Classification of the Multiple Stages of Parkinson's Disease by a Deep Convolution Neural Network Based on 99mTc-TRODAT-1 SPECT Images

Parkinson's Disease and Photobiomodulation: Potential for Treatment

Parkinson's disease is the second most common neurodegenerative disease and is increasing in incidence. The combination of motor and non-motor symptoms makes this a devastating disease for people with Parkinson's disease and their care givers. Parkinson's disease is characterised by mitochondrial dysfunction and neuronal death in the substantia nigra, a reduction in dopamine, accumulation of α-synuclein aggregates and neuroinflammation. The microbiome-gut-brain axis is also important in Parkinson's disease, involved in the spread of inflammation and aggregated α-synuclein. The mainstay of Parkinson's disease treatment is dopamine replacement therapy, which can reduce some of the motor signs. There is a need for additional treatment options to supplement available medications. Photobiomodulation (PBM) is a form of light therapy that has been shown to have multiple clinical benefits due to its enhancement of the mitochondrial electron transport chain and the subsequent increase in mitochondrial membrane potential and ATP production. PBM also modulates cellular signalling and has been shown to reduce inflammation. Clinically, PBM has been used for decades to improve wound healing, treat pain, reduce swelling and heal deep tissues. Pre-clinical experiments have indicated that PBM has the potential to improve the clinical signs of Parkinson's disease and to provide neuroprotection. This effect is seen whether the PBM is directed to the head of the animal or to other parts of the body (remotely). A small number of clinical trials has given weight to the possibility that using PBM can improve both motor and non-motor clinical signs and symptoms of Parkinson's disease and may potentially slow its progression.

Review of artificial intelligence clinical applications in Nuclear Medicine

This paper provides an in-depth analysis of the clinical applications of artificial intelligence (AI) in Nuclear Medicine, focusing on three key areas: neurology, cardiology, and oncology. Beginning with neurology, specifically Alzheimer's disease and Parkinson's disease, the paper examines reviews on diagnosis and treatment planning. The same pattern is followed in cardiology studies. In the final section on oncology, the paper explores the various AI applications in multiple cancer types, including lung, head and neck, lymphoma, and pancreatic cancer.

Deep learning-based ultra-fast identification of Raman spectra with low signal-to-noise ratio

Ensuring the correct use of cell lines is crucial to obtaining reliable experimental results and avoiding unnecessary waste of resources. Raman spectroscopy has been confirmed to be able to identify cell lines, but the collection time is usually 10-30 s. In this study, we acquired Raman spectra of five cell lines with integration times of 0.1 and 8 s, respectively, and the average accuracy of using long-short memory neural network to identify the spectra of 0.1 s was 95%, and the average accuracy of identifying the spectra of 8 s was 99.8%. At the same time, we performed data enhancement of 0.1 s spectral data by real-valued non-volume preserving method, and the recognition average accuracy of long-short memory neural networks recognition of the enhanced spectral data was improved to 96.2%. With this method, we shorten the acquisition time of Raman spectra to 1/80 of the original one, which greatly improves the efficiency of cell identification.

Evaluation of Raman spectroscopy combined with the gated recurrent unit serum detection method in early screening of gastrointestinal cancer

Gastric and colorectal cancers are significant causes of human mortality. Conventionally, the diagnosis of gastrointestinal tumors has been accomplished through image-based techniques, including endoscopic and biopsy procedures coupled with tissue staining. Most of these methods are invasive. In contrast, Raman spectroscopy has the advantages of being non-invasive and label-free and requiring no additional reagents, making it a potential tool for the detection of serum components. In this study, we collected Raman spectra of serum samples from patients with gastric cancer (n = 93) and colorectal cancer (n = 92) and from healthy individuals (n = 100). Analysis of Raman peak areas revealed that cancer patients had significantly higher peak areas at around 2923 cm-1 compared to normal individuals, which corresponded to the presence of lipids and proteins. We successfully achieved the early screening of gastrointestinal tumors using the improved gated recurrent unit (GRU) algorithm and traditional machine learning methods. The accuracy of identifying digestive tract tumors using different recognition models exceeds 84.72%, with support vector machine (SVM) and GRU achieving 100% accuracy. The use of GRU further demonstrated its ability to differentiate subtypes of gastric and colorectal cancers based on the degree of differentiation and stage, with a recognition accuracy exceeding 95%, which is challenging using traditional machine learning methods. Furthermore, our study revealed that principal component analysis (PCA) dimensionality reduction has a limited impact on the recognition results obtained using different recognition models.

