In recent years, many automatic brain structure segmentation methods have been proposed. However, thesemethods are commonly tested with non-lesioned brains and the effect of lesions on their performance has notbeen evaluated. Here, we analyze the effect of multiple sclerosis (MS) lesions on three well-known automaticbrain structure segmentation methods, namely, FreeSurfer, FIRST and multi-atlas fused by majority voting,which use learning-based, deformable and atlas-based strategies, respectively. To perform a quantitativeanalysis, 100 synthetic images of MS patients with a total of 2174 lesions are simulated on two public databaseswith available brain structure ground truth information (IBSR18 and MICCAI’12). The Dice similarity coefficient(DSC) differences and the volume differences between the healthy and the simulated images are calculated forthe subcortical structures and the brainstem. We observe that the three strategies are affected when lesions arepresent. However, the effects of the lesions do not follow the same pattern; the lesions either make thesegmentation method underperform or surprisingly augment the segmentation accuracy. The obtained resultsshow that FreeSurfer is the method most affected by the presence of lesions, with DSC differences (generated −healthy) ranging from−0.11 ± 0.54 to 9.65 ± 9.87, whereas FIRST tends to be the most robust method whenlesions are present (−2.40 ± 5.54 to 0.44 ± 0.94). Lesion location is not important for global strategies suchas FreeSurfer or majority voting, where structure segmentation is affected wherever the lesions exist. On theother hand, FIRST is more affected when the lesions are overlaid or close to the structure of analysis. The mostaffected structure by the presence of lesions is the nucleus accumbens (from −1.12 ± 2.53 to 1.32 ± 4.00 forthe left hemisphere and from −2.40 ± 5.54 to 9.65 ± 9.87 for the right hemisphere), whereas the structuresthat show less variation include the thalamus (from 0.03 ± 0.35 to 0.74 ± 0.89 and from −0.48 ± 1.08 to−0.04 ± 0.22) and the brainstem (from −0.20 ± 0.38 to 1.03 ± 1.31). The three segmentation approachesare affected by the presence of MS lesions, which demonstrates that there exists a problem in the automaticsegmentation methods of the deep gray matter (DGM) structures that has to be taken into account when usingthem as a tool to measure the disease progression
展开▼
