Frontiers in Neuroinformatics

The Hierarchical Gaussian Filter (HGF) is a hierarchical Bayesian model of learning under uncertainty and volatility, with a widely used MATLAB implementation. We present HGFX 1.0.0, a Python/JAX toolbox whose primary objective is validated behavioral and numerical compatibility with a frozen HGF Toolbox 8.2.0 reference, while removing MATLAB as a user-runtime dependency. Reimplementation is treated as a validation problem rather than source translation: configuration semantics, parameter transforms, forward trajectories, observation likelihoods, objectives, fitting and statistical surfaces, simulation workflows, official demo behavior, model selection, and backend agreement are compared against the pinned oracle under predeclared tolerances. Two official MATLAB demo workflows reproduce the reference at frozen trajectory tolerances, including a regime in which classic HGF encounters negative posterior precision while eHGF completes successfully. In paired model-selection validation, all 36 BIC winners agree between MATLAB and HGFX. Physical NVIDIA GPU applicability was confirmed on two Tesla T4 devices, with a maximum CPU-versus-GPU final-objective difference of 1.42e-14 against a frozen 1e-7 criterion. Historical parameter recovery results that did not meet predeclared criteria, together with exact MATLAB/HGFX limitation matches, are preserved and are not reclassified as scientific success. A prospectively gated comparison with pyhgf 0.3.2 shows binary64-scale agreement on mapped perceptual trajectories in one authorized three-level binary-HGF cell, while participant-response negative log-likelihood is retained as not directly comparable. HGFX therefore provides a MATLAB-independent Python implementation with an explicit evidence model that separates direct parity, matched reference limitations, backend applicability, and future performance claims.

Neuroimaging research focusing on subcortical brain regions showed that they play a role in a wide range of cognitive functions and associated their structural alterations to various psychiatric disorders. Methods to analyse such structures were developed to observe changes, not simply in terms of volumes, but in terms of surfaces, which are able to detect subtle and local changes in shape and geometrical configuration. Such advanced analyses have however been largely restricted to command line environments with relatively limited access to Python users or researchers with low technical expertise. We present SubCortexMesh as a user-friendly toolbox which covers automated surface estimation from popular subcortical volume segmentations (FreeSurfer and the Functional Magnetic Resonance Imaging of the Brain Software Library (FSL)), computes shape-related vertex-wise metrics (thickness, surface area and curvature) for whole cohorts and includes statistical analyses. This is all done inside Python, automatically computing all subjects of a given preprocessed directory, with the explicit intent to minimise steps and manual coding required from the users. SubCortexMesh includes statistical tools which allow conventional random field theory-based cluster analyses on native subject metrics, standardised within common surface templates, thus containing a whole workflow necessary to run an up-to-date shape-wise subcortical analyses in one package.

Simplified spiking neuron models such as the Adaptive Exponential Integrate-and-Fire (AdEx) model reproduce the firing behaviour of diverse neuron types at a fraction of the cost of biophysically detailed models, making them attractive for large-scale brain simulation. Fitting their parameters to recordings, however, still relies on derivative-free search such as grid search or evolutionary algorithms, because the discrete spike-and-reset mechanism renders these models non-differentiable. Surrogate gradients, used in deep spiking networks, replace the spike derivative with a smooth approximation on the backward pass. Whether they also enable efficient gradient-based parameter estimation for single simplified neurons is untested. We implement a differentiable AdEx model with a surrogate-gradient variant in the Jaxley framework. The implementation is on par with target-compiled C++ Brian2 code while remaining end-to-end differentiable, vmap-batchable and GPU/TPU-portable. It is 200 times faster than Brian2's default runtime mode. Across a recovery-radius benchmark of 2,700 paired runs, gradient-based fitting never matched a gradient-free Nelder-Mead baseline. At sub- threshold levels, gradient descent instead beats Nelder-Mead. The obstacle is therefore the spike mechanism and the loss geometry it induces, not gradient descent itself.

