Neuroinformatics

We present a free and open-source, semi-automated, topologically robust pipeline for fitting cable models to 3D surface mesh morphology data of neuronal membranes, particularly suited to structures with complex shapes and topological holes. The motivation for this work is the discovery of morphologically complex neural spines on the auditory space-specific neurons of the barn owl (Tyto alba, Tyto furcata), dubbed "toric spines", notable for their high curvature, branching density, and holes/loops. Multicompartmental simulation software requires morphology to be represented as cable models (e.g., SWC format), yet existing software tools for fitting cable models to complex 3D surface meshes have not produced satisfactory results for toric spines, and loops are generally unsupported. We present the Mesh and Skeleton Cable Fitting (MASCAF) pipeline and software, which fits a cable model (e.g., SWC format) to a surface mesh using mean-curvature flow skeletonization. In this paper, we demonstrate how MASCAF is applied to fit cable models, how loops can be reconstructed in simulations with the Arbor and NEURON simulation software, and how the results can be validated using geometry and simulator-based methods. While non-tree morphologies such as toric spines are neuroanatomically special, our software pipeline provides a cable-model fitting approach for surface mesh data that is topologically robust, deterministic, open-source, and applicable to general morphologies, thereby closing a crucial gap between neuronal imaging and high-resolution simulation.

Background and ObjectiveNormative modeling is a key tool for understanding brain alterations in neurodegenerative diseases, such as cerebellar-type multiple system atrophy. However, existing methods lack interpretability and fail to capture clinically meaningful pathological changes. This study presents DINMC, a Deep Interpretable Normative Model Construction framework, which combines autoencoder-based learning with statistical hypothesis testing to better capture and interpret disease-specific neu-roanatomical changes. MethodsThe DINMC framework constructs normative models using neuroimaging data from multi-site large healthy cohorts. It utilizes a U-shaped convolutional autoencoder to train these models, which are then applied to reconstruct brain features from both patients and healthy controls within the same study cohort. Pathological confidence values are derived by fusing original and deviation feature spaces, offering a measure of disease-related pathology reflected in each dimension of the features. The framework was validated through statistical analysis and prognostic classification and regression tasks. ResultsThe pathological confidence provides valuable insights into the neuroanatomical regions most affected by the disease, as well as the correlation between changes in these regions and clinical assessment scales. Our optimal model outperform traditional methods in prognostic prediction tasks, with an AUC of 0.972 for classification tasks and an R2 of 0.432 for regression tasks. ConclusionDINMC provides a novel and interpretable framework for neuroimaging analysis. By combining deep learning and statistical hypothesis testing, this framework offers a unique solution to improving both the interpretability and performance of normative models in neuroimaging. The approach is scalable to other neuroimaging datasets, offering a versatile tool for broader biomedical applications.

Despite growing understanding of the benefits of having Findable, Accessible, Interoperable, and Reusable (FAIR) data, many datasets still cannot be shared. Federated analysis methods can enable multisite studies that do not require the sharing of participant-level information. However, there are many practical hurdles that prevent the large-scale adoption of federated methods. We discuss challenges related to cross-site data preparation for federated learning, present solutions offered by recent neuroinformatics projects, and showcase an example of tool integration applied to neurodegenerative disease data.

We propose a study protocol for routine clinical electroencephalograms (EEGs) from public hospitals, which represents a vast resource for neuroscience research. These non-invasive measures of brain function, paired with rich clinical annotations from large and diverse patient populations, are critical for developing robust artificial intelligence (AI) models and conducting population-level studies. This protocol presents a scalable methodology for curating and harmonizing extensive clinical EEG datasets, encompassing over 40,000 individual studies, to facilitate research applications. Key steps include: (i) integration of raw EEG recordings with corresponding clinical records, including neurological reports, diagnostic codes, and potentially medication data; and (ii) spatial standardization of EEG signals by mapping them to a common brain space defined by functional and anatomical landmarks. The resulting harmonized datasets enable the development of large-scale EEG foundation models, the discovery of novel EEG waveform representations, and the creation of normative "brain charts" for electrophysiological assessment across the lifespan. By enabling standardised, large-scale analyses of real-world clinical EEG data, this protocol supports data-intensive solutions for EEG applications and addresses the challenge of generalising AI models. Our approach promotes the translation of AI tools from research to diverse patient populations, advancing population neuroscience.

