Usefulness of texture analysis in ¹²³I-FP-CIT for the differentiation of AD and DLB subtypes

I-2β-carbomethoxy-3β-(4-iodophenyl)-N-(3-fluoropropyl) nortropane (¹²³I-FP-CIT) is well known to be a useful tracer for differentiating dementia with Lewy bodies (DLB) and Alzheimer disease (AD). However, clinically, there are some cases in which these diseases cannot be differentiated by ordinary quantitative methods. Therefore, in this study, we established an index that reflects not only the total count but also the distribution and heterogeneity of tracer uptake. We investigated whether assessment of the heterogeneous depletion of ¹²³I-FP-CIT is useful for the differentiation of various types of dementia, i.e., probable DLB, possible DLB, and AD, using texture analysis.

A total of 122 patients with either probable DLB (n=35), possible DLB (n=23), AD (n=44), and normal controls (n=20) were analyzed. Summated single photon emission computed tomography (SPECT) images (7 to 10 slices) of the patients, including the bilateral striatum, were analyzed using the gray-level histogram method (GLHM) of texture analysis. Mean, variance, skewness, and kurtosis of GLHM were compared with the specific binding ratio by Livia Tossici-Bolt's method (SBR).

The sensitivity and specificity for differentiating probable DLB from possible DLB, AD, and normal controls were 97.1% and 77.0%, respectively, for skewness, using a cut-off point of 6.8%, and 97.1% and 81.6%, respectively, for kurtosis, using a cut-off point of 53.4%. The sensitivity and specificity for differentiating probable and possible DLB from AD and normal controls was 65.5% and 98.4%, respectively, for skewness, using a cut-off point of 6.4%, and 79.3% and 93.8%, respectively, for kurtosis, using a cut-off point of 53.4%.

In the assessment of the efficacy of ¹²³I-FP-CIT to differentiate AD and DLB subtypes, mean, variance, skewness, and kurtosis by GLHM was as useful as the SBR method. Moreover, possible DLB and probable DLB could be differentiated by skewness and kurtosis. Our results demonstrate that texture analysis is more useful than conventional quantitative methods for obtaining valuable information of the brain. Textural features as such may have considerable potential as imaging biomarkers of DLB progression.