Using a Convolutional Neural Network and Convolutional Long Short-term Memory to Automatically Detect Aneurysms on 2D-DSA Images (Preprint)

BACKGROUND It is hard to distinguish cerebral aneurysms from overlapping vessels based on 2D DSA images due to their lack of spatial information. OBJECTIVE The aim of this study was to construct a deep learning diagnostic system to improve the ability to detect posterior communicating artery (PCoA) aneurysms on 2D-DSA images and validate the efficiency of the deep learning diagnostic system in 2D-DSA aneurysm detection. METHODS We proposed a two-stage detecting system. First, we established the regional localization stage (RLS) to automatically locate specific detection regions of raw 2D-DSA sequences. Then, in the intracranial aneurysm detection stage (IADS), we constructed the Bi-input+RetinaNet+C-LSTM framework to compare the performance of aneurysm detection with the existing three frameworks. Each of the frameworks had a fivefold cross-validation scheme. The area under the curve (AUC), the receiver operating characteristic (ROC) curve, and mean average precision (mAP) were used to validate the efficiency of different frameworks. The sensitivity, specificity and accuracy were used to identify the abilities of different frameworks. RESULTS A total of 255 patients with PCoA aneurysms and 20 patients without aneurysms were included in this study. The best AUC results of RetinaNet, RetinaNet+C-LSTM, Bi-input+RetinaNet and Bi-input+RetinaNet+C-LSTM were 0.95, 0.96, 0.92 and 0.97, respectively. The sensitivities of RetinaNet, RetinaNet+C-LSTM, Bi-input+RetinaNet, Bi-input+RetinaNet+C-LSTM, and human experts were 89.00% (67.02% to 98.43%), 88.00% (65.76% to 98.06%), 87.00% (64.53% to 97.66%), 89.00% (67.02% to 98.43%), and 90% (68.30% to 98.77%), respectively. The specificity of RetinaNet, RetinaNet+C-LSTM, Bi-input+RetinaNet, Bi-input+RetinaNet+C-LSTM, and human expert were 80.00% (56.34% to 94.27%), 89.00% (67.02% to 98.43%), 86.00% (63.31% to 97.24%), 93.00% (72.30% to 99.56%), and 90% (68.30% to 98.77%), respectively. The accuracies of RetinaNet, RetinaNet+C-LSTM, Bi-input+RetinaNet, Bi-input+RetinaNet+C-LSTM, and human experts were 84.50% (69.57% to 93.97%), 88.50% (74.44% to 96.39%), 86.50% (71.97% to 95.22%), 91.00% (77.63% to 97.72%), and 90.00% (76.34% to 97.21%), respectively. CONCLUSIONS A two-stage aneurysm detection system can reduce the time cost and the computational load. According to our results, more spatial and temporal information can help improve the performances of the frameworks so that Bi-input+RetinaNet+C-LSTM has the best performance compared to the other frameworks. Our study demonstrates that our system can assist doctors in detecting intracranial aneurysms on 2D-DSA images.

Subcellular and regional localization of mRNA translation in midbrain dopamine neurons

Local translation within excitatory and inhibitory neurons is involved in neuronal development and synaptic plasticity. Despite the extensive dendritic and axonal arborizations of central monoaminergic neurons, the subcellular localization of protein synthesis is not well-characterized in these populations. Here, we investigated mRNA localization and translation in midbrain dopaminergic (mDA) neurons, cells with enormous axonal and dendritic projections, both of which exhibit stimulation-evoked dopamine (DA) release. Using highly-sensitive ribosome-bound RNA-sequencing and imaging approaches in mDA axons, we found no evidence for axonal mRNA localization or translation. In contrast, mDA neuronal dendritic projections into the substantia nigra reticulata (SNr) contain ribosomes and mRNAs encoding the major components of DA synthesis, release, and reuptake machinery. Surprisingly, we also observed dendritic localization of mRNAs encoding synaptic vesicle-related proteins, including those involved in vesicular exocytic fusion. Our results are consistent with a role for local translation in the regulation of DA release from dendrites, but not from axons. Our translatome data further defined a molecular signature of the sparse mDA neurons resident in the SNr, including enrichment of Atp2a3/SERCA3, an ER calcium pump previously undescribed in mDA neurons.

Connectivity profile laterality in corticostriatal functional circuitry: a fingerprinting approach

An abnormal magnitude of hemispheric difference (i.e. laterality) in corticostriatal circuits is a shared feature of numerous neurodevelopmental and psychiatric disorders. Detailed quantitation and regional localization of corticostriatal laterality in normative samples stands to further the understanding of hemispheric differences in healthy and disease states. Here, we used a fingerprinting approach to quantify functional connectivity profile laterality (the overall magnitude by which a voxel's profile of connectivity with homotopic regions of the ipsilateral and contralateral cortex differs) in the striatum. Laterality magnitude heatmaps revealed laterality hotspots (constituting outliers in the voxelwise distribution) in the right ventrolateral putamen and left central caudate. Findings were replicated in an independent sample, with significant (p<0.05) spatial overlap observed between the location of the laterality hotspots across samples, as measured via Dice coefficients. At both hotspots, a primary driver of overall laterality was the difference in striatal connectivity strength with the right and left pars opercularis of the inferior frontal gyrus. Right and left striatum laterality magnitude maps were found to significantly differ (p<0.05) at the hotspot locations. Moreover, using subjects' left, but not right, striatum laterality magnitude maps, a support vector machine trained on a discovery sample (n=77) and tested on a replication sample (n=77) significantly predicted (r=0.25, p=0.028) subject performance on a language task, known for its lateralized nature. Laterality magnitude maps remained consistent across different cortical atlas parcellations and did not differ significantly between right handed and left handed individuals. In sum, meaningful variation in functional connectivity profile laterality, both spatially within the striatum and across subjects, is evident in corticostriatal circuits. Findings provide a basis to examine corticostriatal connectivity profile laterality in psychiatric illness.

