Technique For Diagnosis Research Articles

AI in neurodegenerative disorders: A neurosurgical perspective

This paper investigates the application of artificial intelligence (AI) in diagnosing and managing neurodegenerative disorders that require neurosurgical intervention, such as Parkinson's disease (PD) and Alzheimer's disease (AD). A systematic review of the literature was conducted to identify studies that utilized AI techniques for diagnosis, treatment planning, or post-operative monitoring of these conditions. The results demonstrate the potential of AI to improve early detection, treatment outcomes, and patient care. However, challenges such as data quality, explainability, and ethical considerations must be addressed to ensure the responsible and effective integration of AI into clinical practice.

Machine learning techniques for diagnosis of rare diseases from medical images

Introduction/Background: Rare diseases are life-threatening or chronically debilitating conditions that affect a small percentage of the population. Early and accurate diagnosis of rare diseases is challenging due to their complexity and limited understanding. Conventional diagnostic methods are often inadequate, time-consuming, and expensive. Machine learning (ML) has emerged as a promising technique for the analysis of medical images to support the diagnosis of various diseases including rare disorders. ML algorithms can learn complex patterns from large medical imaging datasets to aid clinicians in disease diagnosis, prognosis, and detection of complications. Materials and Methods: A structured search was conducted in electronic databases, including PubMed, Scopus, Web of Science, and Google Scholar to identify peer-reviewed articles published between 2013 to 2023 related to ML-based diagnosis of rare diseases from medical images. A total of 187 articles were identified after removing duplicates. The titles and abstracts of retrieved articles were screened to determine their relevance based on the research objective. Finally, 51 full-text articles were selected for the final review. The key data extracted from selected studies included diseases, imaging modalities, ML algorithms, performance metrics, datasets, and limitations. Results: Most studies evaluated deep learning-based ML techniques, with convolutional neural networks (CNN) being the most applied algorithm. CNNs were mainly used to classify rare diseases based on specific imaging features in X-rays, CT, and MRI scans. Diseases frequently investigated included cardiovascular, neurological, and rare genetic disorders. Publicly available datasets such as Deep Lesion, MSD, and ChestX-ray14 were commonly utilized. Most studies reported high classification accuracy ranging from 80-95% on test datasets. However, limited generalizability due to small private datasets and lack of external validation were limitations. Discussion: The results demonstrate the potential of deep learning for the image-based diagnosis of rare diseases. Features learned from large imaging data sets enabled CNNs to distinguish subtle abnormalities. Hybrid models combining CNNs with other techniques like recurrent neural networks further improved performance. Overall, ML showed promise as a decision support tool. However, more multi-center validation studies are needed using larger and diverse datasets before clinical adoption. Standardization of performance metrics and reporting is also required to establish reliability and generalizability. Conclusion: This comprehensive review provided insights into ongoing research applying ML to medical images for rare disease diagnosis. While initial results are encouraging, further work is still necessary before ML can be reliably used in clinical decision making. Larger collaborative efforts and open-source datasets are needed to advance the field. Standardization of ML frameworks can also promote reproducible research and comparison of different methodologies.

Relative contribution of imaging techniques for the contemporary diagnosis of infective endocarditis: a single-center experience