Independent component analysis (ICA) is widely used to remove artefacts from EEG and TMS-EEG recordings, but the components that correspond to artefacts are usually identified by manual inspection, which is subjective and difficult to reproduce. Existing automated classifiers are either designed for ordinary EEG and do not target the artefacts specific to concurrent transcranial magnetic stimulation, or are built on EEGLAB, so none is available for FieldTrip-based pipelines. We present TEFAR, a lightweight, configurable framework for semi-automatic artefact-component classification that applies the same detectors to ordinary EEG and TMS-EEG. TEFAR is built on FieldTrip and requires no additional MATLAB toolboxes. Each artefact class (line noise, blinks, lateral eye movements, cranial muscle, cardiac activity, and the TMS decay and recharge artefacts) is identified from the spectral, spatial, or temporal signature that its components are known to express. Detection thresholds use robust statistics (the median and the median absolute deviation rather than the mean and standard deviation), so that a single dominant artefact component cannot raise the threshold that is meant to detect it. In 30 ground-truth simulations, TEFAR reached a specificity of 1.000 and a sensitivity of 0.96-0.97 for both profiles. An application of TEFAR to real EEG and TMS-EEG recordings is the next step and will be reported separately.

Deep learning models for electroencephalography (EEG) pathology detection achieve competitive accuracy but offer limited interpretability. In this paper, we introduce concept bottleneck models (CBMs) for EEG pathology detection which use clinical EEG biomarkers computed analytically from the signal as a bottleneck to be used for prediction. Those concepts include band power, spectral ratios, alpha peak frequency and amplitude, hemispheric asymmetry and phase locking values. With the backbone based on shallow convolutional neural network (CNN), we compare a black box baseline with two variants of CBMs. The hybrid variant is a classifier receives a residual projection of the backbone features. The pure variant is a CBM where the classifier receives only the predicted concepts. Models are evaluated on abnormality detection and dementia classification followed by concept prediction quality and leakage analysis. Both CBMs approach the baseline on TUAB (82.7-82.9% vs 83.6%) and are 2-5 percentage points lower on CAUEEG (57.9-60.5% vs 62.7%). The pure CBM exhibits concept fidelity concern where the predicted concepts deviate from their ground truth values. Replacing them with their true values causes severe cost on accuracy by 26 and 22 points on TUAB and CAUEEG. The concept fidelity concern is mitigated by increasing the weight of the concept loss to match the ground truth concepts. the mitigation comes with small accuracy cost on TUAB but a relatively larger cost on CAUEEG. The code of the experiments and full logs are available at https://www.github.com/mhmdrdwn/cbm.

Large-scale biophysically-detailed models of the brain are instrumental in unraveling how cellular, synaptic, and circuit-level mechanisms contribute to neural dynamics. Such models are built around large populations of single-neuron models whose morphologies must preserve physiological variability to reproduce integrative properties and firing patterns observed experimentally. Experimental reconstruction of morphologies is a time-consuming and resource-intensive process, unlikely to supply them at the required scale. Several data-driven methods for morphology synthesis have been developed, which nonetheless rely on extensive datasets for parameter estimation. To address this limitation, we developed NeuWalk, to our knowledge the first public Python library for morphology synthesis based on branching-and-annihilating, biased-and-correlated random walks. It estimates branching and annihilation rates from Sholl intersections and, optionally, bifurcation counts, while also ensuring their replication in synthetic morphologies; user-specified combinations of biases, implementing somatofugality, self-avoidance, spatial competition, and branching-angle control, sculpt morphological patterns characteristic of each neuron class. We then validated the method on mitral and middle tufted cells of the olfactory bulb, semilunar and pyramidal cells of the anterior piriform cortex, and neocortical pyramidal neurons: means and variances of Sholl intersections, bifurcation counts, and total dendritic length were statistically indistinguishable between synthetic and natural morphologies, with the single exception of its variance in apical dendrites of piriform cortex pyramidal neurons. As Sholl intersections and bifurcation counts are commonly reported in the literature, and biases can be inferred from published images or qualitative descriptions, NeuWalk requires no immediate access to experimental reconstructions, striking a trade-off between data-driven parameterization and empiricism without sacrificing morphological accuracy.

Deep brain stimulation (DBS) is a well-established therapy for various neurological disorders. Clinical outcomes of DBS depend on electrode placement and stimulation programming, with growing evidence suggesting that targeting specific sites and networks can improve therapeutic efficacy. This targeting can be facilitated using high-accuracy, multi-modal biophysical models. In this article, we present the open-source platform OSS-DBS v2 that enables researchers and clinicians to build such biophys- ical models. Building upon previous work, the new version combines automated volume conductor generation, accurate and efficient electric field modelling and stimulation-driven neural simulations. OSS-DBS v2 provides an extensive library of intracranial electrodes, which can be modelled simul- taneously to test complex stimulation paradigms. Its application programming interface facilitates integration of external data workflows, such as impedance measurements. Furthermore, an integration with the Lead-DBS toolbox offered a straightforward graphical user interface for stimulation volume and pathway activation modelling, further complemented by an optimization framework. OSS-DBS v2 relies entirely on open-source software, supports all major operating systems and is designed for efficient execution on consumer-grade hardware.

