An efficient memory reserving-and-fading strategy for vector quantization based 3D brain segmentation and tumor extraction using an unsupervised deep learning network.

Deep learning networks are state-of-the-art approaches for 3D brain image segmentation, and the radiological characteristics extracted from tumors are of great significance for clinical diagnosis, treatment planning, and treatment outcome evaluation. However, two problems have been the hindering factors in brain image segmentation techniques. One is that deep learning networks require large amounts of manually annotated data. Another issue is the computational efficiency of 3D deep learning networks. In this study, we propose a vector quantization (VQ)-based 3D segmentation method that employs a novel unsupervised 3D deep embedding clustering (3D-DEC) network and an efficiency memory reserving-and-fading strategy. The VQ-based 3D-DEC network is trained on volume data in an unsupervised manner to avoid manual data annotation. The memory reserving-and-fading strategy beefs up model efficiency greatly. The designed methodology makes deep learning-based model feasible for biomedical image segmentation. The experiment is divided into two parts. First, we extensively evaluate the effectiveness and robustness of the proposed model on two authoritative MRI brain tumor databases (i.e., IBSR and BrainWeb). Second, we validate the model using real 3D brain tumor data collected from our institute for clinical practice significance. Results show that our method (without data manual annotation) has superior accuracy (0.74±0.04 Tanimoto coefficient on IBSR, 97.5% TP and 97.7% TN on BrainWeb, and 91% Dice, 88% sensitivity and 87% specificity on real brain data) and remarkable efficiency (speedup ratio is 18.72 on IBSR, 31.16 on BrainWeb, 31.00 on real brain data) compared to the state-of-the-art methods. The results show that our proposed model can address the lacks of manual annotations, and greatly increase computation speedup with competitive segmentation accuracy compared to other state-of-the-art 3D CNN models. Moreover, the proposed model can be used for tumor treatment follow-ups every 6 months, providing critical details for surgical and postoperative treatment by correctly extracting numerical radiomic features of tumors.

The role of motor system in action-related language comprehension in L1 and L2: An fMRI study.

The framework of embodied cognition has challenged the modular view of a language-cognition divide by suggesting that meaning-retrieval critically involves the sensory-motor system. Despite extensive research into the neural mechanisms underlying language-motor coupling, it remains unclear how the motor system might be differentially engaged by different levels of linguistic abstraction and language proficiency. To address this issue, we used fMRI to quantify neural activations in brain regions underlying motor and language processing in Chinese-English speakers' processing of literal, metaphorical, and abstract language in their L1 and L2. Results overall revealed a response in motor ROIs gradually attenuating in intensity from literal to abstract via metaphorical language in both L1 and L2. Furthermore, contrast analyses between L1 and L2 showed overall greater activations of motor ROIs in the L2. We conclude that motor involvement in language processing is graded rather than all-or-none and that the motor system has a dual-functional role.

Association between Homocysteine and Cerebral Small Vessel Disease: A Meta-Analysis.

BACKGROUND: This study aimed to evaluate whether elevated homocysteine levels is associated with risk of different subtypes of cerebral small vessel disease (CSVD) by using meta-analysis. MATERIALS AND METHODS: Electronic databases were systematically searched up to April 2018 for collecting the studies reporting homocysteine levels in CSVD or CSVD subtypes. After an inclusion and exclusion criteria, the data was extracted. All data was analyzed using Stata software v.12.0 (Stata Corp LP, College Station, TX). The standardized mean difference (SMD) and 95% confidence interval (CI) were used to compare continuous variables. RESULTS: Eighteen studies met eligibility criteria with 5088 participants (1987 patients with CSVD and 3101 controls) included in the meta-analysis. Meta-analysis revealed that, compared with the controls group, the CSVD group had significantly higher homocysteine levels, with the SMD of .50 and 95% CI (.36-.64). Subgroup analyses suggested white matter lesion had significantly higher levels of homocysteine compared with controls (SMD = .56, 95% CI .39-.73), followed by silent brain infarction (SMD = .33, 95% CI .24-.42) and lacunar infarction (SMD = .17, 95% CI -.06 to .40). CONCLUSIONS: This meta-analysis found that CSVD or CSVD subtypes have a significantly higher homocysteine levels than in controls. Further prospective population-based studies are needed to longitudinally evaluate the association between homocysteine levels and progression of different CSVD subtypes.