RT Journal Article
SR Electronic
T1 TAPAS: A Thresholding Approach for Probability Map Automatic Segmentation in Multiple Sclerosis
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 609156
DO 10.1101/609156
A1 Alessandra M. Valcarcel
A1 John Muschelli
A1 Dzung L. Pham
A1 Melissa Lynne Martin
A1 Paul Yushkevich
A1 Peter A. Calabresi
A1 Rohit Bakshi
A1 Russell T. Shinohara
YR 2019
UL http://biorxiv.org/content/early/2019/04/22/609156.abstract
AB Total brain white matter lesion (WML) volume is the most widely established magnetic resonance imaging (MRI) outcome measure in studies of multiple sclerosis (MS). To estimate WML volume, there are a number of automatic segmentation methods, yet, manual delineation remains the gold standard approach. These approaches often yield a probability map to which a threshold is applied to create lesion segmentation masks. Unfortunately, few approaches systematically determine the threshold employed; many methods use a manually selected threshold, thus introducing human error and bias into the automated procedure. In this study, we propose and validate an automatic thresholding algorithm, Thresholding Approach for Probability Map Automatic Segmentation in Multiple Sclerosis (TAPAS), to obtain subject-specific threshold estimates for probability map automatic segmentation of T2-weighted (T2) hyperintense WMLs. Using multimodal MRI, the proposed method applies an automatic segmentation algorithm to obtain probability maps. We obtain the true subject-specific threshold that maximizes Sørensen-Dice Similarity Coefficient (DSC). Then the subject-specific thresholds are modeled on a naive estimate of volume using a general additive model. Applying this model, we predict a subject-specific threshold in data not used for training. We ran a Monte Carlo-resampled split-sample cross-validation (100 validation sets) using two data sets: the first obtained from the Johns Hopkins Hospital (JHH) on a Philips 3 Tesla (3T) scanner (n = 94) and a second collected at the Brigham and Women’s Hospital (BWH) using a Siemens 3T scanner (n = 40). By means of the proposed automated technique, in the JHH data, we found an average reduction in subject-level absolute error of 0.1 mL per one mL increase in manual volume. Using Bland-Altman analysis, we found that volumetric bias associated with group-level thresholding is mitigated when applying TAPAS. The BWH data showed similar absolute error estimates using group-level thresholding or TAPAS likely since Bland-Altman analyses indicate no systematic biases associated with group or TAPAS volume estimates. The current study presents the first validated fully automated method for subject-specific threshold prediction to segment brain lesions.