Neurodegenerative Disorder Disease Prediction Using RCNN Classification and Spiral Image

Right now, breast cancer is considered as a most important health problem among women over the world. The detection of breast cancer in the beginning stage can reduce the mortality rate to a considerable extent. Mammogram is an effective and regularly used technique for the detection and screening of breast cancer. The advanced deep learning (DL) techniques are utilized by radiologists for accurate finding and classification of medical images. This paper develops a new deep segmentation with residual network (DS-RN) based breast cancer diagnosis model using mammogram images. The presented DS-RN model involves preprocessing, Faster Region based Convolution Neural Network (R-CNN) (Faster R-CNN) with Inception v2 model based segmentation, feature extraction and classification. To classify the mammogram images, decision tree (DT) classifier model is used. A detailed simulation process is performed to ensure the betterment of the presented model on the Mini-MIAS dataset. The obtained experimental values stated that the DS-RN model has reached to a maximum classification performance with the maximum sensitivity, specificity, accuracy and F-Measure of 98.15%, 100%, 98.86% and 99.07% respectively.

Due to the complexity of medical images, traditional medical image classification methods have been unable to meet the actual application needs. In recent years, the rapid development of deep learning theory has provided a technical approach for solving medical image classification. However, deep learning has the following problems in the application of medical image classification. First, it is impossible to construct a deep learning model with excellent performance according to the characteristics of medical images. Second, the current deep learning network structure and training strategies are less adaptable to medical images. Therefore, this paper first introduces the visual attention mechanism into the deep learning model so that the information can be extracted more effectively according to the problem of medical images, and the reasoning is realized at a finer granularity. It can increase the interpretability of the model. Additionally, to solve the problem of matching the deep learning network structure and training strategy to medical images, this paper will construct a novel multiscale convolutional neural network model that can automatically extract high-level discriminative appearance features from the original image, and the loss function uses the Mahalanobis distance optimization model to obtain a better training strategy, which can improve the robust performance of the network model. The medical image classification task is completed by the above method. Based on the above ideas, this paper proposes a medical classification algorithm based on a visual attention mechanism-multiscale convolutional neural network. The lung nodules and breast cancer images were classified by the method in this paper. The experimental results show that the accuracy of medical image classification in this paper is not only higher than that of traditional machine learning methods but also improved compared with other deep learning methods, and the method has good stability and robustness.

CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) systems serve as a crucial defense mechanism against automated attacks by distinguishing between human users and bots. However, advancements in deep learning have posed significant challenges to the security of conventional CAPTCHA systems. In this research paper, we present a comparative analysis of two prominent object detection algorithms, Convolutional Neural Networks (CNN) and Region-based Convolutional Neural Networks (RCNN), for breaking CAPTCHAs. The study evaluates the performance of CNN and RCNN algorithms in accurately identifying and deciphering characters within CAPTCHA images. Utilizing a diverse dataset of CAPTCHA samples, experiments are conducted to assess the effectiveness of both algorithms in handling variations in CAPTCHA styles, languages, and complexities. Through extensive experimentation and evaluation, we analyze the strengths and limitations of CNN and RCNN in the context of CAPTCHA breaking. Key metrics such as accuracy, precision, recall, and computational efficiency are compared to provide insights into the relative performance of each algorithm. The findings of this research contribute to the understanding of object detection techniques for CAPTCHA breaking and provide valuable insights for enhancing the security of CAPTCHA systems against emerging threats posed by deep learning-based attacks.

Salivary levels of disease-related biomarkers in the early stages of Parkinson’s and Alzheimer’s disease: A cross-sectional study

Quantifying drug-induced dyskinesias in the arms using digitised spiral-drawing tasks

Due to the complexity of medical images, traditional medical image classification methods have been unable to meet actual application needs. In recent years, the rapid development of deep learning theory has provided a technical approach for solving medical image classification tasks. However, deep learning has the following problems in medical image classification. First, it is impossible to construct a deep learning model hierarchy for medical image properties; second, the network initialization weights of deep learning models are not well optimized. Therefore, this paper starts from the perspective of network optimization and improves the nonlinear modeling ability of the network through optimization methods. A new network weight initialization method is proposed, which alleviates the problem that existing deep learning model initialization is limited by the type of the nonlinear unit adopted and increases the potential of the neural network to handle different visual tasks. Moreover, through an in‐depth study of the multicolumn convolutional neural network framework, this paper finds that the number of features and the convolution kernel size at different levels of the convolutional neural network are different. In contrast, the proposed method can construct different convolutional neural network models that adapt better to the characteristics of the medical images of interest and thus can better train the resulting heterogeneous multicolumn convolutional neural networks. Finally, using the adaptive sliding window fusion mechanism proposed in this paper, both methods jointly complete the classification task of medical images. Based on the above ideas, this paper proposes a medical classification algorithm based on a weight initialization/sliding window fusion for multilevel convolutional neural networks. The methods proposed in this study were applied to breast mass, brain tumor tissue, and medical image database classification experiments. The results show that the proposed method not only achieves a higher average accuracy than that of traditional machine learning and other deep learning methods but also is more stable and more robust.

