Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation DOI Creative Commons

Mojtaba Najafi,

Tohid Yousefi Rezaii,

Sebelan Danishvar

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(17), P. 7612 - 7612

Published: Sept. 2, 2023

The aim of this study was to use geometric features and texture analysis discriminate between healthy unhealthy femurs identify the most influential features. We scanned proximal femoral bone (PFB) 284 Iranian cases (21 83 years old) using different dual-energy X-ray absorptiometry (DEXA) scanners magnetic resonance imaging (MRI) machines. Subjects were labeled as “healthy” (T-score > −0.9) “unhealthy” based on results DEXA scans. Based geometry PFB in MRI, 204 retrieved. used support vector machine (SVM) with kernels, decision tree, logistic regression algorithms classifiers Genetic algorithm (GA) select best set maximize accuracy. There 185 participants classified 99 unhealthy. SVM radial basis function kernels had performance (89.08%) geometrical ones. Even though our findings show high model, further investigation more subjects is suggested. To knowledge, first that investigates qualitative classification PFBs MRI reference scans learning methods GA.

Language: Английский

Revolutionizing Spinal Care: Current Applications and Future Directions of Artificial Intelligence and Machine Learning DOI Open Access
Mitsuru Yagi,

Kento Yamanouchi,

Naruhito Fujita

et al.

Journal of Clinical Medicine, Journal Year: 2023, Volume and Issue: 12(13), P. 4188 - 4188

Published: June 21, 2023

Artificial intelligence (AI) and machine learning (ML) are rapidly becoming integral components of modern healthcare, offering new avenues for diagnosis, treatment, outcome prediction. This review explores their current applications potential future in the field spinal care. From enhancing imaging techniques to predicting patient outcomes, AI ML revolutionizing way we approach diseases. have significantly improved by augmenting detection classification capabilities, thereby boosting diagnostic accuracy. Predictive models also been developed guide treatment plans foresee driving a shift towards more personalized Looking future, envision further ingraining themselves care with development algorithms capable deciphering complex pathologies aid decision making. Despite promise these technologies hold, integration into clinical practice is not without challenges. Data quality, hurdles, data security, ethical considerations some key areas that need be addressed successful responsible implementation. In conclusion, represent potent tools transforming Thoughtful balanced technologies, guided considerations, can lead significant advancements, ushering an era personalized, effective, efficient healthcare.

Language: Английский

Citations

33
Bone tumors: state-of-the-art imaging DOI

Patrick Debs,

Shivani Ahlawat, Laura M. Fayad

et al.

Skeletal Radiology, Journal Year: 2024, Volume and Issue: 53(9), P. 1783 - 1798

Published: Feb. 27, 2024

Language: Английский

Citations

8
Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography DOI Creative Commons

Wilson Ong,

Ren Wei Liu,

Andrew Makmur

et al.

Bioengineering, Journal Year: 2023, Volume and Issue: 10(12), P. 1364 - 1364

Published: Nov. 27, 2023

Osteoporosis, marked by low bone mineral density (BMD) and a high fracture risk, is major health issue. Recent progress in medical imaging, especially CT scans, offers new ways of diagnosing assessing osteoporosis. This review examines the use AI analysis scans to stratify BMD diagnose By summarizing relevant studies, we aimed assess effectiveness, constraints, potential impact AI-based osteoporosis classification (severity) via CT. A systematic search electronic databases (PubMed, MEDLINE, Web Science, ClinicalTrials.gov) was conducted according Preferred Reporting Items for Systematic Reviews Meta-Analyses (PRISMA) guidelines. total 39 articles were retrieved from databases, key findings compiled summarized, including regions analyzed, type their efficacy predicting compared with conventional DXA studies. Important considerations limitations are also discussed. The overall reported accuracy, sensitivity, specificity classifying using images ranged 61.8% 99.4%, 41.0% 100.0%, 31.0% 100.0% respectively, areas under curve (AUCs) ranging 0.582 0.994. While additional research necessary validate clinical reproducibility these tools before incorporating them into routine practice, studies demonstrate promising opportunistically predict classify without need DEXA.

