Knowledge distillation model for Acute Lymphoblastic Leukemia Detection: Exploring the impact of nesterov-accelerated adaptive moment estimation optimizer

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 94, P. 106246 - 106246

Published: March 30, 2024

Language: Английский

---

Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 58(1)

Published: Nov. 8, 2024

The current study investigates the robustness of deep learning models for accurate medical diagnosis systems with a specific focus on their ability to maintain performance in presence adversarial or noisy inputs. We examine factors that may influence model reliability, including complexity, training data quality, and hyperparameters; we also security concerns related attacks aim deceive along privacy seek extract sensitive information. Researchers have discussed various defenses these enhance robustness, such as input preprocessing, mechanisms like augmentation uncertainty estimation. Tools packages extend reliability features frameworks TensorFlow PyTorch are being explored evaluated. Existing evaluation metrics additionally This paper concludes by discussing limitations existing literature possible future research directions continue enhancing status this topic, particularly domain, ensuring AI trustworthy, reliable, stable.

Language: Английский

---

Deep Learning-Based Approaches for Enhanced Diagnosis and Comprehensive Understanding of Carpal Tunnel Syndrome

Diagnostics, Journal Year: 2023, Volume and Issue: 13(20), P. 3211 - 3211

Published: Oct. 14, 2023

Carpal tunnel syndrome (CTS) is a prevalent medical condition resulting from compression of the median nerve in hand, often caused by overuse or age-related factors. In this study, total 160 patients participated, including 80 individuals with CTS presenting varying levels severity across different age groups. Numerous studies have explored use machine learning (ML) and deep (DL) techniques for diagnosis. However, further research required to fully leverage potential artificial intelligence (AI) technology diagnosis, addressing challenges limitations highlighted existing literature. our work, we propose novel approach prediction, monitoring disease progression. The proposed framework consists three main layers. Firstly, employ distinct DL models Through experiments, demonstrates superior performance multiple evaluation metrics, an accuracy 0.969%, precision 0.982%, recall 0.963%. second layer focuses on predicting cross-sectional area (CSA) at 1, 3, 6 months using ML models, aiming forecast progression during therapy. best-performing model achieves 0.9522, R2 score 0.667, mean absolute error (MAE) 0.0132, squared (MdSE) 0.0639. highest predictive observed after months. third concentrates assessing significant changes patients' health status through statistical tests, significance Kruskal-Wallis test, two-way ANOVA test. These tests aim determine effect injections treatment. results reveal highly reduction symptoms, as evidenced scores Symptom Severity Scale Functional Status Scale, well decrease CSA following injection. SHAP then utilized provide understandable explanation final prediction. Overall, study presents comprehensive monitoring, showcasing promising terms accuracy, precision, effective prediction treatment effectiveness analysis.

Language: Английский

---

Carpal Tunnel Syndrome Automated Diagnosis: A Motor vs. Sensory Nerve Conduction-Based Approach

Bioengineering, Journal Year: 2024, Volume and Issue: 11(2), P. 175 - 175

Published: Feb. 11, 2024

The objective of this study was to evaluate the effectiveness machine learning classification techniques applied nerve conduction studies (NCS) motor and sensory signals for automatic diagnosis carpal tunnel syndrome (CTS). Two methodologies were tested. In first methodology, recorded from patients’ median transformed into time-frequency spectrograms using short-time Fourier transform (STFT). These then used as input a deep two-dimensional convolutional neural network (CONV2D) two categories: patients controls. second ulnar nerves subjected multilevel wavelet decomposition (MWD), statistical non-statistical features extracted decomposed signals. utilized train test classifiers. target set three normal subjects (controls), with mild CTS, moderate severe CTS based on conventional electrodiagnosis results. results analysis demonstrated that both surpassed previous attempts at diagnosis. models utilizing exhibited excellent performance, average accuracy 94%. Similarly, classifiers showed significant in distinguishing between controls, 97.1%. findings highlight efficacy incorporating algorithms diagnostic processes NCS, providing valuable tool clinicians management neuropathies such CTS.

Language: Английский

---

Artificial intelligence as an adjunctive tool in hand and wrist surgery: a review

Artificial Intelligence Surgery, Journal Year: 2024, Volume and Issue: 4(3), P. 214 - 32

Published: Sept. 2, 2024

Artificial intelligence (AI) is currently utilized across numerous medical disciplines. Nevertheless, despite its promising advancements, AI’s integration in hand surgery remains early stages and has not yet been widely implemented, necessitating continued research to validate efficacy ensure safety. Therefore, this review aims provide an overview of the utilization AI surgery, emphasizing current application clinical practice, along with potential benefits associated challenges. A comprehensive literature search was conducted PubMed, Embase, Medline, Cochrane libraries, adhering Preferred reporting items for systematic reviews meta-analyses (PRISMA) guidelines. The focused on identifying articles related utilizing multiple relevant keywords. Each identified article assessed based title, abstract, full text. primary 1,228 articles; after inclusion/exclusion criteria manual bibliography included articles, a total 98 were covered review. wrist diagnostic, which includes fracture detection, carpal tunnel syndrome (CTS), avascular necrosis (AVN), osteoporosis screening. Other applications include residents’ training, patient-doctor communication, surgical assistance, outcome prediction. Consequently, very tool that though further necessary fully integrate it into practice.

Language: Английский

---

None

Journal of Medicinal and Chemical Sciences, Journal Year: 2023, Volume and Issue: 6(10)

Published: June 15, 2023

Objective: This article aims to study clinical features of the courses different types CTS improve diagnostics and substantiate tactics treatment.Materials methods: An analysis a total 172 patients (comprising 242 extremities) was conducted displaying symptoms carpal tunnel syndrome (CTS). These were examined treated at SI "ITO NAMS Ukraine". All individuals grouped together for purpose our study.Results: analyzes results examining with signs types: idiopathic, posttraumatic, one associated orthopedic pathology, specifies in progression posttraumatic syndrome, on background an additional methods medical imaging confirm median nerve neuropathy canal, objectivize its severity, establishes etiology essential decide further treatment tactics.Conclusion: The recognized characteristics present opportunity support selection diagnostic procedure validate presence compression-ischemic nerve, ascertain identify underlying causes.

Language: Английский

---

A coupled electro-mechanical approach for early diagnostic of carpal tunnel syndrome

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: June 20, 2023

Abstract Carpal tunnel syndrome (CTS) is a pathology affecting hand function caused by median nerve overload. Numbness in the fingers, loss of sensory and motor hand, pain are all symptoms carpal syndrome. The lack numerical data about mechanical strain inside main disadvantage current clinical approaches employed diagnostics. Moreover, application each diagnostic method alone often leads to misdiagnosis. We proposed combined approach including motion capture, finite element modelling (FEM), electromechanical simulations evaluate compression find correlation with mobility. capture provided boundary conditions for FEM. After that, FEM finger flexion / extension were performed. Further, results put electrical model conduction based on Hodgkin-Huxley extended cable equation. It was exhibited reduced significantly throughout that compared flexion. During extension, load distribution over nine flexor tendons evaluated. index found have highest Mises stress values. how tendon connective tissue contact types affected pressure. difference between 31.7% 59.9% developed has potential become an alternative CTS at early stages. Additionally, it can be as non-invasive procedure evaluation stress.

Language: Английский

---