AI‐Based Mitochondrial Network Characterization as a Biomarker for DNM1L ‐Related Disease Diagnosis
Open Access
- 5 November 2026
- journal article
- Published by Wiley in Advanced Intelligent Systems
Abstract
Pathogenic variants in DNM1L impair Drp1 function, a key regulator of mitochondrial and peroxisomal fission, leading to a neurodevelopmental disorder with a broad clinical spectrum. The clinical and functional heterogeneity of Drp1 deficiency complicates the interpretation of new variants of unknown significance, hindering the disease diagnosis and proper management. This proof‐of‐concept study evaluates whether AI‐based mitochondrial network phenotyping could serve as a characteristic feature of DNM1L mutations, supporting the disease diagnosis. Using fluorescent confocal microscopy images, supervised machine‐learning classification of the mitochondrial network features of DNM1L ‐ patients’ primary fibroblasts enables discrimination from controls and other mitochondrial disorders. To avoid manual data extraction, the deep‐learning Convolutional Neural Network (CNN) EfficientNetB0 is used, following two approaches: direct Fine‐Tuning (FT) and Curriculum‐learning Fine‐Tuning (CFT), in which the model is trained from easy‐to‐complex microscopy images to extract hierarchical visual features. Among these, CFT achieves the best performance, with 77% accuracy and 0.92 AUC (Area Under the ROC Curve), thereby optimally discerning DNM1L mitochondrial networks from other mitochondrial disorders. Overall, these findings provide proof‐of‐concept that mitochondrial network morphology in patient‐derived fibroblasts may constitute a disease‐associated phenotypic signature of DNM1L deficiency and a potentially useful complementary functional readout for the interpretation of DNM1L variants. Further validation in larger cohorts and across independent experimental settings will be required before considering its clinical diagnostic application.Keywords
Funding Information
- Instituto de Salud Carlos III (PI24/00469)
This publication has 34 references indexed in Scilit:
- SKOOTS: Skeleton‐Oriented Object Segmentation for Mitochondria in High‐Resolution Cochlear EM DatasetsAdvanced Science, 2026
- Convolutional Neural Network approach to classify mitochondrial morphologiesComputational Biology and Chemistry, 2025
- Multi-class classification of brain tumor types from MR images using EfficientNetsBiomedical Signal Processing and Control, 2023
- Binary and multi-class automated detection of age-related macular degeneration using convolutional- and transformer-based architecturesComputer Methods and Programs in Biomedicine, 2022
- Clinical-genetic features and peculiar muscle histopathology in infantileDNM1L-related mitochondrial epileptic encephalopathyHuman Mutation, 2019
- Severe infantile parkinsonism because of a de novo mutation on DLP1 mitochondrial‐peroxisomal proteinMovement Disorders, 2017
- Biallelic Mutations in DNM1L are Associated with a Slowly Progressive Infantile EncephalopathyHuman Mutation, 2016
- A novel de novo dominant negative mutation in DNM1L impairs mitochondrial fission and presents as childhood epileptic encephalopathyAmerican Journal of Medical Genetics Part A, 2016
- Postnatal microcephaly and pain insensitivity due to a de novo heterozygous DNM1L mutation causing impaired mitochondrial fission and functionAmerican Journal of Medical Genetics Part A, 2016
- Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformaticsWIREs Data Mining and Knowledge Discovery, 2012