Many studies using mouse models of human brain disorders rely on extended recordings of brain electrical activity through electroencephalogram, or EEG. The features that researchers measure in these recordings, such as seizures and epileptiform activity, are deeply influenced by whether the animal is awake, in non-rapid eye movement (NREM) sleep, or in rapid eye movement (REM) sleep. Because total sleep duration varies naturally across animals, rigorous experimental comparisons require classifying the sleep state of every few seconds of a recording. Manual annotation is highly labor-intensive, often requiring hours per subject. While automated scoring tools accelerate this process, they are typically trained exclusively on healthy cohorts and frequently fail when applied to disease models that exhibit atypical or fragmented sleep architecture. Somnus is an open-source Python package designed to automate rodent sleep staging using EEG, muscle activity (EMG), and optional video-tracking data. It includes a robust base model trained on diverse recordings from six independent laboratories, enabling out-of-the-box classification across various equipment setups without requiring prior manual labeling. A central feature of Somnus is its capacity for rapid adaptation to pathological sleep structure. The software provides a graphical interface that directs researchers to the specific epochs where the base model is least certain. Users can manually correct these targeted epochs in a built-in viewer by comparing the model's classification to the raw EEG signal and video, and then use their corrections to fine-tune the model. This workflow empowers researchers to generate accurate custom scorers for complex disease models or novel treatments with just a few minutes of manual correction, bypassing the need to hand-score entire experimental cohorts or develop their own models from scratch.

Stereotaxic intracranial microinjection in mice is a critical step in neuroscience workflows, enabled by robust hardware design, precise operation, and neuroanatomical expertise. Manual injections are prone to error and stereotax-mountable commercial automated injectors are extremely expensive. Further, the knowledge needed for performing accurate intracranial injections and surgeries is heterogeneous and disparate. Here we demonstrate the design and characterization of the UD Neuroinjector software-hardware-knowledge architecture, which serves to both reduce the cost of performing precisely controlled stereotaxic microinjections and provide a web platform for planning accurate targeting of specific mouse brain regions. We designed the UD Neuroinjector using low-cost hardware and 3D-printed parts, with a total build-cost of $300 --- less than 0.1x the cost of a commercial injector. Arduino-based firmware enables programmable flow rates, automated injection and extraction, and manual joystick control. Capillary-fluid measurements show stable, highly linear displacement (R2 > 0.93) at commonly used injection rates. In a head-to-head comparison with a commercial injector, in vivo DAPI injections into the mouse thalamus showed comparable spread and DAPI+ cell counts. For effective experimental design of intracranial injections, the web-based components of our architecture provide AI-enabled assistance and atlas-guided navigation. We used a hybrid retrieval-augmented generation (RAG) approach to ground AI-assisted protocol guidance for mouse intracranial surgeries using a corpus of 3,738 papers. Using the Common Coordinate Framework version 3 (CCFv3), we designed an interactive tool for identifying target coordinates. Together, the UD Neuroinjector architecture integrates and enables efficient knowledge discovery, experimental design, planning, and implementation of mouse intracranial surgeries.

The choroid plexus (ChP) is a highly vascularized structure located in the brain ventricles that plays important roles in multiple central nervous system functions. ChP enlargement has been implicated in many neuropsychiatric conditions such as multiple sclerosis, depression, schizophrenia, and Alzheimer's disease. However, limitation in the accuracy of the current segmentation tools highlight the need for more reliable methods to quantify ChP volume in healthy and clinical human populations. The shape and size of the ChP vary drastically from person to person, and currently there are no large ChP datasets which allow comprehensive training of segmentation models. Here we introduce DataPlex, a collection of 700 structural MRI brain images where the lateral ventricle ChP has been manually labeled and checked by expert human raters. DataPlex is balanced and representative across a wide range of scanning parameters, demographics, and clinical profiles, and subject-level information will be available for each labeled image. DataPlex will be open source to support the creation of reliable segmentation tools for the human lateral ventricle ChP.