Inflammation-associated peripheral blood cells and serum lipid levels are associated with Parkinson's disease.

Parkinson and essential tremor classification to identify the patient’s risk based on tremor severity

Brain tumour detection is a critical medical procedure where early and accurate diagnosis significantly improves patient outcomes. This study explores the application of deep learning models, specifically VGG19 and InceptionV3, for detecting brain tumours in MRI images. We fine-tuned both models using transfer learning and evaluated them on a dataset of MRI scans. InceptionV3 achieved 100% validation accuracy, while VGG19 achieved 95%, demonstrating their high efficacy in medical image classification. In addition to deep learning, the study integrates insights from traditional image processing techniques, such as edge detection and probabilistic neural networks (PNNs), highlighting how combining deep learning with traditional methods can enhance image preprocessing and quality. The results underscore that while deep learning models are highly effective in brain tumour classification, traditional techniques still play a vital role in optimizing the overall detection process.

In his famous monograph “An Essay in Shaking Palsy,” James Parkinson provided astute descriptions of impaired sleep in his case series of patients with Parkinson's disease (PD) two centuries ago. It is only three decades ago that sleep dysfunction started to attract attention of medical and scientific communities involved in the clinical care and research of PD. Tremendous advancements in our understanding of impaired sleep and alertness associated with PD have developed since then. Sleep problems are one of the major, challenging issues in patients with PD, affecting a significant number of patients. The etiology of sleep problems is multifactorial, including disease-related nocturnal symptoms, medication adverse effects, and primary sleep disorders including restless legs syndrome, rapid eye movement sleep behavior disorder, and sleep apnea syndrome. These causes of impaired sleep-wake cycles in the PD population often coexist or even overlap, rendering the management of sleep problems in PD patients difficult. Also, excessive daytime sleepiness is observed in a significant number of patients. In PD patients, therefore, appropriate assessment of disease-related nocturnal disturbances and primary sleep disorders is imperative. This special issue addresses unmet need for understanding PD-related sleep problems. PD sleep scale 2 (PDSS-2) is a recently developed tool for screening and managing sleep disturbance in PD patients, consisting of 15 items which are clinically relevant to nocturnal problems including nonmotor and motor problems in PD [1]. The original PDSS-2 (German and English) has been translated into several languages, including Japanese [2] and Italian [3]. The PDSS-2 has been used to observe treatment response. In a double-blind, placebo-controlled trial, including 287 PD patients, mean PDSS-2 total score decreased by −5.9 points with rotigotine and by −1.9 points with placebo [4]. In this special issue, K. Horvath et al. estimated the threshold representing minimal clinically important difference of the PDSS-2 total score: the study results showed −3.44 points for detecting improvement or the threshold of 2.07 points for observing worsening. This finding is important when planning studies using the PDSS-2 as outcome measures. Full-night polysomnography (PSG) is a gold standard for diagnosing sleep apnea syndrome; however, applying PSG is often difficult in patients with PD, who have severe parkinsonism or psychiatric comorbidity. P. Gros et al. evaluated the usefulness of unattended portable monitoring (PM) for diagnosis of obstructive sleep apnea (OSA) in patients with PD. Although discrepancy between portable monitoring and PSG was greater in PD patients with more motor dysfunction, the authors confirmed the usefulness of portable monitoring in diagnosing moderate to severe OSA in PD patients. These results provide the rationale for the use of portable sleep monitoring in PD and are very relevant for circumstances where a complete PSG in a sleep laboratory is not available and/or feasible. M. Kaminska et al. performed a review on the relationship between OSA and PD. Although the clinical significance of OSA in PD has been controversial [5, 6], the authors suggest the possibility that treatment of OSA could delay cognitive decline or motor dysfunction in patients with PD. This area of research is of high significance as it is important to assess the prevalence of OSA and the impact of its treatment in the PD population. D. Martinez-Ramirez et al. correlated PSG findings and sleep disorders with clinical characteristics in PD patients and found that sleep disorders and sleep architecture were poorly predictable by clinical characteristic of PD patients. This comprehensive study demonstrates the complexity of sleep dysfunction associated with PD and its complex associations with metrics of PD. In a fine and thoughtful study K. Suzuki et al. provided an interesting insight into the complex relationship between PD and restless legs syndrome (RLS) and leg motor restlessness (LMR). A significant relationship between RLS and PD is suggested by observing a favorable response to dopaminergic treatment in both disorders. However, RLS prevalence in PD patients varies according to different studies. Recently, LMR, characterized by an urge to move the legs that does not fulfill the diagnostic criteria for RLS, has been reported more frequently in patients untreated with PD than healthy controls. This review article may provide a new insight into the relationship between RLS, LMR, and PD. Finally, the complex and still only partially understood interaction of impulse control disorders in PD and sleep is discussed in a review from the clinic of one of the guest editors. In summary, sleep problems are common but underreported by PD patients and underdiagnosed by health professionals. Further understanding of mechanisms that underlie impaired sleep and alertness in PD will allow for development of much needed treatment approaches for this nonmotor manifestation of PD. Koichi Hirata Birgit Hogl Eng King Tan Aleksandar Videnovic