Hybrid Machine Learning Framework for Multistage Parkinson's Disease Classification Using Acoustic Features of Sustained Korean Vowels

Recent research has achieved a great classification rate for separating healthy people from those with Parkinson's disease (PD) using speech and the voice. However, these studies have primarily treated early and advanced stages of PD as equal entities, neglecting the distinctive speech impairments and other symptoms that vary across the different stages of the disease. To address this limitation, and improve diagnostic precision, this study assesses the selected acoustic features of dysphonia, as they relate to PD and the Hoehn and Yahr stages, by combining various preprocessing techniques and multiple classification algorithms, to create a comprehensive and robust solution for classification tasks. The dysphonia features extracted from the three sustained Korean vowels /아/(a), /이/(i), and /우/(u) exhibit diversity and strong correlations. To address this issue, the analysis of variance F-Value feature selection classifier from scikit-learn was employed, to identify the topmost relevant features. Additionally, to overcome the class imbalance problem, the synthetic minority over-sampling technique was utilized. To ensure fair comparisons, and mitigate the influence of individual classifiers, four commonly used machine learning classifiers, namely random forest (RF), support vector machine (SVM), k-nearest neighbor (kNN), and multi-layer perceptron (MLP), were employed. This approach enables a comprehensive evaluation of the feature extraction methods, and minimizes the variance in the final classification models. The proposed hybrid machine learning pipeline using the acoustic features of sustained vowels efficiently detects the early and mid-advanced stages of PD with a detection accuracy of 95.48%, and with a detection accuracy of 86.62% for the 4-stage, and a detection accuracy of 89.48% for the 3-stage classification of PD. This study successfully demonstrates the significance of utilizing the diverse acoustic features of dysphonia in the classification of PD and its stages.

Classification of pathogenic bacteria by Raman spectroscopy combined with variational auto-encoder and deep learning

Rapid and early identification of pathogens is critical to guide antibiotic therapy. Raman spectroscopy as a noninvasive diagnostic technique provides rapid and accurate detection of pathogens. Raman spectrum of single cells serves as the "fingerprint" of the cell, revealing its metabolic characteristics. Rapid identification of pathogens can be achieved by combining Raman spectroscopy and deep learning. Traditional classification techniques frequently require lots of data for training, which is time costing to collect Raman spectra. For trace samples and strains that are difficult to culture, it is difficult to provide an accurate classification model. In order to reduce the number of samples collected and improve the accuracy of the classification model, a new pathogen detection method integrating Raman spectroscopy, variational auto-encoder (VAE), and long short-term memory network (LSTM) is proposed in this paper. We collect the Raman signals of pathogens and input them to VAE for training. VAE will generate a large number of Raman spectral data that cannot be distinguished from the real spectrum, and the signal-to-noise ratio is higher than that of the real spectrum. These spectra are input into the LSTM together with the real spectrum for training, and a good classification model is obtained. The results of the experiments reveal that this method not only improves the average accuracy of pathogen classification to 96.9% but also reduces the number of Raman spectra collected from 1000 to 200. With this technology, the number of Raman spectra collected can be greatly reduced, so that strains that are difficult to culture or trace can be rapidly identified.

Deletion of Tfam in Prx1-Cre expressing limb mesenchyme results in spontaneous bone fractures

INTRODUCTION

Osteoblasts require substantial amounts of energy to synthesize the bone matrix and coordinate skeleton mineralization. This study analyzed the effects of mitochondrial dysfunction on bone formation, nano-organization of collagen and apatite, and the resultant mechanical function in mouse limbs.

MATERIALS AND METHODS

Limb mesenchyme-specific Tfam knockout (Tfam^f/f;Prx1-Cre: Tfam-cKO) mice were analyzed morphologically and histologically, and gene expressions in the limb bones were assessed by in situ hybridization, qPCR, and RNA sequencing (RNA-seq). Moreover, we analyzed the mitochondrial function of osteoblasts in Tfam-cKO mice using mitochondrial membrane potential assay and transmission electron microscopy (TEM). We investigated the pathogenesis of spontaneous bone fractures using immunohistochemical analysis, TEM, birefringence analyzer, microbeam X-ray diffractometer and nanoindentation.

RESULTS

Forelimbs in Tfam-cKO mice were significantly shortened from birth, and spontaneous fractures occurred after birth, resulting in severe limb deformities. Histological and RNA-seq analyses showed that bone hypoplasia with a decrease in matrix mineralization was apparent, and the expression of type I collagen and osteocalcin was decreased in osteoblasts of Tfam-cKO mice, although Runx2 expression was unchanged. Decreased type I collagen deposition and mineralization in the matrix of limb bones in Tfam-cKO mice were associated with marked mitochondrial dysfunction. Tfam-cKO mice bone showed a significantly lower Young's modulus and hardness due to poor apatite orientation which is resulted from decreased osteocalcin expression.

CONCLUSION

Mice with limb mesenchyme-specific Tfam deletions exhibited spontaneous limb bone fractures, resulting in severe limb deformities. Bone fragility was caused by poor apatite orientation owing to impaired osteoblast differentiation and maturation.

