scholarly journals Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mahmood Nazari ◽  
Andreas Kluge ◽  
Ivayla Apostolova ◽  
Susanne Klutmann ◽  
Sharok Kimiaei ◽  
...  
Keyword(s):  
Dopamine Transporter ◽  
Binary Classification ◽  
Temporal Cortex ◽  
Brain Regions ◽  
Classification Performance ◽  
Data Driven ◽  
3 Dimensional ◽  
Parkinsonian Syndromes ◽  
Custom Made ◽  
Spect Images

AbstractThis study used explainable artificial intelligence for data-driven identification of extrastriatal brain regions that can contribute to the interpretation of dopamine transporter SPECT with 123I-FP-CIT in parkinsonian syndromes. A total of 1306 123I-FP-CIT-SPECT were included retrospectively. Binary classification as ‘reduced’ or ‘normal’ striatal 123I-FP-CIT uptake by an experienced reader served as standard-of-truth. A custom-made 3-dimensional convolutional neural network (CNN) was trained for classification of the SPECT images with 1006 randomly selected images in three different settings: “full image”, “striatum only” (3-dimensional region covering the striata cropped from the full image), “without striatum” (full image with striatal region removed). The remaining 300 SPECT images were used to test the CNN classification performance. Layer-wise relevance propagation (LRP) was used for voxelwise quantification of the relevance for the CNN-based classification in this test set. Overall accuracy of CNN-based classification was 97.0%, 95.7%, and 69.3% in the “full image”, “striatum only”, and “without striatum” setting. Prominent contributions in the LRP-based relevance maps beyond the striatal signal were detected in insula, amygdala, ventromedial prefrontal cortex, thalamus, anterior temporal cortex, superior frontal lobe, and pons, suggesting that 123I-FP-CIT uptake in these brain regions provides clinically useful information for the differentiation of neurodegenerative and non-neurodegenerative parkinsonian syndromes.

scholarly journals Mental Task Evaluation for Hybrid NIRS-EEG Brain-Computer Interfaces

2017 ◽  
Vol 2017 ◽  
pp. 1-24 ◽  
Author(s):  
Hubert Banville ◽  
Rishabh Gupta ◽  
Tiago H. Falk
Keyword(s):  
Near Infrared ◽  
Mental Arithmetic ◽  
Binary Classification ◽  
Time Windows ◽  
Brain Regions ◽  
Classification Performance ◽  
Response Patterns ◽  
Word Generation ◽  
Nirs Data ◽  
Accuracy Increase

Based on recent electroencephalography (EEG) and near-infrared spectroscopy (NIRS) studies that showed that tasks such as motor imagery and mental arithmetic induce specific neural response patterns, we propose a hybrid brain-computer interface (hBCI) paradigm in which EEG and NIRS data are fused to improve binary classification performance. We recorded simultaneous NIRS-EEG data from nine participants performing seven mental tasks (word generation, mental rotation, subtraction, singing and navigation, and motor and face imagery). Classifiers were trained for each possible pair of tasks using (1) EEG features alone, (2) NIRS features alone, and (3) EEG and NIRS features combined, to identify the best task pairs and assess the usefulness of a multimodal approach. The NIRS-EEG approach led to an average increase in peak kappa of 0.03 when using features extracted from one-second windows (equivalent to an increase of 1.5% in classification accuracy for balanced classes). The increase was much stronger (0.20, corresponding to an 10% accuracy increase) when focusing on time windows of high NIRS performance. The EEG and NIRS analyses further unveiled relevant brain regions and important feature types. This work provides a basis for future NIRS-EEG hBCI studies aiming to improve classification performance toward more efficient and flexible BCIs.

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

2021 ◽  
Author(s):  
Mahmood Nazari ◽  
Andreas Kluge ◽  
Ivayla Apostolova ◽  
Susanne Klutmann ◽  
Sharok Kimiaei ◽  
...  
Keyword(s):  
Neural Networks ◽  
Dopamine Transporter ◽  
Convolutional Neural Networks ◽  
Automatic Classification ◽  
Clinical Workflow ◽  
Deep Convolutional Neural Networks ◽  
Parkinsonian Syndromes ◽  
Custom Made ◽  
Dat Spect

