Improving measurement of blood-brain barrier permeability with reduced scan time using deep-learning-derived capillary input function

PURPOSE: In Dynamic contrast-enhanced MRI (DCE-MRI), Arterial Input Function (AIF) has been shown to be a significant contributor to uncertainty in the estimation of kinetic parameters. This study is to assess the feasibility of using a deep learning network to estimate local Capillary Input Function (CIF) to estimate blood-brain barrier (BBB) permeability, while reducing the required scan time. MATERIALS AND METHOD: A total of 13 healthy subjects (younger (<40 y/o): 8, older (> 67 y/o): 5) were recruited and underwent 25-min DCE-MRI scans. The 25 min data were retrospectively truncated to 10 min to simulate a reduced scan time of 10 min. A deep learning network was trained to predict the CIF using simulated tissue contrast dynamics with two vascular transport models. The BBB permeability ([Formula: see text]) was measured using 3 methods: (i) [Formula: see text]-25min, using DCE-MRI data of 25 min with individually sampled AIF ([Formula: see text]); (ii) [Formula: see text]-10min, using truncated 10min data with AIF ([Formula: see text]); and (iii) [Formula: see text]-10min, using truncated 10 min data with CIF ([Formula: see text]). The [Formula: see text] estimates from the [Formula: see text]-25min method were used as reference standard values to assess the accuracy of the [Formula: see text]-10min and [Formula: see text]-10min methods in estimating the [Formula: see text] values. RESULTS: When compared to the reference method([Formula: see text]-25min), the [Formula: see text]-10min and [Formula: see text]-10min methods resulted in an overestimation of [Formula: see text] by 217 ± 241 % and 48.0 ± 30.2 %, respectively. The Bland Altman analysis showed that the mean difference from the reference was 8.85 ± 1.78 (x10(−4) min(−1)) with the [Formula: see text]-10min, while it was reduced to 1.63 ± 2.25 (x10(−4) min(−1)) with the [Formula: see text]-10min, resulting in an average reduction of 81%. The limits of agreement also reduced by up to 39.2% with the [Formula: see text]-10min. We found a 75% increase of BBB permeability in the gray matter and a 35% increase in the white matter, when comparing the older group to the younger group. CONCLUSIONS: We demonstrated the feasibility of estimating the capillary-level input functions using a deep learning network. We also showed that this method can be used to estimate subtle age-related changes in BBB permeability with reduced scan time, without compromising accuracy. Moreover, the trained deep learning network can automatically select CIF, reducing the potential uncertainty resulting from manual user-intervention.