Diagnosis Of Neurodegenerative Disorders Research Articles

Targeted Treatment Strategies for Mitochondria Dysfunction: Correlation with Neurological Disorders.

Mitochondria are an essential intracellular organelle for medication targeting and delivery since they seem to create energy and conduct many other cellular tasks, and mitochondrial dysfunctions and malfunctions lead to many illnesses. Many initiatives have been taken to detect, diagnose, and image mitochondrial abnormalities, and to transport and accumulate medicines precisely to mitochondria, all because of special mitochondrial aspects of the pathophysiology of cancer. In addition to the negative membrane potential and paradoxical mitochondrial dynamics, they include high temperatures, high levels of reactive oxygen species, high levels of glutathione, and high temperatures. Neurodegenerative diseases represent a broad spectrum of debilitating illnesses. They are linked to the loss of certain groups of neurons based on an individual's physiology or anatomy. The mitochondria in a cell are generally accepted as the authority with respect to ATP production. Disruption of this system is linked to several cellular physiological issues. The development of neurodegenerative disorders has been linked to mitochondrial malfunction, according to pathophysiological studies. There seems to be substantial evidence connecting mitochondrial dysfunction and oxidative stress to the development of neurodegenerative disorders. It has been extensively observed that mitochondrial malfunction triggers autophagy, which plays a role in neurodegenerative disorders. In addition, excitotoxicity and mitochondrial dysfunction have been linked to the development of neurodegenerative disorders. The pathophysiology of neurodegenerative illnesses has been linked to increased apoptosis and necrosis, as well as mitochondrial malfunction. A variety of synthetic and natural treatments have shown efficacy in treating neurodegenerative illnesses caused by mitochondrial failure. Neurodegenerative illnesses can be effectively treated with existing drugs that target mitochondria, although their precise formulations are poorly understood. Therefore, there is an immediate need to focus on creating drug delivery methods specifically targeted at mitochondria in the treatment and diagnosis of neurodegenerative disorders.

Head-to-Head Comparison of Tau and Amyloid Positron Emission Tomography Visual Reads for Differential Diagnosis of Neurodegenerative Disorders: An International, Multicenter Study.

We compared the accuracy of amyloid and [18F]Flortaucipir (FTP) tau positron emission tomography (PET) visual reads for distinguishing patients with mild cognitive impairment (MCI) or dementia with fluid biomarker support of Alzheimer's disease (AD). Participants with FTP-PET, amyloid-PET, and diagnosis of dementia-AD (n = 102), MCI-AD (n = 41), non-AD diseases (n = 76), and controls (n = 20) were included. AD status was determined independent of PET by cerebrospinal fluid or plasma biomarkers. The mean age was 66.9 years, and 44.8% were women. Three readers interpreted scans blindly and independently. Amyloid-PET was classified as positive/negative using tracer-specific criteria. FTP-PET was classified as positive with medial temporal lobe (MTL) binding as the minimum uptake indicating AD tau (tau-MTL+), positive with posterolateral temporal or extratemporal cortical binding in an AD-like pattern (tau-CTX+), or negative. The majority of scan interpretations were used to calculate diagnostic accuracy of visual reads in detecting MCI/dementia with fluid biomarker support for AD (MCI/dementia-AD). Sensitivity of amyloid-PET for MCI/dementia-AD was 95.8% (95% confidence interval 91.1-98.4%), which was comparable to tau-CTX+ 92.3% (86.7-96.1%, p = 0.67) and tau-MTL+ 97.2% (93.0-99.2%, p = 0.27). Specificity of amyloid-PET for biomarker-negative healthy and disease controls was 84.4% (75.5-91.0%), which was like tau-CTX+ 88.5% (80.4-94.1%, p = 0.34), and trended toward being higher than tau-MTL+ 75.0% (65.1-83.3%, p = 0.08). Tau-CTX+ had higher specificity than tau-MTL+ (p = 0.0002), but sensitivity was lower (p = 0.02), driven by decreased sensitivity for MCI-AD (80.5% [65.1-91.2] vs. 95.1% [83.5-99.4], p = 0.03). Amyloid- and tau-PET visual reads have similar sensitivity/specificity for detecting AD in cognitively impaired patients. Visual tau-PET interpretations requiring cortical binding outside MTL increase specificity, but lower sensitivity for MCI-AD. ANN NEUROL 2024.

