PACS Integration of Semiautomated Imaging Software Improves Day-to-Day MS Disease Activity Detection

Abstract

BACKGROUND AND PURPOSE: The standard for evaluating interval radiologic activity in MS, side-by-side MR imaging comparison, is restricted by its time-consuming nature and limited sensitivity. VisTarsier, a semiautomated software for comparing volumetric FLAIR sequences, has shown better disease-activity detection than conventional comparison in retrospective studies. Our objective was to determine whether implementing this software in day-today practice would show similar efficacy. MATERIALS AND METHODS: VisTarsier created an additional coregistered image series for reporting a color-coded disease-activity change map for every new MS MR imaging brain study that contained volumetric FLAIR sequences. All other MS studies, including those generated during software-maintenance periods, were interpreted with side-by-side comparison only. The number of new lesions reported with software assistance was compared with those observed with traditional assessment in a generalized linear mixed model. Questionnaires were sent to participating radiologists to evaluate the perceived day-today impact of the software. RESULTS: Nine hundred six study pairs from 538 patients during 2 years were included. The semiautomated software was used in 841 study pairs, while the remaining 65 used conventional comparison only. Twenty percent of software-aided studies reported having new lesions versus 9% with standard comparison only. The use of this software was associated with an odds ratio of 4.15 for detection of new or enlarging lesions (P = .040), and 86.9% of respondents from the survey found that the software saved at least 2-5 minutes per scan report. CONCLUSIONS: VisTarsier can be implemented in real-world clinical settings with good acceptance and preservation of accuracy demonstrated in a retrospective environment. ABBREVIATIONS: AIC ¼ akaike information criterion; CSSC ¼ conventional side-by-side comparison; EDSS ¼ Expanded Disability Status Scale; VT ¼ VisTarsier M ultiple sclerosis is a common immune-mediated inflammatory disease of the central nervous system and the most frequent neurologic cause of disability in young adults. 1,2 With the ongoing development and approval of disease-modifying drugs, the armamentarium of therapies to reduce relapse frequency, radiological disease activity and progression continues to grow.

A Clinically-Compatible Workflow for Computer-Aided Assessment of Brain Disease Activity in Multiple Sclerosis Patients

“…Second, we observed that the use of lesion masks produced by the lesion detection module significantly increases the number of lesions detected regardless of the level of expert's experience (more than 15% more lesions with the MUSIC workflow than without). This observation is in line with recent studies not involving deep learning based segmentation (26)(27)(28). In parallel, while not significant, we also observed a natural reduction of the inter-expert variability when using the segmentation masks.…”

Limited utility of adding 3T cervical spinal cord MRI to monitor disease activity in multiple sclerosis

“…We routinely used semi-automated co-registration fusion software to compare 3D FLAIR sequences of the brain, while the aforementioned studies used 2D axial proton density and T2-weighted sequences, which likely resulted in a higher number of new BLs detected in our study. 27,28,30 Differences in MRI field strengths (3T in our study vs 1.5T in some of the studies) may have also contributed to the discrepant results. 31 Interestingly, we did not see a higher yield of CSLs even with the inclusion of PSIR sequence in our SC-MRI protocol, an MRI sequence thought to be more sensitive than the T2-weighted and proton density (PD) sequences used in the prior studies.…”

“…Although structured reporting is not routinely done, it is common practice for the neuroradiologists in our institution to indicate the number and location of new lesions in the report. In rare occasions where the exact number was not provided in the report, the images were re-evaluated, and the number of new lesions was counted and recorded by two neuroradiologists experienced in MS. A semi-automated co-registration fusion software with color overlay 27,28 for comparing volumetric FLAIR sequences of the brain (Volume Matching, Carestream Health; Rochester, NY) was routinely used in our practice during the study period in addition to conventional review of the images. Studies that were reported as equivocal for new lesions were reviewed in consensus by two neuroradiologists with 5- and 10-year experience for final determination of the presence or absence of new lesions or exclusion due to technical factors (poor image quality of current and prior study).…”

Neuroimaging lesion assessment by pseudo-subtraction of overlaid semi-transparent volumes: A technical description and feasibility series

“…Subtraction of magnetic resonance (MR) images has been described in multiple sclerosis to enhance detection of contrast enhancing lesions, estimate lesion volume change, 1 or assess new lesions in longitudinal follow-up. 2 Subtraction of images requires dedicated software not readily available at all imaging centers. Here, we present a simple technique that instead of subtraction utilizes overlaid semi-transparent greyscale volume images from two different time points, namely, routine follow-up.…”