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

Incorporating label uncertainty during the training of convolutional neural networks improves performance for the discrimination between certain and inconclusive cases in dopamine transporter SPECT

PURPOSE

Deep convolutional neural networks (CNN) hold promise for assisting the interpretation of dopamine transporter (DAT)-SPECT. For improved communication of uncertainty to the user it is crucial to reliably discriminate certain from inconclusive cases that might be misclassified by strict application of a predefined decision threshold on the CNN output. This study tested two methods to incorporate existing label uncertainty during the training to improve the utility of the CNN sigmoid output for this task.

METHODS

Three datasets were used retrospectively: a "development" dataset (n = 1740) for CNN training, validation and testing, two independent out-of-distribution datasets (n = 640, 645) for testing only. In the development dataset, binary classification based on visual inspection was performed carefully by three well-trained readers. A ResNet-18 architecture was trained for binary classification of DAT-SPECT using either a randomly selected vote ("random vote training", RVT), the proportion of "reduced" votes ( "average vote training", AVT) or the majority vote (MVT) across the three readers as reference standard. Balanced accuracy was computed separately for "inconclusive" sigmoid outputs (within a predefined interval around the 0.5 decision threshold) and for "certain" (non-inconclusive) sigmoid outputs.

RESULTS

The proportion of "inconclusive" test cases that had to be accepted to achieve a given balanced accuracy in the "certain" test case was lower with RVT and AVT than with MVT in all datasets (e.g., 1.9% and 1.2% versus 2.8% for 98% balanced accuracy in "certain" test cases from the development dataset). In addition, RVT and AVT resulted in slightly higher balanced accuracy in all test cases independent of their certainty (97.3% and 97.5% versus 97.0% in the development dataset).

CONCLUSION

Making between-readers-discrepancy known to CNN during the training improves the utility of their sigmoid output to discriminate certain from inconclusive cases that might be misclassified by the CNN when the predefined decision threshold is strictly applied. This does not compromise on overall accuracy.

Deep Convolutional Neural Networks on Multiclass Classification of Three-Dimensional Brain Images for Parkinson's Disease Stage Prediction

Parkinson's disease (PD), a degenerative disorder of the central nervous system, is commonly diagnosed using functional medical imaging techniques such as single-photon emission computed tomography (SPECT). In this study, we utilized two SPECT data sets (n = 634 and n = 202) from different hospitals to develop a model capable of accurately predicting PD stages, a multiclass classification task. We used the entire three-dimensional (3D) brain images as input and experimented with various model architectures. Initially, we treated the 3D images as sequences of two-dimensional (2D) slices and fed them sequentially into 2D convolutional neural network (CNN) models pretrained on ImageNet, averaging the outputs to obtain the final predicted stage. We also applied 3D CNN models pretrained on Kinetics-400. Additionally, we incorporated an attention mechanism to account for the varying importance of different slices in the prediction process. To further enhance model efficacy and robustness, we simultaneously trained the two data sets using weight sharing, a technique known as cotraining. Our results demonstrated that 2D models pretrained on ImageNet outperformed 3D models pretrained on Kinetics-400, and models utilizing the attention mechanism outperformed both 2D and 3D models. The cotraining technique proved effective in improving model performance when the cotraining data sets were sufficiently large.

Enhancing early Parkinson's disease detection through multimodal deep learning and explainable AI: insights from the PPMI database

Parkinson's is the second most common neurodegenerative disease, affecting nearly 8.5M people and steadily increasing. In this research, Multimodal Deep Learning is investigated for the Prodromal stage detection of Parkinson's Disease (PD), combining different 3D architectures with the novel Excitation Network (EN) and supported by Explainable Artificial Intelligence (XAI) techniques. Utilizing data from the Parkinson's Progression Markers Initiative, this study introduces a joint co-learning approach for multimodal fusion, enabling end-to-end training of deep neural networks and facilitating the learning of complementary information from both imaging and clinical modalities. DenseNet with EN outperformed other models, showing a substantial increase in accuracy when supplemented with clinical data. XAI methods, such as Integrated Gradients for ResNet and DenseNet, and Attention Heatmaps for Vision Transformer (ViT), revealed that DenseNet focused on brain regions believed to be critical to prodromal pathophysiology, including the right temporal and left pre-frontal areas. Similarly, ViT highlighted the lateral ventricles associated with cognitive decline, indicating their potential in the Prodromal stage. These findings underscore the potential of these regions as early-stage PD biomarkers and showcase the proposed framework's efficacy in predicting subtypes of PD and aiding in early diagnosis, paving the way for innovative diagnostic tools and precision medicine.