Three-dimensional (3D) whole-organ imaging and analysis at cellular resolution (termed 3D histology) provide profound insights into the organization and interactions of cells throughout organs. However, the quantitative analysis of these massive datasets remains a significant bottleneck due to the lack of integrated, user-friendly tools. Here, we present 3DBrainOne, an end-to-end ImageJ plugin that streamlines the essential 3D histological analysis of the mouse brain--from raw image preprocessing to region-wise quantification--within a single platform. 3DBrainOne features a robust whole-brain cell-counting module that uses a Difference-of-Gaussians (DoG) blob detection algorithm followed by a ResNet18-based deep learning classifier, enabling high-fidelity automatic whole-brain cell counting with a graphical user interface (GUI) for visual inspection and manual curation of analysis results. 3DBrainOne also supports multi-channel colocalization analysis. Furthermore, this platform includes modules for atlas alignment and brain-region-wise volumetric quantification, enabling brain region-resolved cell counting and structural analyses. As an ImageJ plugin, 3DBrainOne is compatible with a range of operating systems and hardware. In summary, 3DBrainOne is an integrated, versatile, and easy-to-use platform that will facilitate 3D histological analyses in experimental neuroscience.

Structural connectivity (SC) data are crucial for brain network analysis, but SC-based machine learning often suffers from limited data availability, hindering model generalization and robustness. Although data augmentation using deep generative models has attracted increasing attention, it remains unclear how different models capture the complex topological features of SC data. To clarify the learning characteristics of deep generative models for SC generation, this study compares three representative models: variational autoencoder (VAE), Wasserstein GAN with gradient penalty (WGAN-GP), and denoising diffusion probabilistic models (DDPM). We systematically evaluated these models using both synthetic datasets with known characteristics and real-world SC data. Generation quality was assessed using graph-theoretic metric comparisons and visual inspection of the generated adjacency matrices. WGAN-GP showed relatively stable performance across datasets and metrics, without severe performance degradation across evaluation settings. In contrast, VAE and DDPM performed well in specific aspects but were more sensitive to data characteristics. These findings suggest that WGAN-GP may serve as the most balanced baseline for future SC data augmentation studies, whereas VAE and DDPM may be useful depending on the target application and structural properties of interest. Furthermore, because all models struggled to fully reproduce strict global constraints such as planarity, our results suggest that standard generative models may be insufficient to capture the complex topological features of SC data. This highlights the importance of incorporating the desired structural properties into the training or generation process.

Abnormal states such as erroneous behaviors are generally difficult to represent from neural data. However, such states are also known to have specific spatiotemporal features, indicating a feasibility of developing a method to focus on them. If a method can highlight these spatiotemporal features, it may effectively represent such abnormal states, helping evaluate abnormal brain functions. In the present study, we proposed the hierarchy of supported modules (HSM) to highlight spatiotemporal features that can represent abnormal states. HSM spatiotemporally transforms multidimensional neural time-series based on their spatiotemporal context. We evaluated HSM through decoding and similarity analyses using multiple publicly available datasets. In the HSM results, decoding accuracies were higher for erroneous behaviors than for normal behaviors, and similarities were lower between erroneous behaviors and normal behaviors than between normal behaviors, demonstrating the ability of HSM to capture the spatiotemporal features of erroneous behaviors. Surprisingly, many parts of these results were also present even before HSM learning, showing the virtue of HSM as a simple-to-use method. The proposed HSM method may help elucidate the mechanisms underlying erroneous behaviors.