There is increasing demand for quantitative measurements in neuroimaging research, including absolute quantification of regional myelin density. Fast whole-brain macromolecular proton fraction (MPF) imaging enables acquisition and reconstruction of quantitative maps of MPF, a biomarker of myelin, and has been used in many research applications. To date, no standard protocols have been published for parcellating MPF maps. FreeSurfer is a widely used software package for automated brain parcellation. It is designed for use with high-resolution T1-weighted anatomical images, typically acquired with an MPRAGE sequence. MPF maps inherently provide high contrast between white and gray matter and can potentially be used as input images for parcellation, enabling simultaneous quantitative tissue characterization and volumetric assessment. However, it is unclear how the use of MPF maps as input images with FreeSurfer software affect reliability and repeatability of regional MPF and volume estimates. We evaluated three FreeSurfer parcellation workflows for this purpose. The workflows differed in the amount of neuroimaging data required and computational intensity. MPF and MPRAGE data were acquired in two separate sessions for 11 adults. Reliability was evaluated using mean relative differences in estimates, Bland-Altman analysis, and intra-class correlation coefficients (ICCs). Repeatability was assessed using within-subject coefficients of variation (CVws). All three workflows produced similarly high within-subject repeatability across scans. However, reliability in regional MPF estimates was lower in gray matter than in white matter for workflows that used MPF maps as input. Workflows that use MPF maps as FreeSurfer input may be adequate for estimating mean MPF in GM and WM of cortical parcels and in subcortical regions. However, the MPRAGE-based workflow is recommended when reliable individual-level estimates or volume estimates are required.

Automatic segmentation of medical images could accelerate clinical and research workflows, yet existing tools are rarely compared independently on shared benchmarks, making it difficult to assess genuine progress. This is particularly consequential for limb muscle segmentation in magnetic resonance imaging (MRI), which underpins volumetric analysis, radiomics, and fat fraction quantification used as biomarkers in neuromuscular disease -- applications where segmentation errors can directly affect interpretation. Despite the availability of multiple open-source segmentation tools spanning diverse architectures, no independent head-to-head comparison has appeared in the literature. We address this gap by evaluating eight tools, six of which run independently, and the other two of which are meant to be auxiliary algorithms once muscles have been somehow initially labeled. We evaluated these tools on three-dimensional MRI volumes across three base datasets and then later against derived datasets, assessing both quantitative metrics and qualitative usability. Our results reveal substantial performance variation across methods and datasets, with many methods showing reduced accuracy on pathological cases. Domain-specific models trained on large datasets consistently outperformed foundation models and newer general-purpose architectures. Our results reveal practical trade-offs between accuracy, generalizability, and ease of use that are critical for clinical adoption, while raising concerns for deployment on underrepresented populations and pathologies.

Two-photon calcium imaging enables measurements of neural activity from individual neurons and their subcellular processes in awake animals. Axial brain motion can change measured fluorescence independently of neural activity and move small structures out of the imaging plane, confounding two-photon calcium measurements in behaving animals. We developed two complementary post-acquisition methods, selected according to whether the imaged structure remains detectable across the encountered depth range. When it does, z-stack correction estimates imaging depth from a separately acquired reference z-stack and uses an axial fluorescence profile specific to each neural structure to rescale fluorescence to a common reference depth. When a structure can leave a single imaging plane, volume-based z-registration reconstructs a common-depth movie from repeated acquisitions of closely spaced planes. In awake mice, both methods tracked experimentally imposed axial displacements within the sampled range, with depth-estimation root mean squared errors (RMSEs) below 1 m for z-stack correction and 0.69-1.03 m for volume-based z-registration. Correction changed fluorescence substantially for a subset of somata, with larger effects in axonal boutons. Both methods are implemented in suite2p-in-depth, a Python package that integrates with Suite2p and provides diagnostics for depth estimation, correction quality and data reliability. Together, these methods enable axial-motion artifacts to be assessed and corrected within established Suite2p workflows.