The role of AI and machine learning in the diagnosis of Parkinson's disease and atypical parkinsonisms

Parkinson's disease is a neurodegenerative movement disorder associated with motor and non-motor symptoms causing severe disability as the disease progresses. The development of biomarkers for Parkinson's disease to diagnose patients earlier and predict disease progression is imperative. As artificial intelligence and machine learning techniques efficiently process data and can handle multiple data types, we reviewed the literature to determine the extent to which these techniques have been applied to biomarkers for Parkinson's disease and movement disorders. We determined that the most applicable machine learning techniques are support vector machines and neural networks, depending on the size and type of the data being analyzed. Additionally, more complex machine learning techniques showed increased accuracy when compared to less complex techniques, especially when multiple machine learning models were combined. We can conclude that artificial intelligence and machine learning techniques may have the capacity to significantly boost diagnostic capacity in movement disorders and Parkinson's disease.

Neuroimaging and fluid biomarkers in Parkinson's disease in an era of targeted interventions

A major challenge in Parkinson's disease is the variability in symptoms and rates of progression, underpinned by heterogeneity of pathological processes. Biomarkers are urgently needed for accurate diagnosis, patient stratification, monitoring disease progression and precise treatment. These were previously lacking, but recently, novel imaging and fluid biomarkers have been developed. Here, we consider new imaging approaches showing sensitivity to brain tissue composition, and examine novel fluid biomarkers showing specificity for pathological processes, including seed amplification assays and extracellular vesicles. We reflect on these biomarkers in the context of new biological staging systems, and on emerging techniques currently in development.

Automated identification of uncertain cases in deep learning-based classification of dopamine transporter SPECT to improve clinical utility and acceptance

PURPOSE

Deep convolutional neural networks (CNN) are promising for automatic classification of dopamine transporter (DAT)-SPECT images. Reporting the certainty of CNN-based decisions is highly desired to flag cases that might be misclassified and, therefore, require particularly careful inspection by the user. The aim of the current study was to design and validate a CNN-based system for the identification of uncertain cases.

METHODS

A network ensemble (NE) combining five CNNs was trained for binary classification of [123I]FP-CIT DAT-SPECT images as "normal" or "neurodegeneration-typical reduction" with high accuracy (NE for classification, NEfC). An uncertainty detection module (UDM) was obtained by combining two additional NE, one trained for detection of "reduced" DAT-SPECT with high sensitivity, the other with high specificity. A case was considered "uncertain" if the "high sensitivity" NE and the "high specificity" NE disagreed. An internal "development" dataset of 1740 clinical DAT-SPECT images was used for training (n = 1250) and testing (n = 490). Two independent datasets with different image characteristics were used for testing only (n = 640, 645). Three established approaches for uncertainty detection were used for comparison (sigmoid, dropout, model averaging).

RESULTS

In the test data from the development dataset, the NEfC achieved 98.0% accuracy. 4.3% of all test cases were flagged as "uncertain" by the UDM: 2.5% of the correctly classified cases and 90% of the misclassified cases. NEfC accuracy among "certain" cases was 99.8%. The three comparison methods were less effective in labelling misclassified cases as "uncertain" (40-80%). These findings were confirmed in both additional test datasets.

CONCLUSION

The UDM allows reliable identification of uncertain [123I]FP-CIT SPECT with high risk of misclassification. We recommend that automatic classification of [123I]FP-CIT SPECT images is combined with an UDM to improve clinical utility and acceptance. The proposed UDM method ("high sensitivity versus high specificity") might be useful also for DAT imaging with other ligands and for other binary classification tasks.

Dopaminergic imaging in degenerative parkinsonisms, an established clinical diagnostic tool

Parkinson's disease (PD) and other neurodegenerative parkinsonisms are characterised by loss of striatal dopaminergic neurons. Dopamine functional deficits can be measured in vivo using positron emission tomography (PET) and single-photon emission computed tomography (SPECT) ligands assessing either presynaptic (e.g. dopamine synthesis and storage, transporter density) or postsynaptic terminals (i.e. D2 receptors availability). Nuclear medicine imaging thus helps the clinician to separate degenerative forms of parkinsonism with other neurological conditions, e.g. essential tremor or drug-induced parkinsonism. With the present study, we aimed at summarizing the current evidence about dopaminergic molecular imaging in the diagnostic evaluation of PD, atypical parkinsonian syndromes and dementia with Lewy bodies (DLB), as well as its potential to distinguish these conditions and to estimate disease progression. In fact, PET/SPECT methods are clinically validated and have been increasingly integrated into diagnostic guidelines (e.g. for PD and DLB). In addition, there is novel evidence on the classification properties of extrastriatal signal. Finally, dopamine imaging has an outstanding potential to detect neurodegeneration at the premotor stage, including REM-sleep behavior disorder and olfactory loss. Therefore, inclusion of subjects at an early stage for clinical trials can largely benefit from a validated in vivo biomarker such as presynaptic dopamine pathways PET/SPECT assessment.