Abstract Introduction In developed countries, the incidence of infective endocarditis (IE) is up to 6 cases per 100,000 individuals and in-hospital mortality rates are reported to reach 30%. The diagnostic recommendations for IE have been revised in the new ESC guidelines emphasizing the use of transesophageal echocardiography (TEE) and advanced imaging techniques (computed tomography [CT], magnetic resonance [MR], positron emission tomography [PET] and white blood cell scintigraphy [WBC-SPECT]). Aims This research aims to investigate the practical applicability of established clinical guidelines in a real-world population with suspected IE. Methods We reviewed the hospital database from 06/2021 to 06/2023 using the international classification of disease codification (ICD-10) for IE. Only patients admitted to Cardiology or Cardiac Surgery departments were included. Diagnosis of IE was defined according to the modified Duke criteria. Firstly, we identified individuals in whom diagnosis was performed by clinical presentation, blood cultures and transthoracic echocardiogram (TTE). Subsequently, we identified those who required further imaging diagnostic investigation. Results A total of 63 patients were included [mean age 64 ±14 years; 76% male (n=48)]. Native IE was diagnosed in 53 (84%) patients, prosthetic IE in 7 (11%) and cardiac implantable electronic devices-related IE in 3 (5%). A total of 26 (41%) patients had at least one predisposing risk factor, 48 (76%) presented with fever, 24 (38%) suffered an embolic event and 1 (2%) had an immunological phenomenon. Out of 49 positive blood cultures (78%), typical microorganisms consistent with IE were isolated in 25 (78%) of samples: 13 (34%) staphylococcus aureus, 10 (26%) oral streptococci, 9 (24%) enterococcus faecalis, 5 (13%) streptococcus gallolyticus and 1 (3%) HACEK group. Overall, in 22 (34%) patients, a definitive diagnosis of IE was established by means of clinical presentation, blood cultures and TTE. In the remaining, TEE was performed in 86% (n=36). Of those, a definite diagnosis was established in 52% (n=22). Brain and whole-body imaging upgraded the diagnosis from possible to definite in 3 (5%) patients. In the one patient in which a comprehensive clinical evaluation including TTE and TEE rejected IE, the diagnosis was ultimately established by means of PET. The median time from admission to the definite/possible diagnosis of IE was 6 (IQR 2-17) days. A total of 47 (75%) patients underwent surgery, with the most frequent indications being heart failure 46% (n=21) and uncontrolled infection 28% (n=13). Time from diagnosis to surgery was 10 (2-19) days, hospital length of stay was 45 (35-70) days and in-hospital mortality 21%. Conclusion Clinical presentation, blood cultures and TTE plus TEE established the definite or possible diagnosis of IE in most patients with suspected IE. Advanced imaging techniques allowed the establishment of definite diagnosis in only 6% of patients.

MACHINE-LEARNING TECHNIQUES IN MULTIPLE SCLEROSIS PREDICTION USING EEG

The diagnosis and quantification of Multiple Sclerosis (MS) have typically depended on skilled doctors recognizing visual patterns, such as Magnetic Resonance Imaging (MRI) and Electroencephalography (EEG), which resulted in a costly, time-consuming and non-reproducible process. The application of Machine Learning (ML) in MS diagnosis has been getting a lot of attention in the last few years due to the volume of scientific data, the heterogeneity of disease courses, and the variety of diagnostic methods. The EEG has the capability to detect important changes in the brain’s inherent electrical activity, which are influenced by changes in the neural network connections associated with inflammatory demyelinating and neural damage characteristic of the MS. Utilizing multimodal machine learning over the clinically available data may be a contemporary strategy with amazing potential to facilitate early diagnosis. Considering recent EEG investigations as well as the accessibility to their datasets would be the initial steps in utilizing the ML in MS diagnosis. This paper provides a systematic review of the latest techniques for MS diagnostic based on PRISMA guidelines with the prospect of ML application in their investigations. The goal is to find if EEG could be considered a robust and accurate technique for MS diagnosis. In accordance with PRISMA guidelines, we consider 111 papers. In our review, 404 people are considered including 209 with MS and 195 healthy controls. As a result, we generated an updated investigation looking at the ML approaches as well as utilizing EEG as an accurate, but less often used method to help with early diagnosis of MS. We summarize, analyze, discuss, and synthesize the recently published works, current trends, and open research issues. The review also points out knowledge gaps about the necessity of validating results and addressing constraints such as limited sample number. Our investigation proves that the precision of the supervised strategies such as [Formula: see text]NN and SVM is typically higher than that of the unsupervised strategies. On the other hand, by utilizing various techniques such as splitting EEG signal sub-bands, signal windowing, and identifying effective features from the data analysis approaches, we have been able to achieve significant classification accuracy higher than 99%. According to the high degree of accuracy of the results, this approach is becoming the focal point of the research works. The high diagnostic accuracy of the proposed machine learning techniques on the EEG signal analysis shows its potential capacity to become a more widespread procedure as the MS diagnostic techniques. To develop the reliability of these methods, gathering, and analyzing more EEG signals from MS patients and creating more suitable EEG protocols are essential in future studies. In the same way, for the dynamic and online analyses of the EEG signals, in-depth studies are needed to determine more effective EEG protocols and machine-learning techniques.