Biophysically detailed models of human cortical microcircuit provide key insights into brain function and disease biomarkers, yet their computational cost lengthens simulation runtime and limits scalability. To address this, we systematically evaluated recent simplification methods for morphological reduction and synapse merging in terms of preserving spiking and electroencephalographic (EEG) properties of human cortical microcircuit models. At the single- cell level, reduced compartmental models accurately reproduced spiking behaviors. However, at the microcircuit level, while achieving a 5-fold speed-up, morphological reduction failed to preserve spectral dynamics of spiking and EEG despite maintaining average baseline and response firing rates. Conversely, applying synapse merging alone on the full morphology successfully reproduced both spiking activity and EEG dynamics, when constrained to [≤] 50 m spatial intervals, and yielded a 2-fold speed-up. These results were consistent across both cortical layer 2/3 and layer 5 models, and in depression models with reduced somatostatin interneuron inhibition. Our study identifies model simplification methods that speed up cortical microcircuit simulations while preserving the accuracy of the simulated brain signals.

Volumetric imaging is increasingly important in fields such as neuroscience, where quantifying structure and mapping features are inherently three-dimensional problems. Block-face serial two-photon tomography (STPT) has emerged as a powerful approach for high-resolution, whole-organ volumetric imaging. STPT avoids complex sample preparation and balances image quality, speed, and scalability. However, STPT remains niche, in part because of the absence of flexible, general-purpose control software. Here we present BakingTray, an open-source software platform for STPT that extends ScanImage. BakingTrays modular framework accommodates diverse hardware configurations and allows users to build systems customised to their needs. Twelve such systems, which we call BrainSaws, have been constructed worldwide since 2016, with more under construction, and have so far contributed to 35 research papers. The three systems at the Sainsbury Wellcome Centre alone have acquired over 7,000 samples in a busy multi-user facility. We demonstrate the platform across its core neuroscience applications: electrode track localisation, brain-wide cell counting, and bulk projection mapping. Beyond these, we map the cell-type-specific synaptic output of inhibitory neurons in the ventral lateral geniculate nucleus and, with whole-mount staining, amyloid plaques brain-wide in a mouse model of Alzheimers disease. BakingTray is a mature platform for groups or facilities needing a customised volumetric imaging solution, whether built new or converted cheaply from an existing two-photon microscope.

A central goal of neuroscience is to establish how similar (or different) brain networks are across individuals, development, psychiatric conditions, and even between biological and artificial brains. Whenever one such comparison is made, it relies on the assumption that we have a measure that produces an accurate and plausible similarity score. Yet, the field lacks one such measure, and the wide variety of existing measures often produces conflicting results. To address this problem, we perform a systematic comparison of 16 established similarity measures. First, we show that different measures consistently disagree on which brain networks are most similar. Second, we rank all measures according to multiple criteria such as biological plausibility, computational efficiency, and sensitivity. We show that DeltaCon is the most accurate measure in terms of parameter recovery, and that it ranks among the fastest and most noise-tolerant. For this reason, we conclude that DeltaCon is the best general-purpose similarity measure. However, no measure ranks best on more than two of the five criteria we assessed, and different measures should be preferred depending on the exact research question. Measure selection can now be made on evidence and should be a crucial decision in any study that compares brain networks.

Microstate analysis studies dynamic brain activity through a discrete representation of electroencephalographic (EEG) signals and their topography. While the body of literature describing findings in diverse experimental and clinical settings is growing rapidly, the effects of several core components of the microstate algorithm are still insufficiently understood. This study systematically investigates how two common temporal smoothing algorithms, parametric smoothing and GFP peak interpolation, influence a wide range of microstate sequence parameters, and how they shape the integrated picture of brain dynamics inferred from these metrics. We study eyes-closed resting-state EEG recordings from N=201 healthy subjects from a public EEG database. For the elementary temporal metrics, we find that widening smoothing windows markedly increase microstate duration, reduce occurrence rates, but leave coverage mostly unaffected. In terms of simple syntax properties, smoothing windows above 30 ms yield an inconsistent picture with a memoryless, first-order Markov structure at short time scales, but a positive Hurst phenomenon suggestive of long-range correlations at long time scales. Evidence of asymmetry and non-equilibrium dynamics are suppressed by smoothing. At intermediate time scales, microstate periodicity was only observed up to a window size of 28 ms. Smoothing had a strong impact on the complexity metrics entropy rate and excess entropy, decreasing the former and increasing the latter. For most metrics, the effects of GFP peak interpolation were comparable to those of smoothing windows in the range between 28 ms and 44 ms. In conclusion, elementary and higher-order microstate parameters must be interpreted in the context of preprocessing, as many parameters change continuously with smoothing intensity. This limits the comparability of microstate parameters obtained with different preprocessing settings. Strong smoothing with a window size above 30 ms or GFP peak interpolation yields a fundamentally different picture of resting state brain dynamics, i.e. that of a memoryless, aperiodic, time-reversible first-order Markov chain. Since insights from other neurophysiological modalities suggest that time series memory and time-irreversibility are markers of normal brain activity, our recommendation is to avoid intense smoothing to minimize alterations of the initial sequences.

