In silico neuronal morphology classification: A systematic review
Clinical Snapshot
PICO Framework
| P — Population | Studies investigating computational methods for neuronal morphology classification |
| I — Intervention | Various computational methods including artificial neural networks, machine learning algorithms |
| C — Comparator | Different computational approaches and evaluation methods |
| O — Outcomes | Classification accuracy, method effectiveness, representation types used |
Bottom Line
This systematic review synthesises current computational approaches for neuronal morphology classification, finding that artificial neural networks dominate the field (60% of studies) with microscopy-based feature extraction being the preferred representation method (86% of studies). The review demonstrates methodological rigour in study selection and quality assessment, though it lacks heterogeneity analysis and evidence certainty assessment. While primarily of research interest, these findings could inform the development of standardised approaches for neuronal taxonomy in clinical neuroscience applications. The predominance of accuracy as an evaluation metric (83% of studies) suggests a need for more comprehensive performance assessment frameworks. Australian researchers in computational neuroscience and connectomics would benefit from these methodological insights for future neuronal classification projects.
Key Findings
P Value: Not applicable for systematic review
Effect Size: 21 out of 35 studies (60%) used ANNs
Primary Outcome: Artificial Neural Networks are the predominant method for neuronal morphology classification
Nnt Or Sensitivity: 30 out of 35 studies (86%) used microscopy-based representations
Confidence Interval: Not reported
Clinical Application
High for research institutions with computational resources and neuroimaging capabilities Relevant to Australian neuroscience research centres and universities with connectomics programs, though no specific regulatory considerations apply Neuroscience researchers and computational biologists working on neuronal classification
Abstract
Advances in connectomics and the characterization of neuronal diversity have been fundamental to understanding how the brain works. Defining a taxonomy is still challenging and requires complex computational methods. In this paper, we present a systematic review of the state-of-the-art methods for neuronal morphology classification, shedding light on trends and future directions. We address three core research questions: (1) What computational methods are used to classify neuronal morphologies? (2) What kind of representation do the classification models work on? (3) How are the classification models evaluated? We applied a structured protocol including peer-reviewed studies published since 2018. We collected 840 papers from five databases, published between 2018 and 2024. We assessed risk of bias using predefined quality criteria on study design, methodology, and reporting; 35 studies met these standards and were included to extract information and consolidate the results. The results show that Artificial Neural Networks are currently the main method for classifying neurons based on morphometric features (21 papers). Representations based on microscopy images for extracting morphometric features (30) are commonly used. Accuracy (29) is the predominant evaluation measure. Our research findings contribute to the body of knowledge by providing an up-to-date perspective on neuronal classification, which can guide future research in neuroscience and related fields.
References
- 1.Lobato, F., Leite, J., Jacob, A., & Santana, R. (2026). In silico neuronal morphology classification: A systematic review. Neuroscience. https://doi.org/10.1016/j.neuroscience.2026.02.044
Related Research
Cell host & microbe
Adjunctive fecal microbiota transplantation for major depressive disorder: A randomized, double-blind, placebo-controlled trial
10 July 2026
Science advances
AI-driven tripartite classification for optimizing wearable bioelectronics in depression management
27 June 2026
Science advances
Artificial sparse neuron dendrites for visual information inference
21 June 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service