Motor and higher-order functions topography of the human dentate nuclei identified with tractography and clustering methods.

Deep gray matter nuclei are the synaptic relays, responsible to route signals between specific brain areas. Dentate nuclei (DNs) represent the main output channel of the cerebellum and yet are often unexplored especially in humans. We developed a multimodal MRI approach to identify DNs topography on the basis of their connectivity as well as their microstructural features. Based on results, we defined DN parcellations deputed to motor and to higher-order functions in humans in vivo. Whole-brain probabilistic tractography was performed on 25 healthy subjects from the Human Connectome Project to infer DN parcellations based on their connectivity with either the cerebral or the cerebellar cortex, in turn. A third DN atlas was created inputting microstructural diffusion-derived metrics in an unsupervised fuzzy c-means classification algorithm. All analyses were performed in native space, with probability atlas maps generated in standard space. Cerebellar lobule-specific connectivity identified one motor parcellation, accounting for about 30% of the DN volume, and two non-motor parcellations, one cognitive and one sensory, which occupied the remaining volume. The other two approaches provided overlapping results in terms of geometrical distribution with those identified with cerebellar lobule-specific connectivity, although with some differences in volumes. A gender effect was observed with respect to motor areas and higher-order function representations. This is the first study that indicates that more than half of the DN volumes is involved in non-motor functions and that connectivity-based and microstructure-based atlases provide complementary information. These results represent a step-ahead for the interpretation of pathological conditions involving cerebro-cerebellar circuits.

Finding the limits of deep learning clinical sensitivity with fractional anisotropy (FA) microstructure maps.

Background: Quantitative maps obtained with diffusion weighted (DW) imaging, such as fractional anisotropy (FA) -calculated by fitting the diffusion tensor (DT) model to the data,-are very useful to study neurological diseases. To fit this map accurately, acquisition times of the order of several minutes are needed because many noncollinear DW volumes must be acquired to reduce directional biases. Deep learning (DL) can be used to reduce acquisition times by reducing the number of DW volumes. We already developed a DL network named "one-minute FA," which uses 10 DW volumes to obtain FA maps, maintaining the same characteristics and clinical sensitivity of the FA maps calculated with the standard method using more volumes. Recent publications have indicated that it is possible to train DL networks and obtain FA maps even with 4 DW input volumes, far less than the minimum number of directions for the mathematical estimation of the DT. Methods: Here we investigated the impact of reducing the number of DW input volumes to 4 or 7, and evaluated the performance and clinical sensitivity of the corresponding DL networks trained to calculate FA, while comparing results also with those using our one-minute FA. Each network training was performed on the human connectome project open-access dataset that has a high resolution and many DW volumes, used to fit a ground truth FA. To evaluate the generalizability of each network, they were tested on two external clinical datasets, not seen during training, and acquired on different scanners with different protocols, as previously done. Results: Using 4 or 7 DW volumes, it was possible to train DL networks to obtain FA maps with the same range of values as ground truth - map, only when using HCP test data; pathological sensitivity was lost when tested using the external clinical datasets: indeed in both cases, no consistent differences were found between patient groups. On the contrary, our "one-minute FA" did not suffer from the same problem. Conclusion: When developing DL networks for reduced acquisition times, the ability to generalize and to generate quantitative biomarkers that provide clinical sensitivity must be addressed.

A generalized deep learning network for fractional anisotropy reconstruction: Application to epilepsy and multiple sclerosis.

Fractional anisotropy (FA) is a quantitative map sensitive to microstructural properties of tissues in vivo and it is extensively used to study the healthy and pathological brain. This map is classically calculated by model fitting (standard method) and requires many diffusion weighted (DW) images for data quality and unbiased readings, hence needing the acquisition time of several minutes. Here, we adapted the U-net architecture to be generalized and to obtain good quality FA from DW volumes acquired in 1 minute. Our network requires 10 input DW volumes (hence fast acquisition), is robust to the direction of application of the diffusion gradients (hence generalized), and preserves/improves map quality (hence good quality maps). We trained the network on the human connectome project (HCP) data using the standard model-fitting method on the entire set of DW directions to extract FA (ground truth). We addressed the generalization problem, i.e., we trained the network to be applicable, without retraining, to clinical datasets acquired on different scanners with different DW imaging protocols. The network was applied to two different clinical datasets to assess FA quality and sensitivity to pathology in temporal lobe epilepsy and multiple sclerosis, respectively. For HCP data, when compared to the ground truth FA, the FA obtained from 10 DW volumes using the network was significantly better (p <10-4) than the FA obtained using the standard pipeline. For the clinical datasets, the network FA retained the same microstructural characteristics as the FA calculated with all DW volumes using the standard method. At the subject level, the comparison between white matter (WM) ground truth FA values and network FA showed the same distribution; at the group level, statistical differences of WM values detected in the clinical datasets with the ground truth FA were reproduced when using values from the network FA, i.e., the network retained sensitivity to pathology. In conclusion, the proposed network provides a clinically available method to obtain FA from a generic set of 10 DW volumes acquirable in 1 minute, augmenting data quality compared to direct model fitting, reducing the possibility of bias from sub-sampled data, and retaining FA pathological sensitivity, which is very attractive for clinical applications.