Neuropsychological Assessment for Early Detection and Diagnosis of Dementia: Current Knowledge and New Insights.

Dementia remains an underdiagnosed syndrome, and there is a need to improve the early detection of cognitive decline. This narrative review examines the role of neuropsychological assessment in the characterization of cognitive changes associated with dementia syndrome at different states. The first section describes the early indicators of cognitive decline and the major barriers to their identification. Further, the optimal cognitive screening conditions and the most widely accepted tests are described. The second section analyzes the main differences in cognitive performance between Alzheimer's disease and other subtypes of dementia. Finally, the current challenges of neuropsychological assessment in aging/dementia and future approaches are discussed. Essentially, we find that current research is beginning to uncover early cognitive changes that precede dementia, while continuing to improve and refine the differential diagnosis of neurodegenerative disorders that cause dementia. However, neuropsychology faces several barriers, including the cultural diversity of the populations, a limited implementation in public health systems, and the adaptation to technological advances. Nowadays, neuropsychological assessment plays a fundamental role in characterizing cognitive decline in the different stages of dementia, but more efforts are needed to develop harmonized procedures that facilitate its use in different clinical contexts and research protocols.

Artificial intelligence in diagnosis of neurodegenerative disorders (literature review)

Currently, there are virtually no objective diagnostic signs (markers) to diagnose neurodegenerative diseases, that is why it may take months of constant monitoring of symptoms to establish a reliable diagnosis. Now there is an increasing number of reports that artificial intelligence can provide a more accurate diagnosis of neurodegenerative diseases by identifying specific diagnostic features from electroencephalography data, neuroimaging, and wearable devices and smartphones. This study reviews the application of artificial intelligence to the diagnosis of neurodegenerative diseases such as Alzheimer's disease, Parkinson's disease, and Huntington's disease. Using the international databases Scopus and PubMed, as well as the Russian Science Citation Index, we analysed studies that used artificial intelligence methods to detect, monitor, or control the progression of neurodegenerative diseases. The primary focus is on analysing electroencephalography data, neuroimaging data, and data from wearable devices and smartphones. The use of the latter may allow screening, diagnosis, and monitoring of the disease at home with a minimum economic cost. Artificial intelligence can be a useful tool for early, accurate, and non-invasive diagnosis of neurodegenerative diseases, as well as for assessing the effectiveness of treatment and predicting the course of the disease. However, for the widespread implementation of artificial intelligence in clinical practice, several issues related to the quality, availability, and standardization of data, validation and interpretation of results, ethical and legal aspects need to be resolved. The use of artificial intelligence requires both specialists from the IT industry with a deep understanding of the types and kinds of neural networks and physicians with fundamental knowledge of neurology, psychiatry, molecular biology, and biophysics.

Multi input–Multi output 3D CNN for dementia severity assessment with incomplete multimodal data

Alzheimer’s Disease is the most common cause of dementia, whose progression spans in different stages, from very mild cognitive impairment to mild and severe conditions. In clinical trials, Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) are mostly used for the early diagnosis of neurodegenerative disorders since they provide volumetric and metabolic function information of the brain, respectively. In recent years, Deep Learning (DL) has been employed in medical imaging with promising results. Moreover, the use of the deep neural networks, especially Convolutional Neural Networks (CNNs), has also enabled the development of DL-based solutions in domains characterized by the need of leveraging information coming from multiple data sources, raising the Multimodal Deep Learning (MDL). In this paper, we conduct a systematic analysis of MDL approaches for dementia severity assessment exploiting MRI and PET scans. We propose a Multi Input–Multi Output 3D CNN whose training iterations change according to the characteristic of the input as it is able to handle incomplete acquisitions, in which one image modality is missed. Experiments performed on OASIS-3 dataset show the satisfactory results of the implemented network, which outperforms approaches exploiting both single image modality and different MDL fusion techniques.