Transcutaneous stimulation as a niche theme in gastroparesis therapy

Introduction Gastroparesis, a global condition causing bile salt accumulation, is prevalent globally. Diagnosis techniques like bile salt titration and nitric oxide sulfate can improve patient care. However, simptomatic control is needed to reduce inflammation and control potential diseases. Neurological techniques like gyroscope stimulation and endoscopy can diagnose refractive gastroparesis. Interdisciplinary collaboration and bibliometric research are crucial for finding effective treatments. Gastroparesis, a motility issue affecting 0.9-1.3% of diabetics, can be improved by new diagnostic methods like osmotic pressure and gastric emptying, enhancing patient treatment. Methods This study uses a literature review methodology to gather data from the Scopus database on neuroaid, analyzing it using Biblioshiny and VOSviewer software. The focus is on dietary adjustments, glucose regulation, and transcutaneous stimulation’s role in gastroparesis treatment, using quantitative and qualitative analysis. Results The research trend found are documents by year, most relevant sources, factorial map of the most cited documents, factorial map of The documents with the highest contributes, documents by author, documents by country or territory, documents by subject area, documents by affiliation, network visualization, overlay visualization of scopus database using vosviewer, density visualization, thematic map, thematic evolution, cluster analysis, topic dendogram, and country collaboration map. According to our analysis, transcutaneous stimulation holds great promise for treating gastroparesis. We also found the necessity of multidisciplinary collaboration in the management of this illness. Conclusions The study on gastroparesis highlights key themes like diet modification, glucose control, medication therapy, Cajal’s role in smooth muscle concentration, common causes, transcutaneous stimulation, motorcycle themes, vagus nerve, and emerging devices and electronics. Basic themes include gastrointestinal disorders, neuromodulation, patients, diabetes, and gastric electrical stimulation. The management of gastroparesis involves multidisciplinary approaches, lifestyle changes, medication therapy, and bedtime interventions, with further investigation into transcutaneous stimulation being warranted.

Texture Analysis in Volumetric Imaging for Dentomaxillofacial Radiology: Transforming Diagnostic Approaches and Future Directions

This narrative review explores texture analysis as a valuable technique in dentomaxillofacial diagnosis, providing an advanced method for quantification and characterization of different image modalities. The traditional imaging techniques rely primarily on visual assessment, which may overlook subtle variations in tissue structure. In contrast, texture analysis uses sophisticated algorithms to extract quantitative information from imaging data, thus offering deeper insights into the spatial distribution and relationships of pixel intensities. This process identifies unique “texture signatures”, serving as markers for accurately characterizing tissue changes or pathological processes. The synergy between texture analysis and radiomics allows radiologists to transcend traditional size-based or semantic descriptors, offering a comprehensive understanding of imaging data. This method enhances diagnostic accuracy, particularly for the assessment of oral and maxillofacial pathologies. The integration of texture analysis with radiomics expands the potential for precise tissue characterization by moving beyond the limitations of human eye evaluations. This article reviews the current trends and methodologies in texture analysis within the field of dentomaxillofacial imaging, highlights its practical applications, and discusses future directions for research and dental clinical practice.

Profile of cross-reactivity to common pollen allergens in Northwest China based on component resolved diagnosis.

