Texture analysis of dark intraplacental bands on T2WI in the evaluation of placenta accreta spectrum disorders: a feasibility study

Abstract

Background: To evaluate whether texture analysis of dark intraplacental bands on T2WI can provide a novel methodological viewpoint valuable in assessing the classification of placenta accreta spectrum disorders (PAS disorders).Methods: 174 participants with suspected PAS disorders were consecutively included in the study. Texture analysis was implemented on dark intraplacental bands on T2WI by MaZda software. The two steps of parameter selection and reduction led to a decrease of the parameter space dimensionality. The logistics regression models were constructed with texture parameters to evaluate the classification of PAS disorders.Results: Both run length nonuniformity (RLN) and grey level nonuniformity (Gle) of four directions showed significant differences between participants with placenta accreta, increta and percreta (P﹤0.05). The AUC and cut-off for logistic regression model of accreta vs increta were 0.75 (95% CI: 0.54, 0.90) and 6.72, respectively; corresponding values for logistic regression model of increta vs percreta were 0.81 (95% CI: 0.61, 0.93) and 10.92. The sensitivity and specificity for cut-off of 6.72 were 88.46% and 84.62%, respectively; corresponding values for cut-off of 10.92 were 92.59% and 85.71%.Conclusion: Texture analysis offered promise for more quantitative and objective assessment of PAS disorders than other image modalities. It may be a useful add-on to MRI in evaluating the classification of PAS disorders. Trial registration: Registration number: ChiCTR2000038604 and name of registry: Evaluation of diagnostic accuracy of MRI multi-parameter imaging combined with texture analysis for placenta accreta spectrum disorders (PAD).