Hyposmia and apathy in early, de novo Parkinson's disease: Lessons from structural brain connectivity.

INTRODUCTION: The neuroanatomical structures implicated in olfactory and emotional processing overlap significantly. Our understanding of the relationship between hyposmia and apathy, common manifestations of early Parkinson's disease (PD), is inadequate. MATERIALS AND METHODS: We analyzed data on 40 patients with early de-novo idiopathic PD enrolled within 2 years of motor symptom onset in the Parkinson's Progression Markers Initiative (PPMI) study. To be included in the analysis, patients must have smell dysfunction but no apathy at the baseline visit and had completed a diffusion MRI (dMRI) at the baseline visit and at the 48-month follow-up visit. We used the FMRIB Software Library's diffusion tool kit to measure fractional anisotropy (FA) in six regions of interest on dMRI: bilateral anterior corona radiata, left cingulum, left superior corona radiata, genu and body of the corpus callosum. We compared the FA in each region from the dMRI done at the beginning of the study with the follow up studies at 4 years. RESULTS: We found a significant decrease of FA at the bilateral anterior corona radiata, and the genu and body of the corpus callosum comparing baseline scans with follow up images at 4-years after starting the study. CONCLUSION: Structural connectivity changes associated with apathy can be seen early in PD patients with smell dysfunction.

Deep Learning Methods for Identification of White Matter Fiber Tracts: Review of State-of-the-Art and Future Prospective.

Quantitative analysis of white matter fiber tracts from diffusion Magnetic Resonance Imaging (dMRI) data is of great significance in health and disease. For example, analysis of fiber tracts related to anatomically meaningful fiber bundles is highly demanded in pre-surgical and treatment planning, and the surgery outcome depends on accurate segmentation of the desired tracts. Currently, this process is mainly done through time-consuming manual identification performed by neuro-anatomical experts. However, there is a broad interest in automating the pipeline such that it is fast, accurate, and easy to apply in clinical settings and also eliminates the intra-reader variabilities. Following the advancements in medical image analysis using deep learning techniques, there has been a growing interest in using these techniques for the task of tract identification as well. Recent reports on this application show that deep learning-based tract identification approaches outperform existing state-of-the-art methods. This paper presents a review of current tract identification approaches based on deep neural networks. First, we review the recent deep learning methods for tract identification. Next, we compare them with respect to their performance, training process, and network properties. Finally, we end with a critical discussion of open challenges and possible directions for future works.