All medical procedures, including imaging and image interpretation, are relatively risky. But the fact that we make mistakes doesn't mean that we can't control and minimize them.
All medical procedures, including imaging and image interpretation, are relatively risky. But the fact that we make mistakes doesn't mean that we can't control and minimize them.
Today, the multidisciplinary approach and so-called disease pathways are commonplace, and care is centered on patients themselves. We like to think that our digital radiology department is at the center of a well-run medical establishment, the spider in the middle of the web. Procedures are workflow-oriented, and considerable attention is paid to efficiency and quality.
As radiologists, we have to ensure that everything in our part of the chain works smoothly. We need to optimize our workflow and constantly evaluate what kind of information we are delivering, as well as its quality. This is not just about delivering reports on time. The report must make sense, and it must be read and acted upon by the person who requested it.
It should be possible to store, retrieve, and read images made in the radiology department and to send these images wherever they are required 24 hours a day, seven days a week. This could be to another department, another hospital or clinic, or to a colleague who is reporting images from home. The infrastructure to do this must be managed and maintained by the organization as a whole.
The problem with going digital is that your great achievement of today is your baseline for tomorrow. For example, the orthopedic surgeon who was previously happy waiting 72 hours for a report now gets angry if reports do not arrive within minutes of a patient's return from radiology!
How can you maintain this high level of service? We decided that all image-containing data produced at our hospital-the MR images, endoscopy views, pathology results, and neurostereotactic planning data, for example-should be maintained at a single previously identified location. The images need to be archived, but they must still be retrievable virtually instantaneously.
You have an online cache of images that await interpretation, reported images, and data that might be needed when the patient returns, perhaps in three months or even three years. You also need to be sure that when the data are archived, nothing is lost.
Clearly, we are talking about a significant number of terabytes. You will need double-if not triple-redundancy for data security and handling. All the individual imaging data sets and multimedia data sets will need careful protection.
Process management applies to our whole way of working. You might not have to check for dust in film cassettes any more, but you do have to check that the shades of grey you see on the monitor have not faded and that the workstation is not too slow.
Systemwide monitoring of all the database servers and all computers is our next challenge. There is nothing worse than finding that a reporting workstation is not functioning when you have an extensive list of cases to review. We have modified a commercially available system that shows with a green, orange, or red light whether equipment is working, needs watching, or requires immediate action. This visual alert allows the whole system to be checked quickly at the start of each day. Any problems can then be taken care of at once, minimizing downtime.
Our aim is to anticipate problems before they arise. For example, we monitor the storage capacity of the workstation in the angio intervention suite to prevent loss of 3D functionality. We do not want to be faced with an emergency case in the middle of the night and find that digital equipment cannot be used because the hard disk is full.
What about QA of radiologists as well as systems? All of us risk making an erroneous diagnosis. You can never eliminate that risk, but you can minimize it. Double-reading is one option. Peer review is another. Four eyes "see" more than two.
In short, good process management is essential in this digital, patient-centered environment. QA undoubtedly has an associated cost, but so does litigation.
Emerging AI Algorithm Shows Promise for Abbreviated Breast MRI in Multicenter Study
April 25th 2025An artificial intelligence algorithm for dynamic contrast-enhanced breast MRI offered a 93.9 percent AUC for breast cancer detection, and a 92.3 percent sensitivity in BI-RADS 3 cases, according to new research presented at the Society for Breast Imaging (SBI) conference.
The Reading Room Podcast: Current Perspectives on the Updated Appropriate Use Criteria for Brain PET
March 18th 2025In a new podcast, Satoshi Minoshima, M.D., Ph.D., and James Williams, Ph.D., share their insights on the recently updated appropriate use criteria for amyloid PET and tau PET in patients with mild cognitive impairment.
Can Abbreviated Breast MRI Have an Impact in Assessing Post-Neoadjuvant Chemotherapy Response?
April 24th 2025New research presented at the Society for Breast Imaging (SBI) conference suggests that abbreviated MRI is comparable to full MRI in assessing pathologic complete response to neoadjuvant chemotherapy for breast cancer.
Clarius Mobile Health Unveils Anterior Knee Feature for Handheld Ultrasound
April 23rd 2025The T-Mode Anterior Knee feature reportedly offers a combination of automated segmentation and real-time conversion of grayscale ultrasound images into color-coded visuals that bolster understanding for novice ultrasound users.