Abstract Purpose Deep convolutional neural networks (CNN) provide high accuracy for automatic classification of dopamine transporter (DAT) SPECT images. However, CNN are inherently black-box in nature lacking any kind of explanation for their decisions. This limits their acceptance for clinical use. This study tested layer-wise relevance propagation (LRP) to explain CNN-based classification of DAT-SPECT in patients with clinically uncertain parkinsonian syndromes. Methods The study retrospectively included 1296 clinical DAT-SPECT with visual binary interpretation as “normal” or “reduced” by two experienced readers as standard-of-truth. A custom-made CNN was trained with 1008 randomly selected DAT-SPECT. The remaining 288 DAT-SPECT were used to assess classification performance of the CNN and to test LRP for explanation of the CNN-based classification. Results Overall accuracy, sensitivity, and specificity of the CNN were 95.8%, 92.8%, and 98.7%, respectively. LRP provided relevance maps that were easy to interpret in each individual DAT-SPECT. In particular, the putamen in the hemisphere most affected by nigrostriatal degeneration was the most relevant brain region for CNN-based classification in all reduced DAT-SPECT. Some misclassified DAT-SPECT showed an “inconsistent” relevance map more typical for the true class label. Conclusion LRP is useful to provide explanation of CNN-based decisions in individual DAT-SPECT and, therefore, can be recommended to support CNN-based classification of DAT-SPECT in clinical routine. Total computation time of 3 s is compatible with busy clinical workflow. The utility of “inconsistent” relevance maps to identify misclassified cases requires further investigation.

scholarly journals EEGG: An analytic brain-computer interface algorithm

2021 ◽  
Author(s):  
Gang Liu ◽  
Jing Wang
Keyword(s):  
Brain Regions ◽  
Poor Quality ◽  
Classification Performance ◽  
Black Box ◽  
Data Driven ◽  
Left Hand ◽  
Convolutional Networks ◽  
Data Driven Approach ◽  
Traditional Sense ◽  
The Brain

<div><div><b>Objective.</b> In the traditional sense, the modeling approaches can be divided into white-box (physics-based), black-box (data-driven), and gray-box (the combination of physics-based and data-driven). Because the human brain is a black box itself, the EEG-BCI algorithm is generally a data-driven approach. It generates a black-box or gray-box (e.g., "Visualizing convolutional networks") model. However, one black- or gray-box cannot completely explain the brain. This paper presents the first analytic "white-box" EEG-BCI algorithm using Gang neurons (EEGG).</div><div><br></div><div><b>Approach.</b> Independent and interactive components of neurons or brain regions can fully describe the brain. This paper constructed a relationship frame based on the independent and interactive compositions for intention recognition and analysis using a novel dendrite module of Gang neuron. A total of 4,906 EEG data about motor imagery (MI) of left-hand and right-hand movements from 26 subjects were obtained from GigaDB. Firstly, this paper explored EEGG's classification performance according to cross-subject accuracy. Secondly, this paper transformed the EEGG model into a relation spectrum expressing independent and interactive components of brain regions. Then, the relation spectrum was verified through the known ERD/ERS phenomenon. Finally, this paper explored the previously unreachable further BCI-based analysis of brain.</div><div><br></div><div><b>Main results.</b> (1) EEGG was more robust than typical "CSP+" algorithms for the data of poor quality [AUC:0.825±0.074(EEGG)>0.745±0.094(CSP+LDA)/0.591±0.104(CSP+Bayes)/0.750±0.091(CSP+SVM), p<0.001]. (2) The relation spectrum showed the known ERD/ERS phenomenon. (3) Interestingly, EEGG showed that brain regions' interactive components put a brake on ERD/ERS effects for classification (p<0.001). This means that generating fine hand intention needs more centralized activation in the brain.</div><div><br></div><div><b>Significance.</b> EEGG decomposed the biological EEG-intention system of this paper into the relation spectrum inheriting Taylor series, rather than the fuzzy interpretation of outputs, which offers a novel frame for analysis of the brain.</div></div><div><p></p></div>

scholarly journals EEGG: An Analytic Brain-computer Interface Algorithm

2021 ◽  
Author(s):  
Gang Liu ◽  
Jing Wang
Keyword(s):  
Brain Activity ◽  
Brain Regions ◽  
Classification Performance ◽  
Data Driven ◽  
Computer Interface ◽  
Eeg Signals ◽  
Eeg Data ◽  
Data Driven Approach ◽  
Left And Right ◽  
The Brain