The prevalence of allergic diseases such as Allergic Rhinitis and Asthma is steadily increasing globally, with pollen allergy being one of the most significant sensitizing factors. However, the cross-reactivity of different pollen allergies remains unclear, posing challenges in the diagnosis and treatment of individuals with multiple sensitivities. In this study, the Component Resolved Diagnosis technique was performed to simultaneously measure the specific IgE concentrations of 52 patients against Art v and its components (Art v 1), Phl p and its components (Phl p 1, Phl p 4, Phl p 5, Phl p 6, Phl p 7, Phl p 12), Bet v and its components (Bet v 1, Bet v 2), Amb a and its component (Amb a 1), and Amb p. Additionally, sIgE inhibition tests were conducted by Art v, Phl p, and Bet v extracts. Among Art v-positive patients, 64.6% showed positivity for Art v 1. In Phl p-positive patients, Phl p 12 had the highest positivity rate (75.0%). Among Bet v-positive patients, 75.6% exhibited positivity for Bet v 2, whereas for Amb a and Amb p-positive patients, 23.7% and 29.0% respectively showed positivity for Amb a 1. The sIgE inhibition assays results revealed that Art v extract had inhibition rates greater than 73.2% against Phl p and its component Phl p 12, as well as Bet v and its component Bet v 2. Simultaneously, Phl p extract showed inhibition rates of 80.70-89.87% against Phl p 12, Bet v and Bet v 2. Bet v extract showed inhibition rates ranging from 21.9 to 59.8% against Phl p and Bet v 2, with a better inhibition rate (76.80%) against Phl p 12. In conclusion, Art v 1 is identified as the principal component of Art v. The profilin proteins of Phl p and Bet v (Phl p 12 and Bet v 2), are implicated as potential cross-reactive elements contributing to polysensitization in patients with respiratory allergies in the Northwest region of China. This cross-reactivity leads to a shared sensitization mechanism among pollen allergens such as Art v, Phl p, and Bet v.

A Comparative Study of Measurement Systems Using Machine Learning Techniques for Tool Fault Di-agnosis During Metal Removal in the Milling Process

Despite significant advancements in both measurement systems and machine learning techniques, the integration of these technologies for real-time tool fault diagnosis in milling processes remains under developed. Existing studies tend to focus on a comprehensive comparative analysis that bridges these two areas machine learning algorithms or the application of specific measurement sys-tems. There is also a gap in evaluating the cost-effectiveness and practicality of different measurement systems when integrated with machine learning models for industrial applications. This study addresses these gaps by conducting a detailed comparative analysis of multiple measurement sys-tems and their performance with machine learning techniques in a real-world milling context, aim-ing to provide practical recommendations for industry adoption. Using both traditional and Artificial Intelligence (AI) to define and exploit sensory systems in the milling process, as well as various (direct and indirect) monitoring approaches, are summarised in this study. Machine learning tech-niques SVM, KNN, DT performs better and provide higher accuracy and in feature extraction clas-sification techniques statistical features, wavelet transform with the Holder Exponent (HE) having higher accuracy for diagnosing the tool faults.

The state of cancer care in Russia: pancreatic cancer (C25). Diagnosis, prevalence, quality of accounting, typical mortality. Part 1. (clinical and population-based research)

The study focuses on pancreatic cancer (C25), a malignant neoplasm arising from the ductal epithelium or glandular tissue of the pancreas, which accounts for 3% of the overall cancer incidence in Russia. The rates of incidence and mortality are rising, with the number of newly registered patients in Russia being lower than the number of recorded deaths, although the one-year mortality rate among patients is decreasing. The direct cause of pancreatic cancer (C25) remains unknown. Risk factors for developing this condition include genetics, smoking, alcohol abuse, a sedentary lifestyle, excessive meat consumption, and a lack of plant-based foods in the diet. Diseases associated with a high risk of this pathology include long-standing chronic pancreatitis, newly diagnosed type 2 diabetes in individuals aged 50-70, and cystic neoplasms of the pancreas. The aim of the study is to examine the patterns of incidence and mortality, the quality of patient registration, the characteristics of tumor localization, and the histological structure of pancreatic cancer (C25). The study will also track the nature of annual mortality among patients and explore the possibilities, methods, and techniques of modern diagnosis and treatment for these patients. The research confirmed the significant burden of pancreatic cancer (C25), primarily due to the late detection of this disease. The study provided sufficient material to analyze age-related risk factors, as well as the patterns of incidence and mortality in the population. It also examined and presented mortality rates among patients, including during the first year of observation.

Orthogonal Control of Nucleic Acid Function via Chemical Caging-Decaging Strategies.