Introduction Understanding the mechanisms of human neuromaturation constitutes one of the fundamental questions of neuroscience. While it is well described that large-scale brain maturation is initiated within sensorimotor brain regions and progresses to associative cortex, the underlying developmental neurobiology remains to be fully characterized. Animal models have indicated that cortical inhibitory upregulation might be a driver of neurodevelopment. To investigate the hypothesis that cortical inhibitory upregulation plays a similar role in human neuromaturation, we developed a The Virtual Brain (TVB) based computational model (TVB-Child) to explore potential mechanisms of human neurodevelopment. Material and method We created neurodevelopmental dynamic brain network models capturing neurobiological maturation by using the large-scale brain simulator TVB and fitting brain network models to developmental functional MRI (fMRI) from the Human Connectome Project-Development (HCP-D) data set with 640 subjects with an age range of 6-21 years. Age-dependent trajectories in the fMRI data set were first analyzed by combined group-ICA/Dual Regression extracting subject-specific resting-state networks (RSN). Maturational topographical and topological redistribution of these networks were analyzed by linear and non-linear regression of RSN size and degree and strength centrality. Brain network models were fitted to the fMRI functional connectivity obtained from the HCP-D data set. Hypothesizing that cortical inhibition is a driver of neuromaturation, we analyzed spatiotemporal inhibition parameter gradients in the dynamic brain network model for the hypothesized significant correlations with fMRI RSN maturational trajectories. Results While during development frontoparietal (FP) and default mode network (DMN) grew and exhibited an increase in both degree and strength centrality, becoming dominant network hubs, the attention network underwent network pruning with a decrease in size and node degree. The primary sensory network changed little. For the fitted brain network models, we obtained a high degree of reproduction with correlation coefficients between empirical and simulated functional connectivities ranging between 0.80 and 0.95. Values of the feed forward inhibition model parameter wijFFI representing the strength of regional feedforward inhibitory input exhibited the most significant increase with age within the FP and DMN networks. A less pronounced, but significant, age-dependent increase of the inhibitory parameter values were seen in attention networks and no change within primary sensory networks. Conclusion Our study shows that high order (FP, DMN), attention and primary sensory networks exhibit distinct topographical and topological maturation trajectories. Moreover, brain network modeling revealed RSN-specific age-dependent inhibition trajectories, indicating that the model is able to reproduce and thus support candidate mechanisms of neurodevelopment.

AO_SCPLOWBSTRACTC_SCPLOWThe integration of electrophysiological recordings with multimodal neuroimaging data holds great promise for advancing our understanding of brain function and neurological disorders. To facilitate this endeavour, we present electro-MICA, an open-access Python toolbox designed to project electrophysiological features from scalp and intracranial electroencephalography (EEG) onto cortical and hippocampal surfaces generated by validated multimodal imaging ecosystems. The toolbox comprises two pipelines: one for intracranial EEG (iEEG) recorded with stereo-EEG depth electrodes, and one for scalp EEG source localization. Both pipelines are grounded in numerical solutions to the electromagnetic equations governing electric activity in the brain, solved using the Boundary Element Method. A key methodological contribution is the use of a current density double layer model for neural generators, which avoids the mathematical singularities introduced by conventional dipole-based models when electrodes are near the cortical surface, a situation that can arise in iEEG. Electrode contacts are additionally modeled with non-zero length, improving physical realism. Scalp EEG source localization is performed using eLORETA on a subject-specific three-layer head model derived from the anatomical input. Validation against empirical gamma-band iEEG data from 32 subjects demonstrates that the distributed generator model outperforms both distance-based and dipole-based alternatives. An illustrative clinical example demonstrates the toolboxs capacity to reveal associations between intracranial spike rates, cortical thickness, and anatomical connectivity in an epilepsy patient. Electro-MICA requires no parameter selection from the user, facilitating straightforward multimodal analyses in both research and clinical settings. The toolbox is available at github.com/MICA-MNI/electromica with extensive online documentation at electromica.readthedocs.io.

Mapping hierarchical brain networks within traditional Euclidean space causes significant structural distortion, undermining neuroimaging diagnostic frameworks. While hyperbolic models like the Poincare ball preserve these nested topologies, they demand heavy computational overhead due to intricate Mobius operations and curved geodesics. This paper introduces a highly efficient non-Euclidean framework for analyzing neurocognitive decline utilizing the Beltrami-Klein ball model. By projecting hyperbolic geodesics as Euclidean straight lines, this approach converts complex distance calculations into simple dot products, radically reducing processing demands. We validated our methodology against state-of-the-art Poincare and Lorentz baselines using datasets for Schizophrenia, Parkinsons Disease, and Alzheimers Disease. The Klein-based framework demonstrates superior performance, delivering both higher diagnostic precision and accelerated processing velocities across all three neurocognitive disorders.