The symptoms of most neurodegenerative diseases, including Parkinson's disease (PD), usually do not occur until substantial neuronal loss occurs. This makes the process of early diagnosis very challenging. Hence, this research used variant call format (VCF) analysis to detect variants and novel genes that could be used as prognostic indicators in the early diagnosis of prodromal PD. Data were obtained from the Parkinson's Progression Markers Initiative (PPMI), and we analyzed prodromal patients with gVCF data collected in the 2021 cohort. A total of 304 participants were included, including 100 healthy controls, 146 prodromal genetic individuals, 21 prodromal hyposmia individuals, and 37 prodromal individuals with RBD. A pipeline was developed to process the samples from gVCF to reach variant annotation and pathway and disease association analysis. Novel variant percentages were detected in the analyzed prodromal subgroups. The prodromal subgroup analysis revealed novel variations of 1.0%, 1.2%, 0.6%, 0.3%, 0.5%, and 0.4% for the genetic male, genetic female, hyposmia male, hyposmia female, RBD male, and RBD female groups, respectively. Interestingly, 12 potentially novel loci (MTF2, PIK3CA, ADD1, SYBU, IRS2, USP8, PIGL, FASN, MYLK2, USP25, EP300, and PPP6R2) that were recently detected in PD patients were detected in the prodromal stage of PD. Genetic biomarkers are crucial for the early detection of Parkinson's disease and its prodromal stage. The novel PD genes detected in prodromal patients could aid in the use of gene biomarkers for early diagnosis of the prodromal stage without relying only on phenotypic traits.

Parkinson's disease, ischemic stroke, dementia, and cranial computed tomography: Preliminary study

Melanoma lesion detection and segmentation using deep region based convolutional neural network and fuzzy C-means clustering

Parkinson's disease (PD) is a neurodegenerative pathology characterized by the degeneration of midbrain dopamine neurons, whose development and maintenance in brain is related to the transcription factor NR4A2 (also called Nurr1). Notably, NR4A2 is a neuroprotective agent with anti-inflammatory role in microglia and astrocytes. Furthermore, mutations in NR4A2 gene are associated to the familial form of PD, and its gene expression level is down-regulated in blood obtained from PD patients. NR4A2 belongs to the NR4A subfamily consisting of three members: NR4A1, NR4A2, and NR4A3. The NR4A subfamily shares high degree of homology in their molecular structure and cooperates in a spectrum of functions ranging from central nervous system to immune control during physiological and pathological conditions. Considering the close functional link between the member of NR4A subfamily, we performed a gene expression analysis of NR4A1, NR4A2, and NR4A3 in peripheral blood obtained from PD patients and healthy controls (HC). Then, in order to evaluate possible involvement of the NR4A subfamily in other neurodegenerative processes, we carried out the same analysis on blood obtained from Alzheimer's disease (AD) patients. A correlation between clinical features and gene expression was also evaluated. We found a marked down-regulated gene expression of the NR4A subfamily obtained from PD patients, but only a NR4A1 decrease in AD patients compared to HC. This study reports that the entire NR4A subfamily and not only NR4A2 could be systemically involved in PD suggesting that the study of these factors could be a promising approach to develop PD therapy.