A Computerized Analysis with Machine Learning Techniques for the Diagnosis of Parkinson's Disease: Past Studies and Future Perspectives

According to the World Health Organization (WHO), Parkinson's disease (PD) is a neurodegenerative disease of the brain that causes motor symptoms including slower movement, rigidity, tremor, and imbalance in addition to other problems like Alzheimer's disease (AD), psychiatric problems, insomnia, anxiety, and sensory abnormalities. Techniques including artificial intelligence (AI), machine learning (ML), and deep learning (DL) have been established for the classification of PD and normal controls (NC) with similar therapeutic appearances in order to address these problems and improve the diagnostic procedure for PD. In this article, we examine a literature survey of research articles published up to September 2022 in order to present an in-depth analysis of the use of datasets, various modalities, experimental setups, and architectures that have been applied in the diagnosis of subjective disease. This analysis includes a total of 217 research publications with a list of the various datasets, methodologies, and features. These findings suggest that ML/DL methods and novel biomarkers hold promising results for application in medical decision-making, leading to a more methodical and thorough detection of PD. Finally, we highlight the challenges and provide appropriate recommendations on selecting approaches that might be used for subgrouping and connection analysis with structural magnetic resonance imaging (sMRI), DaTSCAN, and single-photon emission computerized tomography (SPECT) data for future Parkinson's research.

Explainable machine learning with pairwise interactions for the classification of Parkinson's disease and SWEDD from clinical and imaging features

Scans without evidence of dopaminergic deficit (SWEDD) refers to patients who mimics motor and non-motor symptoms of Parkinson's disease (PD) but showing integrity of dopaminergic system. For this reason, the differential diagnosis between SWEDD and PD patients is often not possible in absence of dopamine imaging. Machine Learning (ML) showed optimal performance in automatically distinguishing these two diseases from clinical and imaging data. However, the most common applied ML algorithms provide high accuracy at expense of findings intelligibility. In this work, a novel ML glass-box model, the Explainable Boosting Machine (EBM), based on Generalized Additive Models plus interactions (GA2Ms), was employed to obtain interpretability in classifying PD and SWEDD while still providing optimal performance. Dataset (168 healthy controls, HC; 396 PD; 58 SWEDD) was obtained from PPMI database and consisted of 178 among clinical and imaging features. Six binary EBM classifiers were trained on feature space with (SBR) and without (noSBR) dopaminergic striatal specific binding ratio: HC-PDSBR, HC-SWEDDSBR, PD-SWEDDSBR and HC-PDnoSBR, HC-SWEDDnoSBR, PD-SWEDDnoSBR. Excellent AUC-ROC (1) was reached in classifying HC from PD and SWEDD, both with and without SBR, and by PD-SWEDDSBR (0.986), while PD-SWEDDnoSBR showed lower AUC-ROC (0.882). Apart from optimal accuracies, EBM algorithm was able to provide global and local explanations, revealing that the presence of pairwise interactions between UPSIT Booklet #1 and Epworth Sleepiness Scale item 3 (ESS3), MDS-UPDRS-III pronation-supination movements right hand (NP3PRSPR) and MDS-UPDRS-III rigidity left upper limb (NP3RIGLU) could provide good performance in predicting PD and SWEDD also without imaging features.

Soft Attention Based DenseNet Model for Parkinson’s Disease Classification Using SPECT Images

Objective

Deep learning algorithms have long been involved in the diagnosis of severe neurological disorders that interfere with patients’ everyday tasks, such as Parkinson’s disease (PD). The most effective imaging modality for detecting the condition is DaTscan, a variety of single-photon emission computerized tomography (SPECT) imaging method. The goal is to create a convolutional neural network that can specifically identify the region of interest following feature extraction.

