Multiclass machine learning classification of functional brain images for Parkinson's disease stage prediction

Abstract

We analyzed a data set containing functional brain images from 6 healthy controls and 196 individuals with Parkinson's disease (PD), who were divided into five stages according to illness severity. The goal was to predict patients' PD illness stages by using their functional brain images. We employed the following prediction approaches: multivariate statistical methods (linear discriminant analysis, support vector machine, decision tree, and multilayer perceptron [MLP]), ensemble learning models (random forest [RF] and adaptive boosting), and deep convolutional neural network (CNN). For statistical and ensemble models, various feature extraction approaches (principal component analysis [PCA], multilinear PCA, intensity summary statistics [IStat], and Laws' texture energy measure) were employed to extract features, the synthetic minority over‐sampling technique was used to address imbalanced data, and the optimal combination of hyperparameters was found using a grid search. For CNN modeling, we applied an image augmentation technique to increase and balance data sizes over different disease stages. We adopted transfer learning to incorporate pretrained VGG16 weights and architecture into the model fitting, and we also tested a state‐of‐the‐art machine learning model that could automatically generate an optimal neural architecture. We found that IStat consistently outperformed other feature extraction approaches. MLP and RF were the analytic approaches with the highest prediction accuracy rate for multivariate statistical and ensemble learning models, respectively. Overall, the deep CNN model with pretrained VGG16 weights and architecture outperformed other approaches; it captured critical features from imaging, effectively distinguished between normal controls and patients with PD, and achieved the highest classification accuracy.

Explainable AI to improve acceptance of convolutional neural networks for automatic classification of dopamine transporter SPECT in the diagnosis of clinically uncertain parkinsonian syndromes

“…Conventional machine learning methods using support vector machines [33][34][35][36][37][38][39][40][41][42][43], decision trees [44,45], or cluster analyses [46] based on a (small) set of predefined image-derived features have been proposed for this purpose. However, recent work suggests that artificial neural networks, particularly deep CNN, outperform conventional approaches for the automatic classification of DAT-SPECT [18,[47][48][49][50][51][52][53][54][55][56][57][58], partly because artificial neural networks can be less sensitive to camera-and site-specific variability of image quality (e.g., with respect to spatial resolution) [18]. Thus, deep CNN are very promising to support interpretation of DAT-SPECT in clinical routine so that there is a high clinical need for methods to explain CNN-based classification in individual patients.…”

Machine learning and deep learning for clinical data and PET/SPECT imaging in Parkinson's disease: a review

“…Recently, Huang et al [121] proposed a method to identify patients' PD illness stages using their [99mTC] TRODAT-1 SPECT imaging. This approach includes three ML models: multivariate statistical methods (LDA, SVM, decision tree and MLP), ensemble learning models [RF and adaptive boosting (AdaBoost)] and CNN.…”

Automated Machine Learning: a case study of genomic “image-based” prediction in maize hybrids

“…The lack of similarity between structures might arise from the ability of AutoML to adapt the network to the dataset (Jin et al, 2019), which changes due to sampling in repeated validation. Huang et al (Huang et al 2020) suggest this event to be a consequence of insufficient data, but further confirmation is required. Additionally, this may also be associated with the sampling nature of the hyperparameter search system (Jin et al, 2019).…”