The ability to precisely control the function of nucleic acids plays an important role in biosensing and biomedicine. In recent years, novel strategies employing biological, physical, and chemical triggers have been developed to modulate the function of nucleic acids spatiotemporally. These approaches commonly involve the incorporation of stimuli-responsive groups onto nucleic acids to block their functions until triggers-induced decaging restore activity. These inventive strategies deepen our comprehension of nucleic acid molecules' dynamic behavior and provide new techniques for precise disease diagnosis and treatment. Focusing on the spatiotemporal regulation of nucleic acid molecules through the chemical caging-decaging strategy, we here present an overview of the innovative triggered control mechanisms and accentuate their implications across the fields of chemical biology, biomedicine, and biosensing.

Current signal analysis using SW-GAT networks for fault diagnosis of electromechanical drive systems under extreme data imbalance

Abstract In complex industrial environments, ensuring the safe operation and effective maintenance of electromechanical equipment is of paramount importance. Intelligent fault diagnosis based on deep learning is currently the most popular data-driven method. However, conventional intelligent fault diagnosis techniques face several challenges: (1) Most diagnostic models rely heavily on analyzing vibration signals. However, vibration sensors are difficult to deploy in space-constrained environments, and vibration signals are frequently contaminated by strong noise. (2) The prevalence of class imbalance between normal and fault data in equipment condition monitoring can lead to model over-reliance on information from a few classes. (3) Traditional diagnostic models presuppose data independence, neglecting the coupling relationships between data. To address the aforementioned issue, this paper proposes a Self-Weighted Graph Attention Networks (SW-GAT) based on motor stator current signal analysis, aimed at solving the fault diagnosis problem of critical transmission components in electromechanical systems under severely imbalanced data scenarios. Firstly, the raw current data is preprocessed using Stacked Auto-Encoders (SAE), and then the decoded current frequency-domain data is utilized to construct graphical data, thereby enhancing the non-common features and weak fault information in the current signals. Secondly, by introducing the graph pooling attention mechanism into GAT, the model can more effectively focus on useful fault feature information within the graph data. Finally, a novel interclass adjustment loss function is designed to adaptively adjust and balance class weights, enabling the model to pay greater attention to minority class samples and thereby improving the recognition accuracy for minority class faults. Validating the proposed method on two cases and comparing it with other advanced approaches, our method achieved the highest accuracy among the compared methods.

A multi-source domain feature-decision dual fusion adversarial transfer network for cross-domain anti-noise mechanical fault diagnosis in sustainable city

Rotating machinery forms the critical backbone of infrastructure in a sustainable city, with bearings playing a pivotal role as key mechanical transmission components. Therefore, the health status of these bearings directly influences the safe operation of the infrastructure. Accurate and reliable diagnosis of defects in these components minimizes downtime, reduces maintenance costs, and prevents major accidents, ultimately providing insights in the construction and management of a sustainable city. Typically, in actual industrial scenarios, varying working conditions and various types of machines can result in significant discrepancies in the distribution of sample data. Moreover, the non-negligible noise may degrade the diagnostic performance. Therefore, realizing an accurate and reliable bearing diagnosis considering the cross-domain and noise environment remains a challenge. Leveraging the merits of information fusion and multi-source domain transfer learning, this article proposes a multi-source domain feature-decision dual fusion adversarial transfer network (DFATN) to break through the aforesaid limitations. Initially, an adversarial transfer framework is developed, incorporating novel feature matching evaluation and joint distribution difference losses. This framework is designed to facilitate the learning of feature invariants across domains and to enhance the sharing of domain-specific knowledge, even in noise. Relying on channel-spatial interactive feature fusion, a multi-scale feature extractor (MFE) is constructed to share the interaction and enhance the modeling of complex features in multiple dimensions. Additionally, a fault state-related decision fusion mechanism (SDF) is also implemented to integrate diagnostic information, significantly enhancing the generalization performance and robustness of the proposed network. By employing both public Paderborn University (PU) and laboratory-collected (Lab) datasets, the effectiveness and superiority of the proposed DFATN on bearing fault diagnosis are validated. For cross-working condition tasks, the proposed method realizes impressive performance, with average accuracies of 96.52% and 98.76% for Paderborn University (PU) and laboratory-collected (Lab) datasets, respectively. For cross-machine tasks, the average accuracy is 83.36%, outperforming other latest cross-domain fault diagnosis techniques.

A Recent Advance in the Diagnosis, Treatment, and Vaccine Development for Human Schistosomiasis.