<div><div> <p><a></a></p><div> <p><a></a><a><i>Objective. </i></a>Modeling the brain as a white box is vital for investigating the brain. However, the physical properties of the human brain are unclear. Therefore, BCI algorithms using EEG signals are generally a data-driven approach and generate a black- or gray-box model. This paper presents the first EEG-based BCI algorithm (EEGBCI using Gang neurons, EEGG) decomposing the brain into some simple components with physical meaning and integrating recognition and analysis of brain activity. </p> <p><i>Approach. </i>Independent and interactive components of neurons or brain regions can fully describe the brain. This paper constructed a relationship frame based on the independent and interactive compositions for intention recognition and analysis using a novel dendrite module of Gang neurons. A total of 4,906 EEG data of left- and right-hand motor imagery(MI) from 26 subjects were obtained from GigaDB. Firstly, this paper explored EEGG’s classification performance by cross-subject accuracy. Secondly, this paper transformed the trained EEGG model into a relation spectrum expressing independent and interactive components of brain regions. Then, the relation spectrum was verified using the known ERD/ERS phenomenon. Finally, this paper explored the previously unreachable further BCIbased analysis of the brain. </p> <p><i>Main results. </i>(1) EEGG was more robust than typical “CSP+” algorithms for the poorquality data. (2) The relation spectrum showed the known ERD/ERS phenomenon. (3) Interestingly, EEGG showed that interactive components between brain regions suppressed ERD/ERS effects on classification. This means that generating fine hand intention needs more centralized activation in the brain. </p> <p><i>Significance. </i>EEGG decomposed the biological EEG-intention system of this paper into the relation spectrum inheriting the Taylor series (<i>in analogy with the data-driven but human-readable Fourier transform and frequency spectrum</i>), which offers a novel frame for analysis of the brain.</p> </div> </div></div><div><p></p></div>

scholarly journals Deep Learning-Based Classification of GAD67-Positive Neurons Without the Immunosignal

2021 ◽  
Vol 15 ◽  
Author(s):  
Kotaro Yamashiro ◽  
Jiayan Liu ◽  
Nobuyoshi Matsumoto ◽  
Yuji Ikegaya
Keyword(s):  
Deep Learning ◽  
Primary Motor Cortex ◽  
Learning Algorithm ◽  
Binary Classification ◽  
Brain Regions ◽  
Acid Decarboxylase ◽  
Cell Type ◽  
Custom Made ◽  
Excitatory Neurons

Excitatory neurons and GABAergic interneurons constitute neural circuits and play important roles in information processing. In certain brain regions, such as the neocortex and the hippocampus, there are fewer interneurons than excitatory neurons. Interneurons have been quantified via immunohistochemistry, for example, for GAD67, an isoform of glutamic acid decarboxylase. Additionally, the expression level of other proteins varies among cell types. For example, NeuN, a commonly used marker protein for postmitotic neurons, is expressed differently across brain regions and cell classes. Thus, we asked whether GAD67-immunopositive neurons can be detected using the immunofluorescence signals of NeuN and the fluorescence signals of Nissl substances. To address this question, we stained neurons in layers 2/3 of the primary somatosensory cortex (S1) and the primary motor cortex (M1) of mice and manually labeled the neurons as either cell type using GAD67 immunosignals. We then sought to detect GAD67-positive neurons without GAD67 immunosignals using a custom-made deep learning-based algorithm. Using this deep learning-based model, we succeeded in the binary classification of the neurons using Nissl and NeuN signals without referring to the GAD67 signals. Furthermore, we confirmed that our deep learning-based method surpassed classic machine-learning methods in terms of binary classification performance. Combined with the visualization of the hidden layer of our deep learning algorithm, our model provides a new platform for identifying unbiased criteria for cell-type classification.

A Study on the Auxiliary Diagnosis of Thyroid Disease Images Based on Multiple Dimensional Deep Learning Algorithms

2020 ◽  
Vol 16 (3) ◽  
pp. 199-205
Author(s):  
Yuejun Liu ◽  
Yifei Xu ◽  
Xiangzheng Meng ◽  
Xuguang Wang ◽  
Tianxu Bai
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Region Of Interest ◽  
Classification Performance ◽  
Thyroid Diseases ◽  
Great Success ◽  
Learning Models ◽  
Good Classification Performance ◽  
Spect Images

Background: Medical imaging plays an important role in the diagnosis of thyroid diseases. In the field of machine learning, multiple dimensional deep learning algorithms are widely used in image classification and recognition, and have achieved great success. Objective: The method based on multiple dimensional deep learning is employed for the auxiliary diagnosis of thyroid diseases based on SPECT images. The performances of different deep learning models are evaluated and compared. Methods: Thyroid SPECT images are collected with three types, they are hyperthyroidism, normal and hypothyroidism. In the pre-processing, the region of interest of thyroid is segmented and the amount of data sample is expanded. Four CNN models, including CNN, Inception, VGG16 and RNN, are used to evaluate deep learning methods. Results: Deep learning based methods have good classification performance, the accuracy is 92.9%-96.2%, AUC is 97.8%-99.6%. VGG16 model has the best performance, the accuracy is 96.2% and AUC is 99.6%. Especially, the VGG16 model with a changing learning rate works best. Conclusion: The standard CNN, Inception, VGG16, and RNN four deep learning models are efficient for the classification of thyroid diseases with SPECT images. The accuracy of the assisted diagnostic method based on deep learning is higher than that of other methods reported in the literature.

