Automated image quality evaluation of structural brain MRI using an ensemble of deep learning networks

Abstract

Background Deep learning (DL) is a promising methodology for automatic detection of abnormalities in brain MRI. Purpose To automatically evaluate the quality of multicenter structural brain MRI images using an ensemble DL model based on deep convolutional neural networks (DCNNs). Study Type Retrospective. Population The study included 1064 brain images of autism patients and healthy controls from the Autism Brain Imaging Data Exchange (ABIDE) database. MRI data from 110 multiple sclerosis patients from the CombiRx study were included for independent testing. Sequence T1‐weighted MR brain images acquired at 3T. Assessment The ABIDE data were separated into training (60%), validation (20%), and testing (20%) sets. The ensemble DL model combined the results from three cascaded networks trained separately on the three MRI image planes (axial, coronal, and sagittal). Each cascaded network consists of a DCNN followed by a fully connected network. The quality of image slices from each plane was evaluated by the DCNN and the resultant image scores were combined into a volumewise quality rating using the fully connected network. The DL predicted ratings were compared with manual quality evaluation by two experts. Statistical Tests Receiver operating characteristic (ROC) curve, area under ROC curve (AUC), sensitivity, specificity, accuracy, and positive (PPV) and negative (NPV) predictive values. Results The AUC, sensitivity, specificity, accuracy, PPV, and NPV for image quality evaluation of the ABIDE test set using the ensemble model were 0.90, 0.77, 0.85, 0.84, 0.42, and 0.96, respectively. On the CombiRx set the same model achieved performance of 0.71, 0.41, 0.84, 0.73, 0.48, and 0.80. Data Conclusion This study demonstrated the high accuracy of DL in evaluating image quality of structural brain MRI in multicenter studies. Level of Evidence: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:1260–1267.

A survey of deep learning models in medical therapeutic areas

“…Only 25.4% (31) of the 126 papers were validated with databases different than the initial dataset, and only two studies (1.6%) detailed its application to clinical practice, Figure 15. These studies validated their results in different databases than the initial dataset were: [51], [57], [74], [82], [86], [92] , [94], [98][99][100][101][102][103][104][105][106][107], [94]. And only two [82,101] describes the application of the model in the current clinical practice.…”

“…In neuropsychiatry, the aim of many studies is the diagnosis [50,55,62,63,83,100] but also, we can find studies to predict disease evolution [72,108], to allow patients to write through their eyes movement [96].…”

Image Quality Assessment of Fetal Brain MRI Using Multi‐Instance Deep Learning Methods

“…Their best model showed precision, recall, F‐score, and accuracy equal to 0.74, 0.76, 0.72, and 0.77. Sujit et al 15 used an ensemble learning of CNNs to predict image quality of T1‐weighted pediatric and adult brain MRIs. They reported sensibility, specificity, and accuracy equal to 0.77, 0.85, and 0.84.…”

“…Several automatic methods have been proposed to assess the image quality of adult and pediatric MRIs in various anatomical sites 11–15 . Pizzaro et al 11 used a support‐vector‐machine (SVM) fed with hand‐crafted features to predict the image quality of 3D T 1 ‐weighted adult brain MRIs.…”

Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review)

“…Sujit et al ( 69 ) developed a DCNN aiming to automatically evaluate the quality of multicenter structural brain MRI images, using 1,064 images from autism patients from ABIDE database (60% training, 20% validation and 20% test) while they tested on a cohort of 110 MS patients from the CombiRx dataset ( 70 ). The results demonstrated the high accuracy of the proposed method to evaluate image quality of structural brain MRI in multi-center studies (ABIDE dataset achieved AUC 0.90, sensitivity 0.77, specificity 0.85, accuracy 0.84, PPV 0.42, and NPV 0.96 while for the CombiRx there were AUC 0.71, sensitivity 0.41, specificity 0.84, accuracy 0.73, PPV 0.48, and NPV 0.80).…”