Schistosomiasis, which affects a large number of people worldwide, is among the most overlooked parasitic diseases. The disease is mainly prevalent in sub-Saharan Africa, southeast Asian countries, and South America due to the lack of adequate sanitation. The disease is mainly associated with poor hygiene, sanitation, and contaminated water, so it is also known as a disease of poverty. Three Schistosoma species (S. mansoni, S. japonicum, and S. haematobium) cause significant human infections. Co-infections with Schistosoma and other parasites are widely common. All these parasites may cause intestinal or urogenital schistosomiasis, where the disease may be categorized into the acute, sensitized, and chronic phases. The disease is more prevalent among school children, which may cause anemia and reduce development. Chronic infections frequently cause significant liver, intestinal, and bladder damage. Women exposed to contaminated water while performing normal duties like washing clothes might acquire urogenital schistosomiasis (UGS), which can cause tissue damage and raise the risk of blood-borne disease transmission, including human immunodeficiency virus (HIV) transmission. Praziquantel (PZQ) is the World Health Organization (WHO)-prescribed treatment for individuals who are known to be infected, but it does not prevent further re-infections with larval worms. Vaccine development and new molecular-based diagnosis techniques have promised to be a reliable approach to the diagnosis and prevention of schistosomiasis. The current review emphasizes the recent advancement in the diagnosis of schistosomiasis by molecular techniques and the treatment of schistosomiasis by combined and alternative regimes of drugs. Moreover, this review has also focused on the recent outbreak of schistosomiasis, the development of vaccines, and their clinical trials.

PCR- and wash-free detection of serum miRNA via signaling probe hybridization.

Detection of microRNAs (miRNAs) in the serum is an effective liquid biopsy technique for cancer diagnosis. However, conventional diagnostic methods are time-consuming and complex. Therefore, in this study, we established a signaling probe-based DNA microarray system for miRNA detection. PCR, fluorescence labeling, and washing are not necessary for signaling probes. Four probes were designed using different miRNAs as diagnostic cancer markers. The developed system is useful for various miRNAs, regardless of their target lengths (18-26-mer) and GC content (36%-89%). Here, all the assays were performed within 40 min. Overall, our signaling probe-based DNA hybridization system facilitates the simple and rapid detection of serum miRNAs without the need for gene amplification, fluorescence labeling and washing.

Highly Sensitive Molecular Diagnostic Platform for Scrub Typhus Diagnosis Using O. tsutsugamushi Enrichment and Nucleic Acid Extraction.

Scrub typhus is caused by the Gram-negative obligate intracellular bacterium Orientia tsutsugamushi, and this tick-borne disease is difficult to distinguish from other acute febrile illnesses as it typically presents with symptoms such as rash, crusting at the bite site, headache, myalgia, lymphadenopathy, and elevated liver transaminases. It can often be diagnosed clinically, but not all patients present with characteristic symptoms, so serological diagnosis and molecular techniques may be required. However, existing diagnostic tests often have low sensitivity and specificity, making early detection difficult. This study presents a nucleic acid extraction method using large volumes of plasma and buffy coat to increase sensitivity, as well as an improved detection method using two target genes. Using the I-PULL device, nucleic acids can be extracted from up to 4 mL of sample in 30 min, avoiding contamination. The extracted DNA detects two genes of O. tsutsugamushi, increasing sensitivity compared to single-gene detection. Clinical validation in 38 patient samples showed 100% specificity and 95.24% sensitivity for the single target gene, with specificity and sensitivity rising to 100% when both genes are analyzed. This molecular diagnostic platform can be useful for distinguishing scrub typhus from similar diseases.

An EfficientNet integrated ResNet deep network and explainable AI for breast lesion classification from ultrasound images

AbstractBreast cancer is one of the major causes of deaths in women. However, the early diagnosis is important for screening and control the mortality rate. Thus for the diagnosis of breast cancer at the early stage, a computer‐aided diagnosis system is highly required. Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost. Recently, many learning‐based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset (BUSI) datasets; however, the manual handling is not an easy process and time consuming. The authors propose an EfficientNet‐integrated ResNet deep network and XAI‐based framework for accurately classifying breast cancer (malignant and benign). In the initial step, data augmentation is performed to increase the number of training samples. For this purpose, three‐pixel flip mathematical equations are introduced: horizontal, vertical, and 90°. Later, two pre‐trained deep learning models were employed, skipped some layers, and fine‐tuned. Both fine‐tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer. Explainable artificial intelligence‐based analysed the performance of trained models. After that, a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean. This technique selects the best features and fuses using a new parallel zero‐padding maximum correlated coefficient features. In the end, the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms. The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4% and 98% accuracy in two different experiments. Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy. In addition, the proposed framework was executed less than the original deep learning models.

