Open AccessDeep learning in rare disease. Detection of tubers in tuberous sclerosis complex
Author(s) -
Iván Sánchez Fernández,
Edward Yang,
Paola Calvachi,
Marta AmengualGual,
Joyce Wu,
Darcy A. Krueger,
Hope Northrup,
Martina Bebin,
Mustafa Şahin,
KunHsing Yu,
Jurriaan M. Peters
Publication year - 2020
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0232376
Subject(s) - artificial intelligence , deep learning , convolutional neural network , computer science , test set , pattern recognition (psychology) , receiver operating characteristic , cross validation , binary classification , fluid attenuated inversion recovery , magnetic resonance imaging , tuberous sclerosis , set (abstract data type) , artificial neural network , machine learning , support vector machine , pathology , medicine , radiology , programming language
Objective To develop and test a deep learning algorithm to automatically detect cortical tubers in magnetic resonance imaging (MRI), to explore the utility of deep learning in rare disorders with limited data, and to generate an open-access deep learning standalone application. Methods T2 and FLAIR axial images with and without tubers were extracted from MRIs of patients with tuberous sclerosis complex (TSC) and controls, respectively. We trained three different convolutional neural network (CNN) architectures on a training dataset and selected the one with the lowest binary cross-entropy loss in the validation dataset, which was evaluated on the testing dataset. We visualized image regions most relevant for classification with gradient-weighted class activation maps (Grad-CAM) and saliency maps. Results 114 patients with TSC and 114 controls were divided into a training set, a validation set, and a testing set. The InceptionV3 CNN architecture performed best in the validation set and was evaluated in the testing set with the following results: sensitivity: 0.95, specificity: 0.95, positive predictive value: 0.94, negative predictive value: 0.95, F1-score: 0.95, accuracy: 0.95, and area under the curve: 0.99. Grad-CAM and saliency maps showed that tubers resided in regions most relevant for image classification within each image. A stand-alone trained deep learning App was able to classify images using local computers with various operating systems. Conclusion This study shows that deep learning algorithms are able to detect tubers in selected MRI images, and deep learning can be prudently applied clinically to manually selected data in a rare neurological disorder.