Neurophysiology datasets are becoming increasingly complex, combining behavioral measurements with high-dimensional neuronal activity recordings coming from optical and/or electrophysiological measurements. The Neurodata Without Borders (NWB) standard has emerged in the community as the format of record. While standardized and widely used preprocessing tools generating NWB files have been developed, extensible frameworks for scientific analysis downstream of the NWB ecosystem are still under-represented. We present CICADA, a Python framework dedicated to analysis of neurophysiological data in the standardized NWB format. The toolbox is built as three hierarchically-organized packages: cicada-nwb (NWB access layer), cicada-analysis (plugin-based analysis engine and tool library), and cicada-gui (PyQt5 desktop application at the head of the pipeline). Beyond this architectural separation, CICADA is built around a central design principle: supporting a continuum from turnkey use to full modularity. Researchers can use the complete GUI-driven cicada-gui workflow without writing code, programmatically use existing analysis plugins from cicada-analysis, contribute to new analysis plugins, reuse utilities from cicada-tools, or build entirely custom pipelines on top of the cicada-nwb access layer alone. The same analysis plugin runs identically in interactive GUI and parameter-configured headless modes, enabling reproducible multi-session, multi-animal group analyses. We illustrate the versatility of CICADA with example analyses of behavioral, calcium imaging (two-photon and widefield) and extracellular electrophysiology datasets from rodent laboratories. CICADA is open source, actively maintained, and designed so that any laboratory can contribute at any level of the stack without modifying the core framework.

Understanding vascular contributions to disease is a major unmet need. White matter lesions (WML) are an accepted imaging marker of cerebral small vessel disease, giving insights into its related pathologies. A unified approach for WML analyses in large multi-site data is lacking despite the need for pooling of data to overcome the limitations of often small heterogenous MRI studies which make subtyping and identifying patterns within disease groups difficult. Our ENIGMA-PD-WML pipeline is an open-source containerized pipeline containing all the code and packages required for pre-processing, processing and post-processing of T1-weighted and FLAIR data, outputting accurate and reproducible binary WML maps using a UNet approach. The pipeline provides a standardized image analysis approach for WML and outputs data in both native and MNI space to allow for sharing and pooling of data from multiple sites for large-data analysis. In addition to a reliable standardized approach for WML segmentation, key priorities when developing the pipeline included: usability, i.e., requiring minimal manual input and technical expertise to use, and suitability to run on various MRI scanners and acquisition parameters as is common in multi-site data. This paper describes the pipeline in detail, with rationale for each step, providing transparency and facilitating its usage to overcome reproducibility issues in large-scale WML analyses.

BackgroundMagnetoencephalography (MEG) is a unique technique in human neuroimaging combining high temporal resolution (millisecond or faster) with moderate spatial resolution (several millimeter). While many software packages for MEG data analysis exist, there is no pipeline developed for the specific purpose of enabling the automated analysis of very large, multi-site datasets. ResultsThe ENIGMA consortium was developed to enable large scale collaborations in the fields of neuroimaging and genetics. To facilitate ENIGMA MEG working group data analysis, we developed the ENIGMA MEG pipeline. The first ENIGMA MEG working group project involves spectral analysis of resting state MEG data, thus our current pipeline is designed to carry out that task. The goals of the ENIGMA MEG pipeline include ease of use, automated processing wherever possible, detailed logging and quality assurance (QA) features, the use of the brain imaging data structure (BIDS) format, anonymized output, and consistent processing across vendors. The pipeline is built using the MNE-Python framework and incorporates a re-trained version of the MEGnet deep neural network algorithm for automated artifact detection. QA tools are designed to enable high throughput evaluation of a large number of subject datasets. All software is open source and available on GitHub (https://github.com/nih-megcore/enigma_MEG). We used our pipeline to process data from three publicly available MEG cohorts, demonstrating its functionality and compatibility with large-scale processing. ConclusionsWhile the current ENIGMA pipeline is limited to resting state data and spectral analysis for the current working group project, the software is highly modularized, allowing straightforward extension to other analysis questions. Further development of the tool to enable connectivity and task-based MEG analysis are planned. The ENIGMA MEG pipeline represents an important first step to augment the existing arsenal of analysis tools, enabling multi-site, high throughput data analysis.