Characterisation of a novel [18F]FDG brain PET database and combination with a second database for optimising detection of focal abnormalities, using focal cortical dysplasia as an example

BackgroundBrain [18F]FDG PET is used clinically mainly in the presurgical evaluation for epilepsy surgery and in the differential diagnosis of neurodegenerative disorders. While scans are usually interpreted visually on an individual basis, comparison against normative cohorts allows statistical assessment of abnormalities and potentially higher sensitivity for detecting abnormalities. Little work has been done on out-of-sample databases (acquired differently to the patient data). Combination of different databases would potentially allow better power and discrimination. We fully characterised an unpublished healthy control brain [18F]FDG PET database (Marseille, n = 60, ages 21–78 years) and compared it to another publicly available database (MRXFDG, n = 37, ages 23–65 years). We measured and then harmonised spatial resolution and global values. A collection of patient scans (n = 34, 13–48 years) with histologically confirmed focal cortical dysplasias (FCDs) obtained on three generations of scanners was used to estimate abnormality detection rates using standard software (statistical parametric mapping, SPM12).ResultsRegional SUVs showed similar patterns, but global values and resolutions were different as expected. Detection rates for the FCDs were 50% for comparison with the Marseille database and 53% for MRXFDG. Simply combining both databases worsened the detection rate to 41%. After harmonisation of spatial resolution, using a full factorial design matrix to accommodate global differences, and leaving out controls older than 60 years, we achieved detection rates of up to 71% for both databases combined. Detection rates were similar across the three scanner types used for patients, and high for patients whose MRI had been normal (n = 10/11).ConclusionsAs expected, global and regional data characteristics are database specific. However, our work shows the value of increasing database size and suggests ways in which database differences can be overcome. This may inform analysis via traditional statistics or machine learning, and clinical implementation.

Pixel Perfect – Imaging Technologies in Biomedical Research (Vol. 27, Nos. 03n04, Full Issue)

In this issue, we have two highlights that will look at how far imaging technologies have come since the X-ray. First, Keefe Chee from BD Life Sciences, Singapore, discusses how real-time imaging spectral flow cytometry (RTI-SFC) allows scientists to identify previously unclassifiable cells in real time, bridging a long-standing gap in biomedical research. And then we have Torrey Smith, CEO of Endiatx, to share with us about PillBot™, the world's first motorised pill camera that will allow a doctor to view the entire stomach and assess for any lesions, making stomach cancer diagnosis more accessible and palatable. Finally, some research highlights we have this issue include a novel diagnostic tool that will improve the clinical diagnosis of neurodegenerative disorders, a textile that can convert body movement into electricity, and a uterine tissue-specific hydrogel that could aid in infertility.

Sensor-Based Locomotion Data Mining for Supporting the Diagnosis of Neurodegenerative Disorders: A Survey

Locomotion characteristics and movement patterns are reliable indicators of neurodegenerative diseases (NDDs). This survey provides a systematic literature review of locomotion data mining systems for supporting NDD diagnosis. We discuss techniques for discovering low-level locomotion indicators, sensor data acquisition and processing methods, and NDD detection algorithms. The survey presents a comprehensive discussion on the main challenges for this active area, including the addressed diseases, locomotion data types, duration of monitoring, employed algorithms, and experimental validation strategies. We also identify prominent open challenges and research directions regarding ethics and privacy issues, technological and usability aspects, and availability of public benchmarks.

Artificial intelligence-coupled plasmonic infrared sensor for detection of structural protein biomarkers in neurodegenerative diseases.

Diagnosis of neurodegenerative disorders (NDDs) including Parkinson's disease and Alzheimer's disease is challenging owing to the lack of tools to detect preclinical biomarkers. The misfolding of proteins into oligomeric and fibrillar aggregates plays an important role in the development and progression of NDDs, thus underscoring the need for structural biomarker-based diagnostics. We developed an immunoassay-coupled nanoplasmonic infrared metasurface sensor that detects proteins linked to NDDs, such as alpha-synuclein, with specificity and differentiates the distinct structural species using their unique absorption signatures. We augmented the sensor with an artificial neural network enabling unprecedented quantitative prediction of oligomeric and fibrillar protein aggregates in their mixture. The microfluidic integrated sensor can retrieve time-resolved absorbance fingerprints in the presence of a complex biomatrix and is capable of multiplexing for the simultaneous monitoring of multiple pathology-associated biomarkers. Thus, our sensor is a promising candidate for the clinical diagnosis of NDDs, disease monitoring, and evaluation of novel therapies.