Convolutional Neural Network-Based Parkinson Disease Classification Using SPECT Imaging Data

In this paper, we used the single-photon emission computerized tomography (SPECT) imaging technique to visualize the deficiency of dopamine-generated patterns inside the brain. These patterns are used to establish a patient’s disease progression, which helps distinguish the patients into different categories. Furthermore, we used a convolutional neural network (CNN) model to classify the patients based on the dopamine level inside the brain. The dataset used throughout this paper is the Parkinson’s progressive markers initiative (PPMI) dataset. The collected dataset was pre-processed and data amplification was performed to balance the imbalanced dataset. A CNN-based neural network was defined to classify input SPECT images into four categories. The motivation behind the proposed model is to reduce the number of resources consumed while maintaining the performance of the classification model. This will help the healthcare ecosystem run the classification model on mobile devices. The proposed model contains 14 layers with input layers, convolutional layers, max-pool layers, flatten layers, and dense layers with different dimensions. The dense layer classifies the patients into four different categories, including PSD, healthy control, scans without evidence of dopaminergic deficit (SWEDD), and GenReg PSD from the entire SPECT imaging dataset, which is used to establish the disease progression of different patients using SPECT images. The proposed model is trained with a large dataset with 58,692 images for training and 11,738 images for validation, and 7826 for testing. The proposed model outperforms the classification models from the surveyed papers. The proposed model’s accuracy is 0.889, recall is 0.9012, the precision is 0.9104, and the F1-score is 0.9057.

Low-Parameter Small Convolutional Neural Network Applied to Functional Medical Imaging of Tc-99m Trodat-1 Brain Single-Photon Emission Computed Tomography for Parkinson's Disease

Parkinson’s disease (PD), a progressive disease that affects movement, is related to dopaminergic neuron degeneration. Tc-99m Trodat-1 brain (TRODAT) single-photon emission computed tomography (SPECT) aids the functional imaging of dopamine transporters and is used for dopaminergic neuron enumeration. Herein, we employed a convolutional neural network to facilitate PD diagnosis through TRODAT SPECT, which is simpler than models such as VGG16 and ResNet50. We retrospectively collected the data of 3188 patients (age range 20–107 years) who underwent TRODAT SPECT between June 2011 and December 2019. We developed a set of functional imaging multiclassification deep learning algorithms suitable for TRODAT SPECT on the basis of the annotations of medical experts. We then applied our self-proposed model and compared its results with those of four other models, including deep and machine learning models. TRODAT SPECT included three images collected from each patient: one presenting the maximum absorption of the metabolic function of the striatum and two adjacent images. An expert physician determined that our model’s accuracy, precision, recall, and F1-score were 0.98, 0.98, 0.98, and 0.98, respectively. Our TRODAT SPECT model provides an objective, more standardized classification correlating to the severity of PD-related diseases, thereby facilitating clinical diagnosis and preventing observer bias.

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.

Applications of artificial intelligence in nuclear medicine image generation

Recently, the application of artificial intelligence (AI) in medical imaging (including nuclear medicine imaging) has rapidly developed. Most AI applications in nuclear medicine imaging have focused on the diagnosis, treatment monitoring, and correlation analyses with pathology or specific gene mutation. It can also be used for image generation to shorten the time of image acquisition, reduce the dose of injected tracer, and enhance image quality. This work provides an overview of the application of AI in image generation for single-photon emission computed tomography (SPECT) and positron emission tomography (PET) either without or with anatomical information [CT or magnetic resonance imaging (MRI)]. This review focused on four aspects, including imaging physics, image reconstruction, image postprocessing, and internal dosimetry. AI application in generating attenuation map, estimating scatter events, boosting image quality, and predicting internal dose map is summarized and discussed.

Detection of Postural Control in Young and Elderly Adults Using Deep and Machine Learning Methods with Joint-Node Plots

Postural control decreases with aging. Thus, an efficient and accurate method of detecting postural control is needed. We enrolled 35 elderly adults (aged 82.06 ± 8.74 years) and 20 healthy young adults (aged 21.60 ± 0.60 years) who performed standing tasks for 40 s, performed six times. The coordinates of 15 joint nodes were captured using a Kinect device (30 Hz). We plotted joint positions into a single 2D figure (named a joint–node plot, JNP) once per second for up to 40 s. A total of 15 methods combining deep and machine learning for postural control classification were investigated. The accuracy, sensitivity, specificity, positive predicted value (PPV), negative predicted value (NPV), and kappa values of the selected methods were assessed. The highest PPV, NPV, accuracy, sensitivity, specificity, and kappa values were higher than 0.9 in validation testing. The presented method using JNPs demonstrated strong performance in detecting the postural control ability of young and elderly adults.