Diffusion MRI (dMRI) streamline tractography is the gold-standard for in vivo estimation of white matter (WM) pathways in the human brain. However, standard dMRI tractography methods are highly dependent on the quality of the dMRI data. Recent advancements integrating tractography with deep learning have enabled the generation of streamlines from T1-weighted (T1w) MRI and anatomical data. In this work, we propose a method to obtain high quality tractography from clinically-feasible dMRI data by adding T1w MRI and anatomical context. We train a convolutional-recurrent neural network (CoRNN) as a local tractography estimator, using clinical quality dMRI, T1w volume and anatomical labels as input. We then compare performance between a baseline resampling method and the proposed network, finding statistically significant differences in performance and bundle reconstruction characteristics. This result may allow the estimation of brain connectivity patterns from previously unusable data.