The genetic counselor: recognizing their critical role in neurology clinics in the era of genomic medicine (P12-4.001)

<h3>Objective:</h3> To describe the critical role of the clinical genetic counselor in the neurology setting and their impact on patient care. <h3>Background:</h3> Genetic testing is increasingly utilized in the diagnosis of neurodegenerative disorders. This is particularly relevant as the field moves towards neurogenetic intervention. Determining who should be genetically tested, which tests should be performed, which labs are most appropriate and how to secure insurance coverage for patients with neurological conditions remains a challenge. Reviewing the complexity of testing options and potential impact of the results on patients and family members is also time-consuming and can be a barrier to care when physicians are required to fill this role unassisted by clinical professionals with targeted genetic expertise. Genetic counselors are healthcare professionals with specialized training in medical genetics and psychosocial counseling who can solve this challenge in clinical care. <h3>Design/Methods:</h3> Here we describe the role and impact of genetic counselor in the Massachusetts General Hospital Ataxia Center as a case in point. <h3>Results:</h3> The genetic counselor’s primarily roles are in pretest and posttest counseling. Pretest counseling includes comprehensive genetic evaluations and determining appropriate genetic testing pathways for individuals with suspected hereditary ataxic disorders. They review test benefits, limitations, and risks, impacts on patients and family members, and facilitate prior authorizations for insurance approval and test orders. Posttest counseling involves disclosure of sensitive results in the context of the patient’s medical and family history, and incudes psychosocial support. Follow up includes connecting patients to resources and support groups, arranging family segregation studies in case of uncertain results, and cascade testing for at risk relatives. <h3>Conclusions:</h3> The genetic counselor’s knowledge and counseling skills help improve patient care, optimize physician time, focus the testing strategy, and reduce costs. Genetic counselors are integral members of the multidisciplinary neurology team in the era of genomic medicine. <b>Disclosure:</b> Ms. Chen has nothing to disclose. Dr. Schmahmann has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Medavante. Dr. Schmahmann has stock in Cadent. The institution of Dr. Schmahmann has received research support from National Ataxia Foundation. The institution of Dr. Schmahmann has received research support from Biohaven. Dr. Schmahmann has received intellectual property interests from a discovery or technology relating to health care. Dr. Schmahmann has received publishing royalties from a publication relating to health care. Dr. Schmahmann has received publishing royalties from a publication relating to health care. Dr. Schmahmann has received publishing royalties from a publication relating to health care.

Review of Technological Challenges in Personalised Medicine and Early Diagnosis of Neurodegenerative Disorders.

Neurodegenerative disorders are characterised by progressive neuron loss in specific brain areas. The most common are Alzheimer's disease and Parkinson's disease; in both cases, diagnosis is based on clinical tests with limited capability to discriminate between similar neurodegenerative disorders and detect the early stages of the disease. It is common that by the time a patient is diagnosed with the disease, the level of neurodegeneration is already severe. Thus, it is critical to find new diagnostic methods that allow earlier and more accurate disease detection. This study reviews the methods available for the clinical diagnosis of neurodegenerative diseases and potentially interesting new technologies. Neuroimaging techniques are the most widely used in clinical practice, and new techniques such as magnetic resonance imaging (MRI) and positron emission tomography (PET) have significantly improved the diagnosis quality. Identifying biomarkers in peripheral samples such as blood or cerebrospinal fluid is a major focus of the current research on neurodegenerative diseases. The discovery of good markers could allow preventive screening to identify early or asymptomatic stages of the neurodegenerative process. These methods, in combination with artificial intelligence, could contribute to the generation of predictive models that will help clinicians in the early diagnosis, stratification, and prognostic assessment of patients, leading to improvements in patient treatment and quality of life.