Regional Localization of Mouse Brain Slices Based on Unified Modal Transformation

Brain science research often requires accurate localization and quantitative analysis of neuronal activity in different brain regions. The premise of related analysis is to determine the brain region of each site on the brain slice by referring to the Allen Reference Atlas (ARA), namely the regional localization of the brain slice. The image registration methodology can be used to solve the problem of regional localization. However, the conventional multi-modal image registration method is not satisfactory because of the complexity of modality between the brain slice and the ARA. Inspired by the idea that people can automatically ignore noise and establish correspondence based on key regions, we proposed a novel method known as the Joint Enhancement of Multimodal Information (JEMI) network, which is based on a symmetric encoder–decoder. In this way, the brain slice and the ARA are converted into a segmentation map with unified modality, which greatly reduces the difficulty of registration. Furthermore, combined with the diffeomorphic registration algorithm, the existing topological structure was preserved. The results indicate that, compared with the existing methods, the method proposed in this study can effectively overcome the influence of non-unified modal images and achieve accurate and rapid localization of the brain slice.

Using convolutional neural network and long short time memory to automatically detect aneurysm on 2D DSA images (Preprint)

BACKGROUND It is hard to distinguish cerebral aneurysm from overlap vessels based on the 2D DSA images, for its lack the spatial information. OBJECTIVE The aim of this study is to construct a deep learning diagnostic system to improve the ability of detecting the PCoA aneurysm on 2D-DSA images and validate the efficiency of deep learning diagnostic system in 2D-DSA aneurysm detecting. METHODS We proposed a two stage detecting system. First, we established the regional localization stage (RLS) to automatically locate specific detection region of raw 2D-DSA sequences. And then, in the intracranial aneurysm detection stage (IADS) ,we build three different frames, RetinaNet, RetinaNet+LSTM, Bi-input+RetinaNet+LSTM, to detect the aneurysms. Each of the frame had fivefold cross-validation scheme. The area under curve (AUC), the receiver operating characteristic (ROC) curve, and mean average precision (mAP) were used to validate the efficiency of different frames. The sensitivity, specificity and accuracy were used to identify the ability of different frames. RESULTS 255 patients with PCoA aneurysms and 20 patients without aneurysm were included in this study. The best results of AUC of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 0.95, 0.96, and 0.97, respectively. The sensitivity of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 81.65% (59.40% to 94.76%), 87.91% (64.24% to 98.27%), 84.50% (69.57% to 93.97%), respectively. The specificity of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 88.89% (66.73% to 98.41%), 88.12% (66.06% to 98.08%), and 88.50% (74.44% to 96.39%), respectively. The accuracy of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 92.71% (71.29% to 99.54%), 89.42% (68.13% to 98.49%), and 91.00% (77.63% to 97.72%), respectively. CONCLUSIONS Two stage aneurysm detecting system can reduce time cost and the computation load. According to our results, more spatial and temporal information can help improve the performance of the frames, so that Bi-input+RetinaNet+LSTM has the best performance compared to other frames. And our study can demonstrate that our system was feasible to assist doctor to detect intracranial aneurysm on 2D-DSA images.

Cooperative employment cycles in Spain. Does regional localization matter?

This paper presents a territorial analysis of the cooperatives within various Spanish regions. The purpose is threefold. The first objective is to investigate whether the cooperatives’ employment cycle shows a different relationship regarding the business cycle and whether this depends on the regional localization of the cooperatives. The second is to evaluate whether the greater the cooperative tradition, the greater the decoupling between business cycle and cooperatives’ cyclical phases. The third objective is to find out if, within the different Spanish regions, those cooperatives that survived the 2008 crisis share some common patterns. Our results show that (1) more than 50% of the regions achieve a medium degree of a pro-cyclical relationship and that only a small group of regions presents a counter-cyclical relationship; (2) the cooperatives' employment exhibits a certain degree of resilience; and (3) the cooperatives that survived the crisis were mature, small-sized firms with adequate financial ratios but with a negative profit margin.

The question of structural changes in the territorial location of milk production in the Leningrad Region

Modern features of the territorial structure of milk production in a separate region are considered. The purpose of the study was to analyze the dynamics of dairy cattle breeding in the Leningrad region in the territorial aspect for 2008–2018. The main method of research was economic and statistical analysis of data and their comparative evaluation. Results. The specificity of quantitative and qualitative changes in milk production by category of farms has been revealed. In the context of municipal districts of the Leningrad region, they were grouped depending on the growth rate (decrease) in the volume of milk produced in farms of all categories in 2018 compared to 2008. Adverse trends in the development of dairy cattle breeding in agricultural organizations of the region were noted, as their share in milk production decreased in 13 municipal districts of the Leningrad region. Changes in the volume of state support for the dairy cattle industry in the region in the territorial aspect for the specified period were determined. It is revealed that, despite the subsidies in milk production, increased its intra-regional localization. As a result, in 2018, more than 50 % of the volume of regional milk production was provided by only 4 districts of the Leningrad region. In the remaining 13 districts, there are no prerequisites for employment and rural development, and the reduction in milk production in rural areas has reached 48.3 %. The necessary measures are proposed to smooth out the territorial unevenness in milk production as a condition for overcoming the depressiveness of rural development. The scientific novelty of the study is to assess the nature of the emerging territorial features of the placement of milk production in the Leningrad region and its intraregional differentiation.