Background: Whole-brain segmentation of neonatal low-field MRI is needed for regional volumetric analysis, but established segmentation systems are designed around different field strengths, contrasts, and age ranges. Methods: We first applied complete end-to-end pipelines, including FreeSurfer, FSL-based processing, Infant FreeSurfer, FastSurfer, BrainSuite, SPM12/CAT12, iBEAT v2, the dHCP structural pipeline, and M-CRIB-S, directly to 0.35T neonatal T2-weighted images. Because those systems did not produce a complete 47-region output, we next tested released end-to-end AI segmentation models, including SynthSeg, FastSurfer, FastSurferVINN, and QuickNAT. These were highly sensitive to input format, contrast, voxel geometry, and the high-field training domain. We then decomposed the task into skull stripping, registration, super-resolution, atlas propagation, and tissue refinement and tested the available components individually. Results: No complete end-to-end pipeline or released AI model delivered a usable 47-region segmentation in direct application. Stage-wise testing showed that preprocessing, reconstruction, registration, atlas propagation, and expectation-maximization each solved only part of the problem. Their final assembly produced complete 47-region outputs across the neonatal cohort. Conclusions: Direct application of established pipelines was insufficient for 0.35T neonatal T2-weighted MRI. A stage-wise combination of compatible components provided the workable solution.

Background: Software tools can support MRI diagnosis of focal cortical dysplasias (FCDs) - subtle, surgically-treatable lesions that underlie drug-resistant focal epilepsy (DRFE). MELD-graph, a widely used open-source tool combining surface-based morphometry with a convolutional neural network, was developed using 1.5T and 3T MRI data. 7T MRI is increasingly used for lesion detection in DRFE. This study investigated whether MELD-graph is robust to domain shift at 7T. Methods: We collated paired 3T and 7T T1-weighted MRI, and FLAIR where available, from 23 patients with FCD (6 histologically-verified, 17 identified radiologically) and 39 healthy controls at four epilepsy centres. Manual lesion labels were used as ground truth. MELD-graph was run on 3T images, on 7T images with the default pipeline, and on 7T images with adaptations for 7T MRI (SPM bias-field correction, SynthStrip skull-stripping, sub-millimetric FreeSurfer reconstruction), with and without ComBat harmonisation. FCD detection performance and surface morphometry features were compared. Results: Sensitivity for FCD detection was 65% (15/23) at 3T, 48% (11/23) for 7T default and 52% (12/23) for 7T adapted, with Combat harmonisation. Among radiologically 3T-negative patients, 2/8 were detected at 3T and 3/8 at 7T; and among histologically confirmed FCD, 3/6 at 3T and 1/6 at 7T. Specificity was significantly lower at 7T (default 39%, adapted 45%) than 3T (76%). False-positives predominantly occurred in the basal temporal lobes. ComBat harmonisation improved specificity in all conditions and largely compensated for field-strength dependent differences in surface morphometry features. Adding FLAIR at 7T increased false-positive predictions. Conclusion: Sensitivity is comparable but specificity of MELD-graph is lower at 7T compared to 3T. Adaptations for 7T MRI can reduce segmentation errors but do not significantly improve FCD detection, while harmonisation improves performance. The adapted pipeline is released open-source. 7T MELD-graph outputs may inform radiologist review in challenging cases but require cautious interpretation.

Training spike detectors on real recordings is challenging because algorithmically generated labels can be noisy and incomplete. We propose VanillaSort, combining multichannel detection with spatially augmented, template-guided clustering. VanillaDet uses visibility-aware masking, truncated Gaussian targets and a temporally tolerant positive-bag loss, followed by conditional event-SNR gating. VanillaCluster combines HuiduRep embeddings with relative-amplitude features for Gaussian mixture clustering and refines assignments using cross-fitted waveform templates built from selected core events. VanillaDet improves detection accuracy over SimSort by two and three percentage points on the static and drift subsets of Hybrid Janelia, respectively. The complete pipeline also improves sorting performance over the corresponding HuiduRep baselines. These results support learning from imperfect real-data labels and incorporating waveform consistency into neuronal assignment.