Focused Ultrasound-mediated Liquid Biopsy in a Tauopathy Mouse Model.

Background Neurodegenerative disorders (such as Alzheimer disease) characterized by the deposition of various pathogenic forms of tau protein in the brain are collectively referred to as tauopathies. Identification of the molecular drivers and pathways of neurodegeneration is critical to individualized targeted treatment of these disorders. However, despite important advances in fluid biomarker detection, characterization of these molecular subtypes is limited by the blood-brain barrier. Purpose To evaluate the feasibility and safety of focused ultrasound-mediated liquid biopsy (sonobiopsy) in the detection of brain-derived protein biomarkers in a transgenic mouse model of tauopathy (PS19 mice). Materials and Methods Sonobiopsy was performed by sonicating the cerebral hemisphere in 2-month-old PS19 and wild-type mice, followed by measurement of plasma phosphorylated tau (p-tau) species (30 minutes after sonication in the sonobiopsy group). Next, spatially targeted sonobiopsy was performed by sonicating either the cerebral cortex or the hippocampus in 6-month-old PS19 mice. To detect changes in plasma neurofilament light chain (a biomarker of neurodegeneration) levels, blood samples were collected before and after sonication (15 and 45-60 minutes after sonication). Histologic staining was performed to evaluate tissue damage after sonobiopsy. The Shapiro-Wilk test, unpaired and paired t tests, and the Mann-Whitney U test were used. Results In the 2-month-old mice, sonobiopsy significantly increased the normalized levels of plasma p-tau species compared with the conventional blood-based liquid biopsy (p-tau-181-to-mouse tau [m-tau] ratio: 1.7-fold increase, P = .006; p-tau-231-to-m-tau ratio: 1.4-fold increase, P = .048). In the 6-month-old PS19 mice, spatially targeted sonobiopsy resulted in a 2.3-fold increase in plasma neurofilament light chain after sonication of the hippocampus and cerebral cortex (P < .001). After optimization of the sonobiopsy parameters, no excess microhemorrhage was observed in the treated cerebral hemisphere compared with the contralateral side. Conclusion This study showed the feasibility of sonobiopsy to release phosphorylated tau species and neurofilament light chain to the blood circulation, potentially facilitating diagnosis of neurodegenerative disorders. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Fowlkes in this issue.

The neurology ‐ psychiatry interface: variations on a diagnostic theme

Despite the panoply of clinical assessment and neuroimaging modalities at the disposal of clinicians today, the diagnosis of neurodegenerative disorders may still prove challenging, particularly in the early stages, because of the subtlety of early changes and/or their overlap with (so‐called) psychiatric disorders. A case illustrating these difficulties is presented, in which long‐term follow‐up proved to be the most important investigation to establish the correct diagnosis.

Adopting transfer learning for neuroimaging: a comparative analysis with a custom 3D convolution neural network model

BackgroundIn recent years, neuroimaging with deep learning (DL) algorithms have made remarkable advances in the diagnosis of neurodegenerative disorders. However, applying DL in different medical domains is usually challenged by lack of labeled data. To address this challenge, transfer learning (TL) has been applied to use state-of-the-art convolution neural networks pre-trained on natural images. Yet, there are differences in characteristics between medical and natural images, also image classification and targeted medical diagnosis tasks. The purpose of this study is to investigate the performance of specialized and TL in the classification of neurodegenerative disorders using 3D volumes of 18F-FDG-PET brain scans.ResultsResults show that TL models are suboptimal for classification of neurodegenerative disorders, especially when the objective is to separate more than two disorders. Additionally, specialized CNN model provides better interpretations of predicted diagnosis.ConclusionsTL can indeed lead to superior performance on binary classification in timely and data efficient manner, yet for detecting more than a single disorder, TL models do not perform well. Additionally, custom 3D model performs comparably to TL models for binary classification, and interestingly perform better for diagnosis of multiple disorders. The results confirm the superiority of the custom 3D-CNN in providing better explainable model compared to TL adopted ones.

Biomarkers of Inflammation Increase with Tau and Neurodegeneration but not with Amyloid-β in a Heterogenous Clinical Cohort.

