Convolutional Neural Networks for Automatic Tuber Segmentation and Quantification of Tuber Burden in Tuberous Sclerosis Complex

Authors

Iván Sánchez Fernández
Matheus D Soldatelli
Gillian N Miller
Catharina F Gout
Ellen C Broekhuizen
Iris C J den Hertog
Daan A Pijs
Errol Apostolopoulos
Prabhjot Kaur
Abdelhakim Ouaalam
Martina E Bebin
Hope Northrup
Darcy A Krueger
Joyce Y Wu
Alexander L Cohen
Mustafa Sahin
Davood Karimi
Simon K Warfield
Jurriaan M Peters

Language

English

Publication Date

2-1-2026

Journal

Epilepsia

DOI

10.1111/epi.70007

PMID

41258699

PMCID

PMC12832091

PubMedCentral® Posted Date

1-26-2026

PubMedCentral® Full Text Version

Author MSS

Abstract

Objective: This study was undertaken to develop a fully automated algorithm for tuber segmentation and quantification of tuber volume that performs similarly to the gold standard human neuroradiologist.

Methods: We used brain magnetic resonance imaging (MRI) from patients with tuberous sclerosis complex (TSC) to train and validate a convolutional neural network (CNN), which was evaluated on segmentation with the Dice-Sørensen similarity coefficient (DSSC) and on tuber burden quantification with Spearman correlation coefficient against a neuroradiologist's gold standard in the test set.

Results: We collected 263 MRIs from 196 patients (57% males) with median (25th percentile-75th percentile) age of 4.3 (3.0-10.1) years: 176 MRIs in the train set, 39 in the validation set, and 48 in the test set. The final model achieved in the test set a DSSC of .820 (95% confidence interval [CI] = .799-.840) in the whole brain and in the different lobes the following: .831 (95% CI = .804-.850) in left frontal, .827 (95% CI = .799-.853) in right frontal, .817 (95% CI = .779-.842) in left temporal, .834 (95% CI = .812-.849) in right temporal, .821 (95% CI = .783-.856) in left parietal, .840 (95% CI = .810-.865) in right parietal, .832 (95% CI = .808-.851) in left occipital, and .856 (95% CI = .838-.871) in right occipital. CNN tuber volume quantification nearly perfectly correlated (Spearman correlation coefficient) with the neuroradiologist's across the whole brain (.984, 95% CI = .971-.991) and in the different lobes: .966 (95% CI = .940-.981) in left frontal, .973 (95% CI = .952-.985) in right frontal, .936 (95% CI = .888-.964) in left temporal, .967 (95% CI = .942-.982) in right temporal, .989 (95% CI = .980-.994) in left parietal, .983 (95% CI = .970-.990) in right parietal, .992 (95% CI = .985-.995) in left occipital, and .982 (95% CI = .968-.990) in right occipital (all p < .00001).

Significance: We generated, trained, validated, and made publicly available a CNN that achieves a near-perfect correlation with a neuroradiologist gold standard quantification of tuber burden, allows for objective tuber segmentation, and increases rigor and reproducibility in TSC research across institutions.

Keywords

Humans, Tuberous Sclerosis, Male, Female, Magnetic Resonance Imaging, Child, Neural Networks, Computer, Child, Preschool, Brain, Image Processing, Computer-Assisted, Algorithms, Convolutional Neural Networks, Convolutional neural network, Deep learning, Neuroradiology, Tuber burden, Tuberous sclerosis complex

Published Open-Access

yes

Recommended Citation

Sánchez Fernández, Iván; Soldatelli, Matheus D; Miller, Gillian N; et al., "Convolutional Neural Networks for Automatic Tuber Segmentation and Quantification of Tuber Burden in Tuberous Sclerosis Complex" (2026). Faculty, Staff and Student Publications. 6351.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/6351