Learning from Imbalanced Data: Integration of Advanced Resampling Techniques and Machine Learning Models for Enhanced Cancer Diagnosis and Prognosis

Background/Objectives: This study aims to evaluate the performance of various classification algorithms and resampling methods across multiple diagnostic and prognostic cancer datasets, addressing the challenges of class imbalance. Methods: A total of five datasets were analyzed, including three diagnostic datasets (Wisconsin Breast Cancer Database, Cancer Prediction Dataset, Lung Cancer Detection Dataset) and two prognostic datasets (Seer Breast Cancer Dataset, Differentiated Thyroid Cancer Recurrence Dataset). Nineteen resampling methods from three categories were employed, and ten classifiers from four distinct categories were utilized for comparison. Results: The results demonstrated that hybrid sampling methods, particularly SMOTEENN, achieved the highest mean performance at 98.19%, followed by IHT (97.20%) and RENN (96.48%). In terms of classifiers, Random Forest showed the best performance with a mean value of 94.69%, with Balanced Random Forest and XGBoost following closely. The baseline method (no resampling) yielded a significantly lower performance of 91.33%, highlighting the effectiveness of resampling techniques in improving model outcomes. Conclusions: This research underscores the importance of resampling methods in enhancing classification performance on imbalanced datasets, providing valuable insights for researchers and healthcare professionals. The findings serve as a foundation for future studies aimed at integrating machine learning techniques in cancer diagnosis and prognosis, with recommendations for further research on hybrid models and clinical applications.

Bio-inspired feature selection for early diagnosis of Parkinson's disease through optimization of deep 3D nested learning.

Parkinson's disease (PD) is one of the most common neurodegenerative disorders that affect the quality of human life of millions of people throughout the world. The probability of getting affected by this disease increases with age, and it is common among the elderly population. Early detection can help in initiating medications at an earlier stage. It can significantly slow down the progression of this disease, assisting the patient to maintain a good quality of life for a more extended period. Magnetic resonance imaging (MRI)-based brain imaging is an area of active research that is used to diagnose PD disease early and to understand the key biomarkers. The prior research investigations using MRI data mainly focus on volume, structural, and morphological changes in the basal ganglia (BG) region for diagnosing PD. Recently, researchers have emphasized the significance of studying other areas of the human brain for a more comprehensive understanding of PD and also to analyze changes happening in brain tissue. Thus, to perform accurate diagnosis and treatment planning for early identification of PD, this work focuses on learning the onset of PD from images taken from whole-brain MRI using a novel 3D-convolutional neural network (3D-CNN) deep learning architecture. The conventional 3D-Resent deep learning model, after various hyper-parameter tuning and architectural changes, has achieved an accuracy of 90%. In this work, a novel 3D-CNN architecture was developed, and after several ablation studies, the model yielded results with an improved accuracy of 93.4%. Combining features from the 3D-CNN and 3D ResNet models using Canonical Correlation Analysis (CCA) resulted in 95% accuracy. For further enhancements of the model performance, feature fusion with optimization was employed, utilizing various optimization techniques. Whale optimization based on a biologically inspired approach was selected on the basis of a convergence diagram. The performance of this approach is compared to other methods and has given an accuracy of 97%. This work represents a critical advancement in improving PD diagnosis techniques and emphasizing the importance of deep nested 3D learning and bio-inspired feature selection.