BackgroundThe relevance of spontaneous activity has been unlocked thanks to recent large scale recordings that revealed, via Shared Variance Component Analysis (SVCA), the high-dimensional nature of the ongoing activity. A fundamental problem is how the dimension modifies when more neurons are included in the analysis. Contradictory results have been reported on this subject based on SVCA and Principal Component Analysis (PCA). New MethodWe investigate pro et contra of SVCA and PCA for the identification of reliable responses encoding underlying state variables. We focus on common features of the spectra of the reliable variances (RVs) and on their dimensionality. The analysis is demonstrated on previously published Ca2+ data from the visual and the dorsal cortex in head fixed mice during spontaneous behavior. ResultsRVs grow proportionally to the number N of neurons and show a power-law decay k- with the k-th SVC dimension over a range bounded by a maximal dimension kc, initially diverging as N 1/ and then saturating at sufficiently large N. The reliable dimensionality, estimated with different methodologies, also shows a clear saturation to an asymptotic value for large N. Furthermore, its value decreases when becomes larger, as demonstrated by employing experimental data as well as theoretical predictions. ConclusionWe have shown that SVCA is an extremely effective tool to extract reliable features from the neural signals, and that the exponent represents a biomarker able to reveal the level of correlation of the neurons as well as the dimensionality of the reliable space. HighlightsO_LIAdvantages and drawbacks of Shared Variance Component Analysis to extract reliable signals from neural data C_LIO_LIComparison of different methods to estimate reliable neural dimensionality associated to spontaneous activity C_LIO_LIAnalytical expressions of embedding dimensionality for power-law decaying reliable variances C_LIO_LIBounded growth of the dimensionality with the number of neurons C_LI

Neuroimaging data management and processing are tedious and error-prone, prompting reproducibility concerns. Globally, studies with heterogeneous infrastructure and governance policies lead to eclectic data processing and sharing, necessitating standardization of data workflows to ensure reusability and comparability of multi-centric datasets. The Nipoppy neuroinformatics framework facilitates such standardization by combining specification, protocol, and software to manage study-level data workflows. With its adoption, researchers can share standardized, derived datasets enabling efficient, reproducible, and inclusive research.

Currently, there is no consensus about how investigators should format their NIBS data for sharing. This presents a barrier to the advancement of big data analyses because it requires time-consuming operations to generate consistent formats across different shared datasets. Recently, we launched Big non-invasive brain stimulation data (Big NIBS data), an open-access platform and repository for NIBS data (https://www.bignibsdata.com/), providing a structured mechanism for researchers to share NIBS data. However, the reusability and interoperability of data uploaded to Big NIBS data is restricted by the absence of a common data structure. The current paper addresses this problem by creating the NIBS data analysis structure (NIBS-DAS), a template pipeline for the layout, management, and analysis of collated NIBS outcome data. While its primary purpose is to provide a template layout for uploading collated data to the Big NIBS data repository, NIBS-DAS also offers guidelines for the management and analysis of collated NIBS data, thereby forming a data analysis pipeline that can be freely used by the NIBS field in general. We anticipate that NIBS-DAS will serve to facilitate data sharing on the Big NIBS data platform and promote greater standardisation of data management and analytical practices in the NIBS field.

The human cerebellum plays a central role in motor, emotional, and cognitive functions, and is implicated in many brain disorders. To improve the analysis of functional and anatomical imaging from the cerebellum, we introduce SUITPy, an improved and fully revised Python implementation of the widely used SUIT toolbox. For this new version, we developed a U-Net based model to automatically isolate the cerebellum from adjacent cortical tissue, which achieves higher fidelity than existing algorithms. The isolation works robustly without manual corrections for imaging data across the lifespan. We show that isolation and subsequent normalization to a cerebellum-only template lead to a more precise alignment of cerebellar structures across participants compared to normalization using a whole-brain template. We also show the utility of the cerebellar mask to prevent contamination of cerebellar functional data from surrounding cortical structures. The toolbox also provides functionality for visualizing cerebellar data on a flatmap, along with a range of anatomical and functional cerebellar atlases, thereby offering an essential tool that enables accurate cerebellar analysis across the lifespan.