Methods

The study comprised a total of 1,390 DaTscan imaging groups with PD and normal classes. The architecture of DenseNet-121 is leveraged with a soft-attention block added before the final classification layer. For visually analyzing the region of interest (ROI) from the images after classification, Soft Attention Maps and feature map representation are used.

Outcomes

The model obtains an overall accuracy of 99.2% and AUC-ROC score 99%. A sensitivity of 99.2%, specificity of 99.4% and f1-score of 99.1% is achieved that surpasses all prior research findings. Soft-attention map and feature map representation aid in highlighting the ROI, with a specific attention on the putamen and caudate regions.

Conclusion

With the deep learning framework adopted, DaTscan images reveal the putamen and caudate areas of the brain, which aid in the distinguishing of normal and PD cohorts with high accuracy and sensitivity.

Multi-Class Classifier in Parkinson’s Disease Using an Evolutionary Multi-Objective Optimization Algorithm

In this contribution, a novel methodology for multi-class classification in the field of Parkinson’s disease is proposed. The methodology is structured in two phases. In a first phase, the most relevant volumes of interest (VOI) of the brain are selected by means of an evolutionary multi-objective optimization (MOE) algorithm. Each of these VOIs are subjected to volumetric feature extraction using the Three-Dimensional Discrete Wavelet Transform (3D-DWT). When applying 3D-DWT, a high number of coefficients is obtained, requiring the use of feature selection/reduction algorithms to find the most relevant features. The method used in this contribution is based on Mutual Redundancy (MI) and Minimum Maximum Relevance (mRMR) and PCA. To optimize the VOI selection, a first group of 550 MRI was used for the 5 classes: PD, SWEDD, Prodromal, GeneCohort and Normal. Once the Pareto Front of the solutions is obtained (with varying degrees of complexity, reflected in the number of selected VOIs), these solutions are tested in a second phase. In order to analyze the SVM classifier accuracy, a test set of 367 MRI was used. The methodology obtains relevant results in multi-class classification, presenting several solutions with different levels of complexity and precision (Pareto Front solutions), reaching a result of 97% as the highest precision in the test data.

Brain Tumor Classification Using a Combination of Variational Autoencoders and Generative Adversarial Networks

Brain tumors are a pernicious cancer with one of the lowest five-year survival rates. Neurologists often use magnetic resonance imaging (MRI) to diagnose the type of brain tumor. Automated computer-assisted tools can help them speed up the diagnosis process and reduce the burden on the health care systems. Recent advances in deep learning for medical imaging have shown remarkable results, especially in the automatic and instant diagnosis of various cancers. However, we need a large amount of data (images) to train the deep learning models in order to obtain good results. Large public datasets are rare in medicine. This paper proposes a framework based on unsupervised deep generative neural networks to solve this limitation. We combine two generative models in the proposed framework: variational autoencoders (VAEs) and generative adversarial networks (GANs). We swap the encoder-decoder network after initially training it on the training set of available MR images. The output of this swapped network is a noise vector that has information of the image manifold, and the cascaded generative adversarial network samples the input from this informative noise vector instead of random Gaussian noise. The proposed method helps the GAN to avoid mode collapse and generate realistic-looking brain tumor magnetic resonance images. These artificially generated images could solve the limitation of small medical datasets up to a reasonable extent and help the deep learning models perform acceptably. We used the ResNet50 as a classifier, and the artificially generated brain tumor images are used to augment the real and available images during the classifier training. We compared the classification results with several existing studies and state-of-the-art machine learning models. Our proposed methodology noticeably achieved better results. By using brain tumor images generated artificially by our proposed method, the classification average accuracy improved from 72.63% to 96.25%. For the most severe class of brain tumor, glioma, we achieved 0.769, 0.837, 0.833, and 0.80 values for recall, specificity, precision, and F1-score, respectively. The proposed generative model framework could be used to generate medical images in any domain, including PET (positron emission tomography) and MRI scans of various parts of the body, and the results show that it could be a useful clinical tool for medical experts.

Biomarkers in Neurodegenerative Diseases

An increasing number of people are affected by various neurodegenerative diseases each year, impacting the quality of life of millions of people worldwide [...]