Utilizing Multi-layer Perceptron for Esophageal Cancer Classification Through Machine Learning Methods

Aims This research paper aims to check the effectiveness of a variety of machine learning models in classifying esophageal cancer through MRI scans. The current study encompasses Convolutional Neural Network (CNN), K-Nearest Neighbor (KNN), Recurrent Neural Network (RNN), and Visual Geometry Group 16 (VGG16), among others which are elaborated in this paper. This paper aims to identify the most accurate model to facilitate increased, improved diagnostic accuracy to revolutionize early detection methods for this dreadful disease. The ultimate goal is, therefore, to improve the clinical practice performance and its results with advanced machine learning techniques in medical diagnosis. Background Esophageal cancer poses a critical problem for medical oncologists since its pathology is quite complex, and the death rate is exceptionally high. Proper early detection is essential for effective treatment and improved survival. The results are positive, but the conventional diagnostic methods are not sensitive and have low specificity. Recent progress in machine learning methods brings a new possibility to high sensitivity and specificity in the diagnosis. This paper explores the potentiality of different machine-learning models in classifying esophageal cancer through MRI scans to complement the constraints of the traditional diagnostics approach. Objective This study is aimed at verifying whether CNN, KNN, RNN, and VGG16, amongst other advanced machine learning models, are effective in correctly classifying esophageal cancer from MRI scans. This review aims at establishing the diagnostic accuracy of all these models, with the best among all. It plays a role in developing early detection mechanisms that increase patient outcome confidence in the clinical setting. Methods This study applies the approach of comparative analysis by using four unique machine learning models to classify esophageal cancer from MRI scans. This was made possible through the intensive training and validation of the model using a standardized set of MRI data. The model’s effectiveness was assessed using performance evaluation metrics, which included accuracy, precision, recall, and F1 score. Results In classifying esophageal cancers from MRI scans, the current study found VGG16 to be an adequate model, with a high accuracy of 96.66%. CNN took the second position, with an accuracy of 94.5%, showing efficient results for spatial pattern recognition. The model of KNN and RNN also showed commendable performance, with accuracies of 91.44% and 88.97%, respectively, portraying their strengths in proximity-based learning and handling sequential data. These findings underline the potential to add significant value to the processes of esophageal cancer diagnosis using machine learning models. Conclusion The study concluded that machine learning techniques, mainly VGG16 and CNN, had a high potential for escalated diagnostic precision in classifying esophageal cancer from MRI imaging. VGG16 showed great accuracy, while CNN displayed advanced spatial detection, followed by KNN and RNN. Thus, the results set new opportunities for introducing advanced computational models to the clinics, which might transform strategies for early detection to improve patient-centered outcomes in oncology.

GAN-Augmented Naïve Bayes for identifying high-risk coronary artery disease patients using CT angiography data

Coronary artery disease (CAD) is one of the most common cardiovascular disorders affecting millions of individuals globally. It is the leading cause of mortality in both the wealthy and impoverished nations. CAD patients exhibit a wide range of symptoms, some of which are not evident until a major incident occurs. The development of techniques for early detection and precise diagnosis is heavily dependent on research. The proposed system introduces a novel approach, Generative Adversarial Networks Augmented Naïve Bayes (GAN-ANB), to classify high-risk CAD patients using Coronary Computed Tomography Angiography (CCTA) imaging data. The database included images from Coronary Computed Tomography Angiography (CCTA) records of 5,000 individuals. The developed GAN framework consists of a generator to generate synthetic patient profiles, and a discriminator to distinguish between genuine and synthetic profiles to improve the identification of high-risk CAD patients. Adding synthetic data to the training process allowed the discriminator to be utilized further to improve predictive modeling. The performance of the GAN-enhanced prediction model was assessed using accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic curve (ROC). The model exhibited an outstanding Dice Similarity Coefficient (0.91), Mean Intersection Over Union (0.90), recall (0.96), and precision (0.98) in differentiating between high-risk and low-risk individuals. The identification of high-risk patients with CAD is greatly enhanced by the integration of GANs with clinical and imaging data. ROC of 0.99 was achieved by the GAN-ANB model, which outperformed conventional machine learning models, was achieved using the GAN-ANB model. High cholesterol level, diabetes, and some CCTA-derived imaging characteristics, including plaque load and luminal stenosis, were among the major predictors. This method offers a powerful tool for early diagnosis and intervention, potentially leading to improved patient outcomes and lower healthcare expenditure.