Despite dire predictions regarding the flood of data coming from 16-slice CT scans, radiologists for the most part have kept pace. Routing these exams, however, can be maddening, particularly whole-body scans of trauma patients.
Despite dire predictions regarding the flood of data coming from 16-slice CT scans, radiologists for the most part have kept pace. Routing these exams, however, can be maddening, particularly whole-body scans of trauma patients.
Scans covering two or more body parts may require multiple readings. Because CT and PACS typically assemble data under a single accession number, a whole-body image of head, neck, chest, abdomen, and pelvis usually is noted simply as a head scan, for the first body part examined. If several radiologists are to read these cases, support staff must manually split them into parts and route them. Further problems may be lurking down the road.
"Your PACS can have accession numbers (defined by studies read earlier) with no images associated with them," said Dr. Harold White, a radiologist with the Akron General Health System. "When that happens, you don't have anything to look at."
A software traffic cop can help. The dyseCT software developed by DeJarnette Research Systems automatically segments CT scans according to body parts, routes the segments to designated radiologists, and assigns specific accession numbers for each reading. It even assigns the codes for billing each study.
Radiologists using a multidisciplinary approach to reading trauma or oncology cases stand to benefit most from dyseCT, according to White. In these cases, several radiologists specializing in different body areas may be interested in the same scan.
"If you're at a small institution, handling the problem manually may work," White said. "But at a large institution, doing the work manually will probably cause a lot of problems."
Akron General Medical Center in Ohio serves as a level 1 trauma center. White and colleagues read from seven 16-slice CTs, which together generate a terabyte of data each month. It's just too much data for staff to split up manually, White said. The data volume will likely go up when the center adds a 64-slice scanner later this year.
Akron Medical is one of about a dozen institutions that have turned to dyseCT for help. Work-study analyses performed at five of these sites indicate that inefficiencies associated with typical multislice operations running in a PACS environment cost an institution $150 per day per CT, or $50,000 per CT per year. If so, dyseCT, priced at $23,000, is a bargain.
The product modifies the DICOM modality work list, using a group procedure to replace the multiple procedures. It analyzes the images and associates them with anatomic regions. Then it matches them to the appropriate orders.
The software relies on "bone moments" to split the body into segments, said Wayne DeJarnette, president and founder of DeJarnette Research Systems. These moments, based on measurements showing where bone density is greatest, provide profiles that match the different body segments. A body scan can be segmented into any number of parts to match the reading paradigm.
The flood of data coming from multislice scanners prompted DeJarnette to create dyseCT, but CT is no longer the only modality responsible for a surge in data. Improvements in MR have opened the door to whole-body scanning in that modality as well. In response, DeJarnette is developing an encore product, migrating the capabilities built into dyseCT to a version designed for MR.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.