Improving Multiple Sclerosis Plaque Detection Using a Semiautomated Assistive Approach

Abstract

BACKGROUND AND PURPOSE:Treating MS with disease-modifying drugs relies on accurate MR imaging follow-up to determine the treatment effect. We aimed to develop and validate a semiautomated software platform to facilitate detection of new lesions and improved lesions.

Neuroradiologists Compared with Non-Neuroradiologists in the Detection of New Multiple Sclerosis Plaques

“…11 A previous study has shown that a semiautomated assistive platform is fast, robust, and detects many more new lesions on MR imaging of patients with MS than conventional side-by-side comparison. 9 The same software has also been shown to perform similarly when used by readers of different radiology experience, including readers with minimal radiology experience. 12 This new approach allowed us to use it as a new "gold standard" against which we can measure the performance of radiologists of various levels of subspecialty experience.…”

“…A semiautomated software package (VT) has previously been validated and shown to detect an increased number of new lesions in patients with MS compared with conventional side-by-side comparison. 9 The development of the software processing tool and data processing procedure has been described in that earlier study. All of the patients included in this study have been reported previously.…”

“…All of the patients included in this study have been reported previously. 9 The prior article described the development, implementation, and outcome of the semiautomated software package, whereas the current study reports the differences between NRs and NNRs in reporting MS studies by using the outcomes from the previous study as a "gold standard. "…”

“…An example of the VT output is displayed in Fig 1. Importantly, the reporting radiologists had the full diagnostic gamut of conventional imaging sequences available for review, excluding VT change maps, whereas the VT dataset used only the change maps from VT (by using volumetric T2 FLAIR) in new lesion detection. 9 Reporting radiologists were categorized as NR, defined as someone who had spent at least 1 year in a neuroradiology fellowship program, or NNR, defined as someone who has not had specific subspecialist training in neuroradiology.…”

Fast and Robust Unsupervised Identification of MS Lesion Change Using the Statistical Detection of Changes Algorithm

“…One approach to overcoming this problem is to extract lesion masks using a lesion segmentation algorithm 2 , which are subtracted to yield a lesion change mask. Alternatively, lesion change can be detected on the subtraction of two images either by humans 3 or with the help of an algorithm relying on the subtraction signal and lesion geometry 4 . While image subtraction can substantially improve lesion contrast, separating lesion change from background noise requires consideration of the statistical properties of the signal and noise.…”