A deep learning framework for 18F-FDG PET imaging diagnosis in pediatric patients with temporal lobe epilepsy

Abstract

Purpose Epilepsy is one of the most disabling neurological disorders, which affects all age groups and often results in severe consequences. Since misdiagnoses are common, many pediatric patients fail to receive the correct treatment. Recently, 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) imaging has been used for the evaluation of pediatric epilepsy. However, the epileptic focus is very difficult to be identified by visual assessment since it may present either hypo- or hyper-metabolic abnormality with unclear boundary. This study aimed to develop a novel symmetricity-driven deep learning framework of PET imaging for the identification of epileptic foci in pediatric patients with temporal lobe epilepsy (TLE). Methods We retrospectively included 201 pediatric patients with TLE and 24 age-matched controls who underwent 18F-FDG PET-CT studies. 18F-FDG PET images were quantitatively investigated using 386 symmetricity features, and a pair-of-cube (PoC)-based Siamese convolutional neural network (CNN) was proposed for precise localization of epileptic focus, and then metabolic abnormality level of the predicted focus was calculated automatically by asymmetric index (AI). Performances of the proposed framework were compared with visual assessment, statistical parametric mapping (SPM) software, and Jensen-Shannon divergence-based logistic regression (JS-LR) analysis. Results The proposed deep learning framework could detect the epileptic foci accurately with the dice coefficient of 0.51, which was significantly higher than that of SPM (0.24, P < 0.01) and significantly (or marginally) higher than that of visual assessment (0.31–0.44, P = 0.005–0.27). The area under the curve (AUC) of the PoC classification was higher than that of the JS-LR (0.93 vs. 0.72). The metabolic level detection accuracy of the proposed method was significantly higher than that of visual assessment blinded or unblinded to clinical information (90% vs. 56% or 68%, P < 0.01). Conclusion The proposed deep learning framework for 18F-FDG PET imaging could identify epileptic foci accurately and efficiently, which might be applied as a computer-assisted approach for the future diagnosis of epilepsy patients. Trial registration NCT04169581. Registered November 13, 2019 Public site: https://clinicaltrials.gov/ct2/show/NCT04169581

Clinical evaluation of a novel atlas-based PET/CT brain image segmentation and quantification method for epilepsy

“…In future studies, we will investigate cases with structural differences due to brain atrophy or traumatic brain injury to further improve our method. Moreover, the application of deep-learning techniques for the diagnosis and localization of epilepsy has been proposed by another research team (20).…”

“…Studies have been conducted to establish radiation histological prediction models for low-grade glioma-related epilepsy based on MRI data, thus enabling the individualized treatment of patients with this type of epilepsy (16)(17)(18)(19). Zhang et al proposed a Siamese convolutional neural network based on cube pair for the accurate localization of epileptic foci, and then used the AI to automatically calculate and predict the degree of metabolic abnormalities of the foci (20). However, there are also several potential obstacles to the use of machinelearning applications, including the size of the training data set, the accuracy of the referenced label, confounded clinical variables, and variability in data collection and interpretation (21)(22)(23).…”

A muggles guide to deep learning wizardry

“…22 Detection of seizure foci on FDG brain PET was also enhanced, regardless of ictal or interictal status, with CNN based DL applications in pediatric patients with the DL framework. 23 You conjured up a Patronus that drove away all those dementors! That's very, very advanced magic.…”

Deep Random Forest with Ferroelectric Analog Content Addressable Memory

“…These results suggest great promise for the ferroelectric ACAM array when implementing the DRF. In addition, we also implemented a simple random forest model (i.e., no layer-by-layer structure) using the ferroelectric ACAM and evaluated its performance on some EEG [41] and PET [42] dataset. Table S1 summarizes the metrics including cell size, energy and latency per classification using our ferroelectric ACAM based random forest, as well as other advanced machine learning model implementations.…”