Neuroinflammation is an integral part of Alzheimer's disease (AD) pathology. Inflammatory mediators can exacerbate the production of amyloid-β (Aβ), the propagation of tau pathology and neuronal loss. To evaluate the relationship between inflammation markers and established markers of AD in a mixed memory clinic cohort. 105 cerebrospinal fluid (CSF) samples from a clinical cohort under investigation for cognitive complaints were analyzed. Levels of Aβ42, total tau, and phosphorylated tau were measured as part of the clinical pathway. Analysis of inflammation markers in CSF samples was performed using multiplex immune assays. Participants were grouped according to their Aβ, tau, and neurodegeneration status and the Paris-Lille-Montpellier (PLM) scale was used to assess the likelihood of AD. From 102 inflammatory markers analyzed, 19 and 23 markers were significantly associated with CSF total tau and phosphorylated tau levels respectively (p &lt; 0.001), while none were associated with Aβ42. The CSF concentrations of 4 inflammation markers were markedly elevated with increasing PLM class indicating increased likelihood of AD (p &lt; 0.001). Adenosine deaminase, an enzyme involved in sleep homeostasis, was the single best predictor of high likelihood of AD (AUROC 0.788). Functional pathway analysis demonstrated a widespread role for inflammation in neurodegeneration, with certain pathways explaining over 30% of the variability in tau values. CSF inflammation markers increase significantly with tau and neurodegeneration, but not with Aβ in this mixed memory clinic cohort. Thus, such markers could become useful for the clinical diagnosis of neurodegenerative disorders alongside the established Aβ and tau measures.

Human-Guided Functional Connectivity Network Estimation for Chronic Tinnitus Identification: A Modularity View.

The functional connectivity network (FCN) has been used to achieve several remarkable advancements in the diagnosis of neuro-degenerative disorders. Therefore, it is imperative to accurately estimate biologically meaningful FCNs. Several efforts have been dedicated to this purpose by encoding biological priors. However, owing to the high complexity of the human brain, the estimation of an 'ideal' FCN remains an open problem. To the best of our knowledge, almost all existing studies lack the integration of domain expert knowledge, which limits their performance. In this study, we focused on incorporating domain expert knowledge into the FCN estimation from a modularity perspective. To achieve this, we presented a human-guided modular representation (MR) FCN estimation framework. Specifically, we designed an adversarial low-rank constraint to describe the module structure of FCNs under the guidance of domain expert knowledge (i.e., a predefined participant index). The chronic tinnitus (TIN) identification task based on the estimated FCNs was conducted to examine the proposed MR methods. Remarkably, MR significantly outperformed the baseline and state-of-the-art(SOTA) methods, achieving an accuracy of 92.11%. Moreover, post-hoc analysis revealed that the FCNs estimated by the proposed MR could highlight more biologically meaningful connections, which is beneficial for exploring the underlying mechanisms of TIN and diagnosing early TIN.

The affective, behavioural, and cognitive reactions to a diagnosis of Primary Progressive Aphasia: A qualitative descriptive study.

Receiving a diagnosis of neurodegenerative disorder is life changing. Primary progressive aphasia is one such disease. Understanding how receiving this diagnosis impacts on individuals may help plan support services. However, limited qualitative research from the perspectives of people with Primary Progressive Aphasia are available for suitable care planning. Current literature primarily focuses on experiences of family members. The present study aims to fill this gap by examining the affective, behavioural, and cognitive experiences of people with Primary Progressive Aphasia. Semi-structured interviews were conducted with six participants with PPA. A qualitative descriptive approach was used to describe responses from participants on: (i) what they experienced prior to receiving their diagnosis; (ii) their experience of receiving the diagnosis; and (iii) how they were living with their PPA. Verbatim transcripts were analysed using thematic analysis to identify main themes. Analysis revealed a superordinate theme of Multifaceted Grief with subthemes described in sequence of research questions posed, representing the three phases of Pre-Diagnosis, Time of Diagnosis, and Post-Diagnosis. Themes collectively revealed participants' ongoing experience of loss in dealing with the evolving challenges of Primary Progressive Aphasia. Experiences of loss emerged with descriptions of feelings, thoughts, and limitations in relation to changes imposed by the illness, impacting daily activities and life roles central to participants' pre-diagnosis sense of self. Participants' affective, behavioural and cognitive reactions to their Primary Progressive Aphasia diagnosis marks the onset of Multifaceted Grief borne of loss of communication and cognition. Participants expressed a need for information regarding a possible Primary Progressive Aphasia trajectory and support to enable a successful transition as their disease progressed. Collaborative engagement between speech pathologists and people with Primary Progressive Aphasia incorporates addressing all levels of the International Classification of Functioning and Health by considering neurological, psychological, and psychosocial experiences of the person with the diagnosis.