Growing and clinical evidence supports the conclusion that Parkinson’s Disease (PD) is a complex multisystem disorder not exclusively affecting the dopaminergic circuits. In fact, the dopaminergic neuronal loss does not cover all the clinical aspects of PD. Therefore, different non-dopaminergic neurotransmitter systems have been invoked as playing a role in the PD clinical picture. Principally, the inefficiency of serotonergic circuitry has been demonstrated in PD animal models, as well as in post-mortem and in vivo human studies. In the recent article published in Brain, Zahi Qamhawi and colleagues interrogated 123I-FP-CIT single-photon emission computed tomography documenting raphe serotonergic dysfunction in a large group of early PD patients compared to a subset of possible PD patients without evidence of dopaminergic deficit (SWEDD) and a population of healthy controls (1). This paper combined an accurate clinical evaluation with a sophisticated neuroimaging protocol and documented in PD patients a mean raphe serotonin (5-HT) transporter availability significantly lower than both SWEDD patients and controls. These findings, achieved in a large cohort of PD patients, enforced previous autoptic examinations documenting serotonergic neurons loss due to Lewy body pathology in the raphe nuclei of PD patients (2). Accordingly, neuroimaging studies have shown the progressive 5-HT transporter availability reduction in the raphe nuclei as PD pathology progresses (3–5). It is well accepted that concentration of 5-HT and its metabolite 5-hydroxyindolacetic acid (5-HIAA) in CSF reflects the serotonergic metabolism and turnover in the CNS (6, 7). We performed a case-control study investigating CSF levels of 5-HT and 5-HIAA in a cohort of PD patients, after a 3-day dopaminergic therapy withdrawal and in absence of serotonergic agents (8). We demonstrated the significant reduction of CSF 5-HT and 5-HIAA concentrations in PD patients compared to controls. We also found the significant reduction of CSF 5-HT and 5-HIAA in the PD population with respect to Alzheimer’s Disease patients (8), thus highlighting that the impairment of serotonergic system could represent a specific effect of synuclein-mediated neurodegeneration (8). As a matter of fact, novel experimental studies in alpha-synuclein (α-syn) mouse model of PD showed the impairment of serotonergic system owing to the intracellular accumulation of α-syn in serotonergic neurons coupled with the reduction of 5-HT levels in lower brainstem (9). Based on the clinical presentation, Qamhawi and collegues divided PD patients into two subgroups corresponding to patients with and without resting tremor. Remarkably, patients with tremor had lower mean raphe 5-HT transporter availability than patients unaffected by tremor. Since tremor amplitude, constancy, and severity negatively correlated with raphe 5-HT transporter availability in the whole PD cohort, authors suggested that the serotonergic system inefficiency could be responsible for parkinsonian tremor. This finding was consistent with previous studies detecting an association between 5-HT receptor availability in the raphe nuclei and severity of parkinsonian tremor (10). However, in our CSF study, we found no differences in CSF 5-HT and 5-HIAA levels between tremor dominant and non-tremor dominant patients. This discrepancy could be ascribed to the fact that Qamhawi and collegues studied de novo early PD patients, whereas we investigated patients with higher Hoehn and Yahr stage and greater motor disability at the Unified PD Rating Scale-motor section. It could be of interest to evaluate in follow-up studies how the serotonergic transmission damage may influence PD motor symptoms along with the progression of the disease. Concurrently, the reliability of the proposed difference in raphe 5-HT transporter availability found by Qamhawi and coworkers in early PD patients should be also analyzed in more advanced PD patients. Remarkably, Qamhawi and coauthors documented that raphe 5-HT transporter availability did not correlate with PD non-motor symptoms, such as fatigue, depression, and sleep-wake cycle disturbances. In agreement with this finding, we did not identify mutual interplays linking CSF 5-HT and 5-HIAA concentrations to depression, apathy, and sleep disturbances. Although our report sustained Qamhawi and coworkers results, literature proposes controversial data regarding the involvement of serotonergic pathways breakage in the pathophysiology of PD non-motor symptoms (11), thus requiring further investigations. All considering, we suppose that the reduced 5-HT transporter availability, as shown by Qamhawi and collegues, and the 5-HT synthesis, metabolism, and turnover impairment, resulting in reduced CSF levels of 5-HT and 5-HIAA (8) may both contribute to the serotonergic transmission dysfunction evident in PD. Hence, serotonin circuitry inefficiency could represent the fitting partner of the dopaminergic deficit in PD.