Implementation and evaluation of a protocol management system for automated review of CT protocols

Abstract

Protocol review is important to decrease the risk of patient injury and increase the consistency of CT image quality. A large volume of CT protocols makes manual review labor‐intensive, error‐prone, and costly. To address these challenges, we have developed a software system for automatically managing and monitoring CT protocols on a frequent basis. This article describes our experiences in the implementation and evaluation of this protocol monitoring system. In particular, we discuss various strategies for addressing each of the steps in our protocol‐monitoring workflow, which are: maintaining an accurate set of master protocols, retrieving protocols from the scanners, comparing scanner protocols to master protocols, reviewing flagged differences between the scanner and master protocols, and updating the scanner and/or master protocols. In our initial evaluation focusing only on abdomen and pelvis protocols, we detected 309 modified protocols in a 24‐week trial period. About one‐quarter of these modified protocols were determined to contain inappropriate (i.e., erroneous) protocol parameter modifications that needed to be corrected on the scanner. The most frequently affected parameter was the series description, which was inappropriately modified 47 times. Two inappropriate modifications were made to the tube current, which is particularly important to flag as this parameter impacts both radiation dose and image quality. The CT protocol changes detected in this work provide strong motivation for the use of an automated CT protocol quality control system to ensure protocol accuracy and consistency.PACS number(s): 87.57.Q‐

Exploring the Role of Artificial Intelligence in an Emergency and Trauma Radiology Department

“…20 Scientists are developing neural networks and AI systems that automate the process of protocolling medical imaging requests. [21][22][23][24] Few systems manage CT protocols in departments dealing with high imaging load, ensuring the appropriate imaging study is done at the right time. 22 Other systems attempt to decrease MRI scan time by customizing MRI protocols and sequence selection based on the image requisition and clinical question.…”

“…[21][22][23][24] Few systems manage CT protocols in departments dealing with high imaging load, ensuring the appropriate imaging study is done at the right time. 22 Other systems attempt to decrease MRI scan time by customizing MRI protocols and sequence selection based on the image requisition and clinical question. Electronic order entry systems can directly integrate with machine learning (ML) models which have the potential to decrease the workload of protocolling which is currently done by the radiologist or radiology trainees.…”

A General Framework for Monitoring Image Acquisition Workflow in the Radiology Environment: Timeliness for Acute Stroke CT Imaging

“…The series number tag and series description tags had to match values we pre-defined in a look up table. For example, all perfusion maps had series number over 99 and series descriptions that contained the phrase BRAPID^or BPERFUSION.T he series description tag is something a CT technologist can change at scan time [28], but has a default pre-set value determined by our CT protocol optimization team. The series descriptions in our clinic have a one to one mapping to the five phases we expect an acute stroke exam to contain.…”

Individualization of computed tomography protocols for suspected pulmonary embolism: a national investigation of routines

“…21 Additionally, one of the most strongly emphasized advantages of protocol tailoring is the consistency of image quality across various patient sizes. 22 CT protocols should be tailored based on patient age, size, and clinical condition, 23,24 and dedicated pediatric protocols are often needed. 25 Both the International Atomic Energy Association 26 and the International Commission on Radiological Protection 27 strongly recommend that only pediatric protocols should be used in children.…”