Stage-independent biomarkers for Alzheimer’s disease from the living retina: an animal study

The early diagnosis of neurodegenerative disorders is still an open issue despite the many efforts to address this problem. In particular, Alzheimer’s disease (AD) remains undiagnosed for over a decade before the first symptoms. Optical coherence tomography (OCT) is now common and widely available and has been used to image the retina of AD patients and healthy controls to search for biomarkers of neurodegeneration. However, early diagnosis tools would need to rely on images of patients in early AD stages, which are not available due to late diagnosis. To shed light on how to overcome this obstacle, we resort to 57 wild-type mice and 57 triple-transgenic mouse model of AD to train a network with mice aged 3, 4, and 8 months and classify mice at the ages of 1, 2, and 12 months. To this end, we computed fundus images from OCT data and trained a convolution neural network (CNN) to classify those into the wild-type or transgenic group. CNN performance accuracy ranged from 80 to 88% for mice out of the training group’s age, raising the possibility of diagnosing AD before the first symptoms through the non-invasive imaging of the retina.

Deep learning based low-activity PET reconstruction of [11C]PiB and [18F]FE-PE2I in neurodegenerative disorders

PurposePositron Emission Tomography (PET) can support a diagnosis of neurodegenerative disorder by identifying disease-specific pathologies. Our aim was to investigate the feasibility of using activity reduction in clinical [18F]FE-PE2I and [11C]PiB PET/CT scans, simulating low injected activity or scanning time reduction, in combination with AI-assisted denoising. MethodsA total of 162 patients with clinically uncertain Alzheimer's disease underwent amyloid [11C]PiB PET/CT and 509 patients referred for clinically uncertain Parkinson's disease underwent dopamine transporter (DAT) [18F]FE-PE2I PET/CT. Simulated low-activity data were obtained by random sampling of 5% of the events from the list-mode file and a 5% time window extraction in the middle of the scan. A three-dimensional convolutional neural network (CNN) was trained to denoise the resulting PET images for each disease cohort. ResultsNoise reduction of low-activity PET images was successful for both cohorts using 5% of the original activity with improvement in visual quality and all similarity metrics with respect to the ground-truth images. Clinically relevant metrics extracted from the low-activity images deviated < 2% compared to ground-truth values, which were not significantly changed when extracting the metrics from the denoised images. ConclusionThe presented models were based on the same network architecture and proved to be a robust tool for denoising brain PET images with two widely different tracer distributions (delocalized, ([11C]PiB, and highly localized, [18F]FE-PE2I). This broad and robust application makes the presented network a good choice for improving the quality of brain images to the level of the standard-activity images without degrading clinical metric extraction. This will allow for reduced dose or scan time in PET/CT to be implemented clinically.

Application research and development of objective examination of olfactory function

The sense of smell is one of the five most primitive human sensory functions, and it plays a very important role in our daily lives. Despite numerous methods for evaluating olfactory function, there is still a lack of standardization of olfactory tests and the results are often inconsistent. Furthermore, the related research on objective evaluation started relatively late. Along with the deciphering of the olfactory pathway, the technical level of olfactory objective inspection has been greatly improved and significant progress has also been made in terms of clinical application, such as: olfactory pathway MRI and fMRI imaging, OERPs, BEAM for various olfactory disorders and early diagnosis of neurodegenerative disorders, as well as related research based on bionic olfactory sensing technology. This article mainly introduces the recent research progress of several commonly used objective olfactory tests and provides reference for more accurate evaluation of olfactory function.