Application of Deep Learning Models for Automated Identification of Parkinson's Disease: A Review (2011-2021)

Parkinson’s disease (PD) is the second most common neurodegenerative disorder affecting over 6 million people globally. Although there are symptomatic treatments that can increase the survivability of the disease, there are no curative treatments. The prevalence of PD and disability-adjusted life years continue to increase steadily, leading to a growing burden on patients, their families, society and the economy. Dopaminergic medications can significantly slow down the progression of PD when applied during the early stages. However, these treatments often become less effective with the disease progression. Early diagnosis of PD is crucial for immediate interventions so that the patients can remain self-sufficient for the longest period of time possible. Unfortunately, diagnoses are often late, due to factors such as a global shortage of neurologists skilled in early PD diagnosis. Computer-aided diagnostic (CAD) tools, based on artificial intelligence methods, that can perform automated diagnosis of PD, are gaining attention from healthcare services. In this review, we have identified 63 studies published between January 2011 and July 2021, that proposed deep learning models for an automated diagnosis of PD, using various types of modalities like brain analysis (SPECT, PET, MRI and EEG), and motion symptoms (gait, handwriting, speech and EMG). From these studies, we identify the best performing deep learning model reported for each modality and highlight the current limitations that are hindering the adoption of such CAD tools in healthcare. Finally, we propose new directions to further the studies on deep learning in the automated detection of PD, in the hopes of improving the utility, applicability and impact of such tools to improve early detection of PD globally.

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

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.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05569-9.

Artificial Intelligence Algorithm-Based Ultrasound Image Segmentation Technology in the Diagnosis of Breast Cancer Axillary Lymph Node Metastasis

This paper aimed to investigate the application of ultrasound image segmentation technology based on the back propagation neural network (BPNN) artificial intelligence algorithm in the diagnosis of breast cancer axillary lymph node metastasis, thereby providing a theoretical basis for clinical diagnosis. In this study, 90 breast cancer patients with axillary lymph node metastasis were selected as the research objects and rolled randomly into an experimental group and a control group. Besides, all of them were examined by ultrasound. The BPNN algorithm for the ultrasound image segmentation diagnosis method was applied to the patiens from the experimental group, while the control group was given routine ultrasound diagnosis. Thus, the value of this algorithm in ultrasonic diagnosis was compared and explored. The results showed that when the number of hidden layer nodes based on the BPNN artificial intelligence algorithm was 2, 3, 4, 5, 6, 7, and 8, the corresponding segmentation accuracy was 97.3%, 96.5%, 94.8%, 94.8%, and 94.1% in turn. Among them, the segmentation accuracy was the highest when the number of hidden layer nodes was 2. The correlation of independent variable bubble plot analysis showed that the presence or absence of capsules, the presence of crab feet or burrs in breast cancer lesions was critical influencing factors for the occurrence of axillary lymph node metastasis, and the standardized importance was 99.7% and 70.8%, respectively. Besides, the area under the two-dimensional receiver operating characteristic (ROC) curve of the BPNN artificial intelligence algorithm model classification was always greater than the area under the curve of manual segmentation, and the segmentation accuracy was 90.31%, 94.88%, 95.48%, 95.44%, and 97.65% in sequence. In addition, the segmentation specificity of different running times was higher than that of manual segmentation. In conclusion, the BPNN artificial intelligence algorithm had high accuracy, sensitivity, and specificity for ultrasound image segmentation, with a better segmentation effect. Therefore, it had a better diagnostic effect for breast cancer axillary lymph node metastasis.

Peripheral neuroimmune interactions: selected review and some clinical implications

Purpose

To provide a brief and focused review on peripheral neuroimmune interactions and their implications for some clinical disorders.

Methods

Narrative review of the literature including of English-language articles published between 1985 and 2021 using PubMed and MEDLINE.

Results

Many studies on experimental models and in vitro indicate that there are close interactions between the neural and immune systems. Processes from sensory afferents and autonomic efferents co-localize with immune cells and interact at discrete anatomical sites forming neuroimmune units. These neuroimmune interactions are bidirectional and mediated by a wide range of soluble factors including neuropeptides, classical neurotransmitters, cytokines, and other molecules that mediate complex cross-talk among nerves and immune cells. Small-diameter sensory afferents express a wide range of receptors that respond directly to tissue damage or pathogen signals and to chemokines, cytokines, or other molecules released from immune cells. Reciprocally, immune cells respond to neurotransmitters released from nociceptive and autonomic fibers. Neuroimmune interactions operate both at peripheral tissues and at the level of the central nervous system. Both centrally and peripherally, glial cells have a major active role in this bidirectional communication.

Conclusions

Peripheral neuroimmune interactions are complex and importantly contribute to the pathophysiology of several disorders, including skin, respiratory, and intestinal inflammatory disorders typically associated with pain and altered barrier function. These interactions may be relevant for persistence of symptoms in disorders associated with intense immune activation.