scholarly journals Using Artificial Neural Network to Discriminate Parkinson’s Disease from Other Parkinsonisms by Focusing on Putamen of Dopamine Transporter SPECT Images

Biomedicines ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 12
Author(s):  
Chung-Yao Chien ◽  
Szu-Wei Hsu ◽  
Tsung-Lin Lee ◽  
Pi-Shan Sung ◽  
Chou-Ching Lin
Keyword(s):  
Neural Network ◽  
Parkinson’S Disease ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Parkinson's Disease ◽  
Dopamine Transporter ◽  
Support Vector ◽  
Dat Spect ◽  
Ann Classifier ◽  
Spect Images

Background: The challenge of differentiating, at an early stage, Parkinson’s disease from parkinsonism caused by other disorders remains unsolved. We proposed using an artificial neural network (ANN) to process images of dopamine transporter single-photon emission computed tomography (DAT-SPECT). Methods: Abnormal DAT-SPECT images of subjects with Parkinson’s disease and parkinsonism caused by other disorders were divided into training and test sets. Striatal regions of the images were segmented by using an active contour model and were used as the data to perform transfer learning on a pre-trained ANN to discriminate Parkinson’s disease from parkinsonism caused by other disorders. A support vector machine trained using parameters of semi-quantitative measurements including specific binding ratio and asymmetry index was used for comparison. Results: The predictive accuracy of the ANN classifier (86%) was higher than that of the support vector machine classifier (68%). The sensitivity and specificity of the ANN classifier in predicting Parkinson’s disease were 81.8% and 88.6%, respectively. Conclusions: The ANN classifier outperformed classical biomarkers in differentiating Parkinson’s disease from parkinsonism caused by other disorders. This classifier can be readily included into standalone computer software for clinical application.

Custom-Made Titanium 3-Dimensional Printed Interbody Cages for Treatment of Osteoporotic Fracture–Related Spinal Deformity

2018 ◽  
Vol 111 ◽  
pp. 1-5 ◽  
Author(s):  
Timothy L. Siu ◽  
Jeffrey M. Rogers ◽  
Kainu Lin ◽  
Robert Thompson ◽  
Mark Owbridge
Keyword(s):  
Osteoporotic Fracture ◽  
Spinal Deformity ◽  
3 Dimensional ◽  
Custom Made

scholarly journals Depression Disorder Classification of fMRI Data Using Sparse Low-Rank Functional Brain Network and Graph-Based Features

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Xin Wang ◽  
Yanshuang Ren ◽  
Wensheng Zhang
Keyword(s):  
Pearson Correlation ◽  
Brain Regions ◽  
Brain Network ◽  
Classification Performance ◽  
Low Rank ◽  
Fmri Data ◽  
Healthy Controls ◽  
Functional Brain ◽  
Functional Brain Network ◽  
Depression Disorder

Study of functional brain network (FBN) based on functional magnetic resonance imaging (fMRI) has proved successful in depression disorder classification. One popular approach to construct FBN is Pearson correlation. However, it only captures pairwise relationship between brain regions, while it ignores the influence of other brain regions. Another common issue existing in many depression disorder classification methods is applying only single local feature extracted from constructed FBN. To address these issues, we develop a new method to classify fMRI data of patients with depression and healthy controls. First, we construct the FBN using a sparse low-rank model, which considers the relationship between two brain regions given all the other brain regions. Moreover, it can automatically remove weak relationship and retain the modular structure of FBN. Secondly, FBN are effectively measured by eight graph-based features from different aspects. Tested on fMRI data of 31 patients with depression and 29 healthy controls, our method achieves 95% accuracy, 96.77% sensitivity, and 93.10% specificity, which outperforms the Pearson correlation FBN and sparse FBN. In addition, the combination of graph-based features in our method further improves classification performance. Moreover, we explore the discriminative brain regions that contribute to depression disorder classification, which can help understand the pathogenesis of depression disorder.

Sign in / Sign up

Export Citation Format

Share Document