RECORD
Dopamine Transporter SPECT Image Classification for Neurodegenerative Parkinsonism via Diffusion Maps and Machine Learning Classifiers
Computer Vision and Pattern Recognition · Submitted 6 Apr 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim It outperforms the other three methods concerning the overall accuracy and the robustness in the training and testing samples.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Neurodegenerative parkinsonism can be assessed by dopamine transporter single photon emission computed tomography (DaT-SPECT). | background 1.00 | 0.05 | 0.02 | asserted 0.94 |
| s1 | Although generating images is time consuming, these images can show interobserver variability and they have been visually interpreted by nuclear medicine physicians to date. | background 0.84 | 0.07 | 0.02 | asserted 0.99 |
| s2 | 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. | contribution 0.99 | 0.45 | 0.07 | asserted 0.87 |
| s3 | 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. | method 1.00 | 0.88 | 0.02 | asserted 1.00 |
| s4 | The images of the training set are embedded into a low-dimensional space by using diffusion maps. | method 1.00 | 0.92 | 0.03 | asserted 1.00 |
| s5 | Moreover, we use Nystr\"om's out-of-sample extension, which embeds new sample points as the testing set in the reduced space. | method 1.00 | 0.91 | 0.02 | asserted 1.00 |
| s6 | 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. | method 1.00 | 0.94 | 0.06 | asserted 0.99 |
| s7 | 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. | method 0.89 | 0.88 | 0.05 | asserted 1.00 |
| s8 | 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). | method 0.85 | 0.93 | 0.03 | asserted 0.78 |
| s9 | We also compare results using 2D and 3D CNN methods. | method 0.80 | 0.90 | 0.02 | asserted 0.74 |
| s10 | 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. | result 1.00 | 0.96 | 0.49 | asserted 1.00 |
| s11 | It outperforms the other three methods concerning the overall accuracy and the robustness in the training and testing samples. | result 0.82 | 0.94 | 0.62 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 1 sentence without a confident label
Uses the method or tool of 1 paper
-
We implement the KCGMH-TWdataset with three SPECT images from $9×9$ grids as a high-order brain image tensor as input to the 3D-Convolutional Neural Network model [ref] .
End-to-End Parkinson Disease Diagnosis using Brain MR-Images by 3D-CNN · Classification · 0.93
Uses data or values from 1 paper
-
One is obtained from the benchmark of Parkinson's Progression Markers Initiative (PPMI) database [ref] , and the other is Taiwan clinical database.
DaTscan SPECT Image Classification for Parkinson's Disease · Introduction · 0.92
Cites as background 1 paper
-
CNNs have been widely applied for medical image analysis, including MRI and fMRI, well-known CNN models using transfer learning architecture such as AlexNet [ref] , VGG-16 [ref] , VGG-19 and Deep Convolution Network (DCNN).
Very Deep Convolutional Networks for Large-Scale Image Recognition · Introduction · 0.96
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.