OSCR

Deep learning-based identification of causative genes in lissencephaly using 3D-MRI volumetric datasets.

Overview

Authors: Naoki Takahashi1, Yoshihiro Sato1, Mitsuhiro Kato2, Atsuko Yamaguchi1
ORCID iDs: Yoshihiro Sato
  1. Department of Design and Data Science, Tokyo City University, Kanagawa, Japan
  2. Department of Pediatrics, SHOWA Medical University, Tokyo, Japan
Institutions: Tokyo City University (Japan); SHOWA Medical University (Japan)
Journal: Neuroimage. Reports, volume 6, issue 3, article 100375
Dates: received 12 February 2026; accepted 18 June 2026; published online 23 June 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1016/j.ynirp.2026.100375 · PMID 42381865 · PMCID PMC13315807 · OpenAlex W7165683317
Open access: gold, a free copy (OpenAlex)
Status: data only
Categories: structural MRI / diffusion (modality)
Methods: Machine learning
Keywords: Neuronal migration disorders, Lissencephaly, MRI, Medical image processing, Deep learning, 3D-CNN
Topic: Genomics and Rare Diseases (Genetics, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: Government of Japan Ministry of Health Labour and Welfare; Japan Society for the Promotion of Science; Showa University
Citations: not cited yet (Europe PMC); 23 references in the paper

Abstract

Background: This paper reports a genetic identification task using 3D convolutional neural network (3D-CNN) models applied to a proprietary 3D magnetic resonance imaging (MRI) dataset of patients with lissencephaly. Lissencephaly is a neuronal migration disorder caused by genetic mutations or deletions in which specific causative genes result in distinct morphological alterations in brain structure.

Objective: The objective of this study was to identify causative genes through image classification by analysing three-dimensional structural features of brain MRI using deep learning.

Methods: In our experiments, we extended representative CNN architectures to handle three-dimensional inputs and performed three-class classification targeting the primary causative genes, LIS1 and DCX, along with a category for other genetic variations.

Results: Our results demonstrated that the 3D-ResNet18 model achieved a mean classification accuracy of over 78%. Furthermore, to enhance the precision for primary genes, we introduced a decision-making process based on prediction probability thresholds.

Conclusions: This approach yielded an average precision improvement of 4.67% for DCX and 4.84% for LIS1 across all the evaluated models.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data availability

The MRI data used for training is not publicly available, but we have released a trained model that ensures reproducibility and has been validated using open data.

Reproduced under the paper's license (CC BY), from the paper cited above.

Data Availability Statement

The code and trained models used in the experiment are available online in Mendeley Data (doi: https://doi.org/10.17632/ybdxcbwp74.1). Please note that the raw training data are not publicly available because they contain sensitive personal information. However, researchers are encouraged to utilize the released pretrained models and referenced open-data samples.

The MRI data used for training is not publicly available, but we have released a trained model that ensures reproducibility and has been validated using open data.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 2, 28 September 2026

  • Authors: added Yoshihiro Sato (0000-0002-2794-9596); removed Yoshihiro Sato

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 6 keywords, 3 funders, 20 references.

Cite

This paper

Takahashi, N., Sato, Y., Kato, M., & Yamaguchi, A. (2026). Deep learning-based identification of causative genes in lissencephaly using 3D-MRI volumetric datasets. Neuroimage. Reports, 6(3), 100375. https://doi.org/10.1016/j.ynirp.2026.100375

BibTeX

@article{takahashi2026deep,
author = {Takahashi, Naoki and Sato, Yoshihiro and Kato, Mitsuhiro and Yamaguchi, Atsuko},
title = {{Deep learning-based identification of causative genes in lissencephaly using 3D-MRI volumetric datasets}},
journal = {Neuroimage. Reports},
year = {2026},
month = jun,
volume = {6},
number = {3},
pages = {100375},
publisher = {Elsevier},
issn = {2666-9560},
doi = {10.1016/j.ynirp.2026.100375},
url = {https://doi.org/10.1016/j.ynirp.2026.100375},
pmid = {42381865},
pmcid = {PMC13315807}
}