Connectomic reconstruction from large image volumes produces segmentation and synaptic-assignment errors that must be resolved to support downstream analyses. As datasets have grown larger and teams more distributed, proofreading has become a critical operational bottleneck. Workflows for proofreading and error correction have not scaled commensurately with connectomic data production and may not accommodate heterogeneous proofreader expertise and machine-generated candidate edits. New tools are therefore needed to organize, prioritize, and coordinate proofreading at volume scale. Here we present NeuVue, a task-management and prioritization framework that operationalizes proofreading through atomic, auditable tasks for individual and team review, multistage routing across proofreader cohorts, performance and volume-state tracking, and integration with community annotation, visualization, and analysis services. We report the use of NeuVue across two volumetric datasets, supporting scalable proofreading by over forty proofreaders and producing over fifty thousand edits. NeuVue provides a reproducible human-in-the-loop framework for generating, validating, and maintaining large connectomic datasets.

Hippocampal area CA2 has recently emerged as a critical region for social recognition memory. Furthermore, this understudied region has been implicated in psychiatric diseases and neurodegenerative diseases. There has been accumulating evidence indicating that the pyramidal neurons (PNs) in area CA2 exhibit functional specializations that correlate with somatic position in stratum pyramidale (sp). In this study, we investigated the morphological differences in dendritic architecture of CA2 PNs with a focus on the radial gradient, i.e., along the deep-superficial axis of the sp. We conducted a comprehensive morphological analysis including Sholl intersection profiles, branching order distributions, root angle distributions, and dendritic cable lengths. We found that CA2 PNs have fewer oblique dendrites and a larger number of tuft-like dendrites as compared to CA1 PNs. Furthermore, within the CA2 population, we found that many of the dendritic structural features gradually changed along the radial axis from deep to superficial somatic location, indicating a continuum of dendritic morphology rather than two sharply defined subtypes of pyramidal neurons. This morphological characterization may serve as a starting point to better understand the corresponding functional organization of CA2. The gradual difference between deeper and superficial CA2 PNs suggests a continuum of their computational capabilities beyond two binary functional classes. In briefUsing several methods, we examine the dendritic morphology of over 130 CA2 and CA1 pyramidal neurons and find that many properties such as the cable length and terminal numbers of the dendritic arbors vary as a with the location of the soma in the pyramidal layer. HighlightsO_LIWe use scholl analysis, graph theory and machine learning techniques to quantify the different dendritic morphologies of CA2 pyramidal neurons. C_LIO_LIMany properties of CA2 pyramidal neuron apical dendrites vary as a function of somatic location in the pyramidal layer. C_LIO_LIMore superficial CA2 pyramidal neurons have longer oblique apical dendrites, and shorter tuft dendrites. C_LI

Quantitative analysis of microscopic images has become a standard in basic biological and biomedical research. Deep machine learning provided a powerful tool facilitating this process. However, practical adoption of deep machine learning to image analysis may be difficult for a researcher who lacks basic coding skills. This is caused by a limited number of non-coding solutions, specifically in the domain of convolutional neural networks (CNNs). This scarcity may be explained by the following paradox. Training of CNNs is a relatively complex process. Researchers who are familiar with this process are also skilled enough to code the full pipeline of CNN implementation from annotation, through model training and evaluation to its usage in laboratory practice. Any kind of an alternative solution, acceptable by a broader group of researchers who are unfamiliar with CNN concepts, must inevitably result in simplification of the entire process, specifically the training step. Such simplification in turn may lead to limitation to solve specific problems by such a tool. Author believes however, that some compromise may be found between complexity and simplicity that would be sufficient to solve some basic problems in the field of basic biological and biomedical research. To address this challenge, author proposes ATI_Box (Annotation, Training, Inference in One Box), a unified, user-oriented platform for end-to-end image semantic segmentation. The system integrates data annotation, storage, model training, evaluation, and quantitative analysis into a single workflow, significantly simplifying the model development process. Image and annotation data are managed through an S3-compatible object storage system (MinIO), enabling scalable and transparent data handling. Annotation process is implemented through Label Studio. Model training is based on convolutional neural network U-Net architecture with ResNet as an encoder. Model evaluation is performed on ground-truth dataset held-out during training and provides pixel-level and object-level evaluation metrics. Batch analysis mode enables automated quantification of model predictions such as object counts and coverage areas. The usability of the platform was presented on examples from laboratory practice. The platform is intentionally devoid of model-tuning capabilities as it is addressed to users unfamiliar with profound machine learning concepts. At the same time, accessibility of such basic features of model training as definition of epochs number or saving and implementing of trained model versions enables one to perform some basic analytical experiments. As such, the platform may serve not only as an analytical tool but also as an educational solution to explain practical basics of semantic segmentation process.