Intravoxel Incoherent Motion

Purpose For diffusion data sets including low and high b-values, the intravoxel incoherent motion model is commonly applied to characterize tissue. The aim of the present study was to show that machine learning allows a model-free approach to determine tissue type without a priori assumptions on the underlying physiology. Materials and Methods In 8 healthy volunteers, diffusion data sets were acquired using an echo-planar imaging sequence with 16 b-values in the range between 0 and 1000 s/mm2. Using the k-nearest neighbors technique, the machine learning algorithm was trained to distinguish abdominal organs (liver, kidney, spleen, muscle) using the signal intensities at different b-values as training features. For systematic variation of model complexity (number of neighbors), performance was assessed by calculation of the accuracy and the kappa coefficient (κ). Most important b-values for tissue discrimination were determined by principal component analysis. Results The optimal trade-off between model complexity and overfitting was found in the range between K = 11 to 13. On “real-world” data not previously applied to optimize the algorithm, the k-nearest neighbors algorithm was capable to accurately distinguish tissue types with best accuracy of 94.5% and κ = 0.92 reached for intermediate model complexity (K = 11). The principal component analysis showed that most important b-values are (with decreasing importance): b = 1000 s/mm2, b = 970 s/mm2, b = 750 s/mm2, b = 20 s/mm2, b = 620 s/mm2, and b = 40 s/mm2. Applying a reduced set of 6 most important b-values, still a similar accuracy was achieved on the real-world data set with an average accuracy of 93.7% and a κ coefficient of 0.91. Conclusions Machine learning allows for a model-free determination of tissue type using intra voxel incoherent motion signal decay curves as features. The technique may be useful for segmentation of abdominal organs or distinction between healthy and pathological tissues.