RIS

TY - JOUR
AU - Takahashi, Naoki
AU - Sato, Yoshihiro
AU - Kato, Mitsuhiro
AU - Yamaguchi, Atsuko
TI - Deep learning-based identification of causative genes in lissencephaly using 3D-MRI volumetric datasets
T2 - Neuroimage. Reports
J2 - Neuroimage Rep
PY - 2026
DA - 2026/06/23
VL - 6
IS - 3
SP - 100375
SN - 2666-9560
PB - Elsevier
DO - 10.1016/j.ynirp.2026.100375
UR - https://doi.org/10.1016/j.ynirp.2026.100375
LA - en
ER -

CSL-JSON

{
"id": "10.1016/j.ynirp.2026.100375",
"type": "article-journal",
"title": "Deep learning-based identification of causative genes in lissencephaly using 3D-MRI volumetric datasets",
"container-title": "Neuroimage. Reports",
"author": [
{
"family": "Takahashi",
"given": "Naoki"
},
{
"family": "Sato",
"given": "Yoshihiro"
},
{
"family": "Kato",
"given": "Mitsuhiro"
},
{
"family": "Yamaguchi",
"given": "Atsuko"
}
],
"container-title-short": "Neuroimage Rep",
"volume": "6",
"issue": "3",
"page": "100375",
"DOI": "10.1016/j.ynirp.2026.100375",
"PMID": "42381865",
"PMCID": "PMC13315807",
"ISSN": "2666-9560",
"publisher": "Elsevier",
"URL": "https://doi.org/10.1016/j.ynirp.2026.100375",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
23
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3389/frai.2026.1849051
Query-guided learning for efficient and interpretable multi-class brain tumor classification in MRI.
Journal: Frontiers in artificial intelligence
In common: structural MRI / diffusion, 4 references
[2] doi:10.1002/acm2.70560 [code]
Hybrid CNN-GCN framework for brain tumor MRI classification: A graph-based approach to smart healthcare diagnostics.
Journal: Journal of applied clinical medical physics
In common: structural MRI / diffusion, 4 references
[3] doi:10.3389/fonc.2026.1834400
BrainFusionNet: an attention-augmented deep convolutional framework with hybrid loss optimisation and test-time augmentation for multi-class brain tumour detection in magnetic resonance images.
Journal: Frontiers in oncology
In common: structural MRI / diffusion, 4 references
[4] doi:10.2196/78300
Deep Learning for Content-Based Medical Image Retrieval in Picture Archiving and Communication Systems for Brain Tumor Detection: Algorithm Development and Validation.
Journal: JMIR medical informatics
In common: structural MRI / diffusion, 3 references
[5] doi:10.3389/fonc.2026.1806663
A denoising autoencoder-enhanced ResNet 50 framework for explainable brain tumor classification using MRI.
Journal: Frontiers in oncology
In common: structural MRI / diffusion, 3 references
[6] doi:10.1371/journal.pone.0350637 [code]
Deep learning-based arterial waveform analysis for predicting postoperative cerebrovascular events in pediatric patients with Moyamoya disease.
Journal: PloS one
In common: 3 references
[7] doi:10.1038/s41592-026-03111-z [code]
A cloud-based miniscope for neurosurveillance of brain health and disease in freely behaving animals.
Journal: Nature methods
In common: 3 references
[8] doi:10.3390/diagnostics16111705
Cross-Dataset Generalization of Deep Learning-Based Detectors for Intracranial Hemorrhage Subtype Localization on Noncontrast Head CT: A Comparative Study.
Journal: Diagnostics (Basel, Switzerland)
In common: 2 references
[9] doi:10.3389/fmed.2026.1810860
Lightweight deep learning for medical imaging using MobileNetV2-based brain pathology classification with Grad-CAM interpretability.
Journal: Frontiers in medicine
In common: 2 references
[10] doi:10.7554/elife.104053 [code]
Brain cognition gaps reveal associations with dopamine and factors related to brain health through artificial intelligence prediction of functional connectome.
Journal: eLife
In common: 2 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.