tient’s 3D MR chest scan. Automated align- ment of image planes taken between heart- beats, the magnet’s very high field strength, and multi-RF channel design made it possible
to examine the patient’s heart with extraordi- nary resolution. Based on that scan, a pro- gram calculated the exact size and shape of the required replacement valve, ordered a customized prosthesis from our ultra sterile automated production center, and marked the route to be taken by the catheter. Minutes later the prosthetic valve was delivered and mounted in the catheter’s tip.
Then the procedure began. With the pa- tient well inside the MR scanner, Dr. Boudrou began guiding the remotely controlled catheter to its target using precision joy sticks. Elsa and I watched in fascination as a virtual 3D view from the catheter’s tip showed the dark red inner walls of the patient’s arteries gliding by as it followed a bright yellow navi- gation stripe superimposed on the actual real- time images.
Finally, the catheter eased into place at the site of the compromised valve. A magnified view appeared showing a virtual target point with which Jean lined up the tip of the actual catheter using a micron guidance feature on his joy sticks.
“Magnifique!” we heard Jean say to him- self over the loudspeaker. Satisfied that the valve was exactly on target, he directed the catheter to discharge an electric impulse that stopped the patient’s heart. A second later, the first part of the prosthesis unfolded, flat- tening the patient’s faulty valve firmly against the inner wall of the atrium. The umbrella valve then unfurled from within the catheter, its microscopic hooks clamping themselves firmly over the perimeter of the old valve.
“Superb!” Jean exclaimed in his rich Parisian accent as a display, based on an analysis of all imaging angles, indicated that the hooks had seamlessly sealed the pros- thetic device into place. A moment later a sig- nal restarted the patient’s heart, and from our displays we could see and hear the new valve opening and closing normally.
“Extraordinary,” Elsa said, when she turned to me. “I will recommend…” But then she no- ticed that something had changed. “Where’s the patient?” she asked, a look of disbelief on her face as she looked at the empty scanner bay. “Oh, my dear Elsa,” I said. “What you just experienced was a full-scale simulation. The patient in the bay was an augmented reality projection – essentially a demonstration of IDSIC’s leadership in data fusion. In a few mo- m e n t s , t h e r e a l p a t i e n t w i l l a r r i v e . ” ■ A r t h u r F . P e a s e
Information technology is transforming healthcare. Vast knowledge bases are being squeezed into algorithms that can detect and characterize pathologies with the accuracy of a world-class expert. In the operating room, image fusion and advances in magnetic resonance are leading the way to real-time visualization of micro- surgical procedures.
e a r n i n g - b a s e d , i n t e l l i g e n t a p p l i c a t i o n s a r e o p e n i n g a n e w w o r l d o f p o s s i b i l i t i e s i n L healthcare. In twenty years or less unneces- sary biopsies could be history, cancer screen- ing will probably be automated, and knowl-
applications will provide clinical decision sup- port with the accuracy of world-class special- ists. Treatment planning, implementation and follow-up will be based on the fusion of im- aging modalities (see p. 72) and real-time, knowledge-based characterization and evalu- ation of the physician’s field of view. Like the power of a gigantic magnifying glass, meticu- lously sifted data from hundreds of thousands of patient cases will be translated into knowl- edge, injected into diagnostic systems in the form of algorithms (see p. 70), and focused on patient exams to produce precision evalu- ations and ever-improving outcomes.
Tomorrow’s knowledge-based revolution is already being born. Its outlines are visible in
It takes powerful software to integrate thousands of slices from high-tech imaging systems into three-dimensional pictures. But the key to supporting physicians in rapidly detecting and characterizing potential pathologies is the use of algorithms based on distilled expert knowledge.
Inside the Algorithms
northern Italy, where a new electronic health card (see p. 76) is creating an information bridge between doctors’ offices, pharmacies and each patient’s medical needs. It’s visible in New York City and Saarbrücken, Germany, where radio-frequency identification wrist- bands (see p. 82) are seamlessly joining patients with their electronic records. And it’s taking shape in radiology practices around the world, where evolving knowledge-based systems are helping physicians to detect dis- eases at the earliest possible stage. With this evolving healthcare landscape in mind, Siemens Medical Solutions (SMS) is develop- ing a spectrum of innovative computer-aided detection (CAD) technologies covering multi- ple imaging modalities and applications.
Catching Lung Nodules Early. Nowhere is the need for knowledge-based healthcare more urgent than in the detection of lung cancer. Not only is this the number one can-
cer killer worldwide, but a single CT chest scan results in up to 1000 slices — so much information that it places high demands on radiologists’ ability to meet their workloads, which can reach up to 40 scans per day. “The sheer quantity of information being gener- ated by diagnostic systems is making it essen- tial that we implement systems capable of ex- tracting meaningful information from medical data,” says Alok Gupta, Ph.D., Vice President for Computer Aided Diagnosis and Therapy at SMS in Malvern, Pennsylvania.
With this in mind, SMS last year launched LungCARE NEV (Nodule Enhanced Viewing), a dedicated application for the localization of small nodules in the lungs. Already available in over 100 clinics worldwide, NEV can detect nodules as small as 3mm in diameter. Like a spell checker in a Word program, NEV can sift through hundreds of images and detect any structures that fit a list of nodule characteris- tics. As the radiologist analyzes a patient’s
lung scan, NEV works as an independent sec- ond reader in the background. When the radi- ologist has completed the initial read, NEV can be activated to highlight potential lesions that may have been missed. “We have found that such techniques help most doctors im- prove their accuracy by anywhere from ten to thirty percent,” says Gupta.
Current guidelines established by the U.S. Food and Drug administration (FDA) require NEV to be used as a second reader. But as ra- diologists gain confidence in the technology, it may eventually be permitted as a concur- rent reader or even as a first reader — a step that would dramatically accelerate workflows in radiology departments and allow physi- cians to focus on the most relevant findings. In fact, the idea of using CAD systems as “first readers” is becoming increasingly attractive in a related field — mammography — where, according to Gupta, “such systems are already detecting above 90 percent of anomalies.”
Pictures of the Future | Fall 2005