Multi-modal imaging with specialized sequences improves accuracy of the automated subcortical grey matter segmentation

Mapping cerebral atrophic trajectory from amnestic mild cognitive impairment to Alzheimer's disease

Alzheimer's disease (AD) patients suffer progressive cerebral atrophy before dementia onset. However, the region-specific atrophic processes and the influences of age and apolipoprotein E (APOE) on atrophic trajectory are still unclear. By mapping the region-specific nonlinear atrophic trajectory of whole cerebrum from amnestic mild cognitive impairment (aMCI) to AD based on longitudinal structural magnetic resonance imaging data from Alzheimer's disease Neuroimaging Initiative (ADNI) database, we unraveled a quadratic accelerated atrophic trajectory of 68 cerebral regions from aMCI to AD, especially in the superior temporal pole, caudate, and hippocampus. Besides, interaction analyses demonstrated that APOE ε4 carriers had faster atrophic rates than noncarriers in 8 regions, including the caudate, hippocampus, insula, etc.; younger patients progressed faster than older patients in 32 regions, especially for the superior temporal pole, hippocampus, and superior temporal gyrus; and 15 regions demonstrated complex interaction among age, APOE, and disease progression, including the caudate, hippocampus, etc. (P < 0.05/68, Bonferroni correction). Finally, Cox proportional hazards regression model based on the identified region-specific biomarkers could effectively predict the time to AD conversion within 10 years. In summary, cerebral atrophic trajectory mapping could help a comprehensive understanding of AD development and offer potential biomarkers for predicting AD conversion.

Automated Segmentation of Midbrain Structures in High-Resolution Susceptibility Maps Based on Convolutional Neural Network and Transfer Learning

Background

Accurate delineation of the midbrain nuclei, the red nucleus (RN), substantia nigra (SN) and subthalamic nucleus (STN), is important in neuroimaging studies of neurodegenerative and other diseases. This study aims to segment midbrain structures in high-resolution susceptibility maps using a method based on a convolutional neural network (CNN).

Methods

The susceptibility maps of 75 subjects were acquired with a voxel size of 0.83 × 0.83 × 0.80 mm³ on a 3T MRI system to distinguish the RN, SN, and STN. A deeply supervised attention U-net was pre-trained with a dataset of 100 subjects containing susceptibility maps with a voxel size of 0.63 × 0.63 × 2.00 mm³ to provide initial weights for the target network. Five-fold cross-validation over the training cohort was used for all the models’ training and selection. The same test cohort was used for the final evaluation of all the models. Dice coefficients were used to assess spatial overlap agreement between manual delineations (ground truth) and automated segmentation. Volume and magnetic susceptibility values in the nuclei extracted with automated CNN delineation were compared to those extracted by manual tracing. Consistencies of volume and magnetic susceptibility values by different extraction strategies were assessed by Pearson correlation coefficients and Bland-Altman analyses.

Results

The automated CNN segmentation method achieved mean Dice scores of 0.903, 0.864, and 0.777 for the RN, SN, and STN, respectively. There were no significant differences between the achieved Dice scores and the inter-rater Dice scores (p > 0.05 for each nucleus). The overall volume and magnetic susceptibility values of the nuclei extracted by the automatic CNN method were significantly correlated with those by manual delineation (p < 0.01).

Conclusion

Midbrain structures can be precisely segmented in high-resolution susceptibility maps using a CNN-based method.

Automatic detection of neuromelanin and iron in the midbrain nuclei using a magnetic resonance imaging ‐based brain template

Parkinson disease (PD) is a chronic progressive neurodegenerative disorder characterized pathologically by early loss of neuromelanin (NM) in the substantia nigra pars compacta (SNpc) and increased iron deposition in the substantia nigra (SN). Degeneration of the SN presents as a 50 to 70% loss of pigmented neurons in the ventral lateral tier of the SNpc at the onset of symptoms. Also, using magnetic resonance imaging (MRI), iron deposition and volume changes of the red nucleus (RN), and subthalamic nucleus (STN) have been reported to be associated with disease status and rate of progression. Further, the STN serves as an important target for deep brain stimulation treatment in advanced PD patients. Therefore, an accurate in‐vivo delineation of the SN, its subregions and other midbrain structures such as the RN and STN could be useful to better study iron and NM changes in PD. Our goal was to use an MRI template to create an automatic midbrain deep gray matter nuclei segmentation approach based on iron and NM contrast derived from a single, multiecho magnetization transfer contrast gradient echo (MTC‐GRE) imaging sequence. The short echo TE = 7.5 ms data from a 3D MTC‐GRE sequence was used to find the NM‐rich region, while the second echo TE = 15 ms was used to calculate the quantitative susceptibility map for 87 healthy subjects (mean age ± SD: 63.4 ± 6.2 years old, range: 45–81 years). From these data, we created both NM and iron templates and calculated the boundaries of each midbrain nucleus in template space, mapped these boundaries back to the original space and then fine‐tuned the boundaries in the original space using a dynamic programming algorithm to match the details of each individual's NM and iron features. A dual mapping approach was used to improve the performance of the morphological mapping of the midbrain of any given individual to the template space. A threshold approach was used in the NM‐rich region and susceptibility maps to optimize the DICE similarity coefficients and the volume ratios. The results for the NM of the SN as well as the iron containing SN, STN, and RN all indicate a strong agreement with manually drawn structures. The DICE similarity coefficients and volume ratios for these structures were 0.85, 0.87, 0.75, and 0.92 and 0.93, 0.95, 0.89, 1.05, respectively, before applying any threshold on the data. Using this fully automatic template‐based deep gray matter mapping approach, it is possible to accurately measure the tissue properties such as volumes, iron content, and NM content of the midbrain nuclei.