Back

Evaluation of statistical detection of change algorithm for triaging multiple sclerosis patients with new lesion activity on longitudinal brain MRI

Homssi, M.; Sweeney, E. M.; Demmon, E.; Sakirsky, M.; Mannheim, W.; Wang, Y.; Gauthier, S. A.; Gupta, A.; Nguyen, T. D.

2023-02-02 radiology and imaging
10.1101/2023.01.31.23285297 medRxiv
Show abstract

Background and PurposeIdentification of new MS lesions on longitudinal MRI by human readers is time-consuming and prone to error. Our objective was to evaluate the improvement in a subject-level detection performance by readers when assisted by the automated statistical detection of change (SDC) algorithm. Materials and MethodsA total of 200 MS patients with mean inter-scan interval of 13.2 {+/-} 2.4 months were included. SDC was applied to the baseline and follow-up FLAIR images to detect potential new lesions for confirmation by readers (Reader+SDC method). This method was compared with readers operating in the clinical workflow (Reader method) for a subject-level detection of new lesions. ResultsReader+SDC found 30 subjects (15.0%) with at least one new lesion, while Reader detected 16 subjects (8.0%). As a subject-level triage tool, SDC achieved a perfect sensitivity of 1.00 (95% CI: [0.88, 1.00]) and a moderate specificity of 0.67 (95% CI: [0.59, 0.74]). The agreement on a subject-level was 0.91 (95% CI: [0.87, 0.95]) between Reader+SDC and Reader, and 0.72 (95% CI: [0.66, 0.78]) between Reader+SDC and SDC. ConclusionSDC improves the detection accuracy of human readers and can serve as a time-saving patient triage tool for detecting new MS lesion activity on longitudinal FLAIR images.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.