Dopamine Transporter SPECT Image Classification for Neurodegenerative Parkinsonism via Diffusion Maps and Machine Learning Classifiers

TL;DR

This study introduces an automatic classification method for DaT-SPECT images using diffusion maps and machine learning, achieving high accuracy in distinguishing normal from abnormal cases in Parkinsonism diagnosis.

Contribution

The paper presents a novel combination of diffusion maps, Nyström extension, and ensemble classifiers for robust, accurate SPECT image classification in Parkinsonism, outperforming other manifold methods and CNNs.

Findings

Diffusion maps achieved 98% accuracy on PPMI dataset.

The method outperformed LLE, Isomap, and Kernel PCA in accuracy and robustness.

High classification accuracy demonstrated on clinical datasets.

Abstract

Neurodegenerative parkinsonism can be assessed by dopamine transporter single photon emission computed tomography (DaT-SPECT). Although generating images is time consuming, these images can show interobserver variability and they have been visually interpreted by nuclear medicine physicians to date. Accordingly, this study aims to provide an automatic and robust method based on Diffusion Maps and machine learning classifiers to classify the SPECT images into two types, namely Normal and Abnormal DaT-SPECT image groups. In the proposed method, the 3D images of N patients are mapped to an N by N pairwise distance matrix and are visualized in Diffusion Maps coordinates. The images of the training set are embedded into a low-dimensional space by using diffusion maps. Moreover, we use Nystr\"om's out-of-sample extension, which embeds new sample points as the testing set in the reduced space. Testing samples in the embedded space are then classified into two types through the ensemble classifier with Linear Discriminant Analysis (LDA) and voting procedure through twenty-five-fold cross-validation results. The feasibility of the method is demonstrated via Parkinsonism Progression Markers Initiative (PPMI) dataset of 1097 subjects and a clinical cohort from Kaohsiung Chang Gung Memorial Hospital (KCGMH-TW) of 630 patients. We compare performances using Diffusion Maps with those of three alternative manifold methods for dimension reduction, namely Locally Linear Embedding (LLE), Isomorphic Mapping Algorithm (Isomap), and Kernel Principal Component Analysis (Kernel PCA). We also compare results using 2D and 3D CNN methods. The diffusion maps method has an average accuracy of 98% for the PPMI and 90% for the KCGMH-TW dataset with twenty-five fold cross-validation results. It outperforms the other three methods concerning the overall accuracy and the robustness in the training and testing samples.