Language: Английский

Citations

16
Artificial Intelligence in Detection, Management, and Prognosis of Bone Metastasis: A Systematic Review DOI Open Access
Giuseppe Francesco Papalia, Paolo Brigato,

L. Sisca

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(15), P. 2700 - 2700

Published: July 29, 2024

Background: Metastasis commonly occur in the bone tissue. Artificial intelligence (AI) has become increasingly prevalent medical sector as support decision-making, diagnosis, and treatment processes. The objective of this systematic review was to assess reliability AI systems clinical, radiological, pathological aspects metastases. Methods: We included studies that evaluated use applications patients affected by Two reviewers performed a digital search on 31 December 2023 PubMed, Scopus, Cochrane library extracted authors, method, interest area, main modalities used, objectives from studies. Results: 59 analyzed contribution computational diagnosing or forecasting outcomes with metastasis. Six were specific for spine study involved nuclear medicine (44.1%), clinical research (28.8%), radiology (20.4%), molecular biology (6.8%). When primary tumor reported, prostate cancer most common, followed lung, breast, kidney. Conclusions: Appropriately trained models may be very useful merging information achieve an overall improved diagnostic accuracy metastasis bone. Nevertheless, there are still concerns settings. Ethical considerations legal issues must addressed facilitate safe regulated adoption technologies. limitations comprise stronger emphasis early detection rather than management prognosis well high heterogeneity type tumor, technology radiological techniques, pathology, laboratory samples involved.

Language: Английский

Citations

6
Bone tumors: a systematic review of prevalence, risk determinants, and survival patterns DOI Creative Commons
Hasan Ali Hosseini,

Sina Heydari,

Kiavash Hushmandi

et al.

BMC Cancer, Journal Year: 2025, Volume and Issue: 25(1)

Published: Feb. 21, 2025

Language: Английский

Citations

0
Bone Metastases DOI Open Access
Avipsa Hazra, Gowrav Baradwaj,

R. Sushma

et al.

Published: March 3, 2025

Citations

0
Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews DOI Creative Commons
Haishan Xu,

Ting‐Ting Gong,

Xin‐Jian Song

et al.

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e53567 - e53567

Published: April 1, 2025

Background Artificial intelligence (AI) has the potential to transform cancer diagnosis, ultimately leading better patient outcomes. Objective We performed an umbrella review summarize and critically evaluate evidence for AI-based imaging diagnosis of cancers. Methods PubMed, Embase, Web Science, Cochrane, IEEE databases were searched relevant systematic reviews from inception June 19, 2024. Two independent investigators abstracted data assessed quality evidence, using Joanna Briggs Institute (JBI) Critical Appraisal Checklist Systematic Reviews Research Syntheses. further in each meta-analysis by applying Grading Recommendations, Assessment, Development, Evaluation (GRADE) criteria. Diagnostic performance synthesized narratively. Results In a comprehensive analysis 158 included studies evaluating AI algorithms noninvasive across 8 major human system cancers, accuracy classifiers central nervous cancers varied widely (ranging 48% 100%). Similarities observed diagnostic head neck, respiratory system, digestive urinary female-related systems, skin, other sites. Most meta-analyses demonstrated positive summary performance. For instance, 9 meta-analyzed sensitivity specificity esophageal cancer, showing ranges 90%-95% 80%-93.8%, respectively. case breast detection, calculated pooled within 75.4%-92% 83%-90.6%, Four reported ovarian both 75%-94%. Notably, lung was relatively low, primarily distributed between 65% 80%. Furthermore, 80.4% (127/158) high according JBI Checklist, with remaining classified as medium quality. The GRADE assessment indicated that overall moderate low. Conclusions Although shows great achieving accelerated, accurate, more objective diagnoses multiple there are still hurdles overcome before its implementation clinical settings. present findings highlight concerted effort research community, clinicians, policymakers is required existing translate this into improved outcomes health care delivery. Trial Registration PROSPERO CRD42022364278; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022364278

Language: Английский

Citations

0
Artificial Intelligence in Hand and Wrist Imaging: Enhancing Diagnostics and Workflow DOI
Pranav Ajmera, Gandikota Girish, Amit Kharat

et al.

Medical radiology, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Integrating Artificial Intelligence in Orthopedic Care: Advancements in Bone Care and Future Directions DOI Creative Commons

Rahul Kumar,

Kyle Sporn,

Joshua Ong

et al.

Bioengineering, Journal Year: 2025, Volume and Issue: 12(5), P. 513 - 513

Published: May 13, 2025

Artificial intelligence (AI) is revolutionizing the field of orthopedic bioengineering by increasing diagnostic accuracy and surgical precision improving patient outcomes. This review highlights using AI for orthopedics in preoperative planning, intraoperative robotics, smart implants, bone regeneration. AI-powered imaging, automated 3D anatomical modeling, robotic-assisted surgery have dramatically changed practices. has improved planning enhancing complex image interpretation providing augmented reality guidance to create highly accurate strategies. Intraoperatively, surgeries enhance reduce human error while minimizing invasiveness. implant sensors allow vivo monitoring, early complication detection, individualized rehabilitation. It also advanced regeneration devices neuroprosthetics, highlighting its innovation capabilities. While advancements are exciting, challenges remain, like need standardized system validation protocols, assessing ethical consequences AI-derived decision-making, with bioprinting tissue engineering. Future research should focus on proving reliability predictability performance AI-pivoted systems their adoption within clinical practice. synthesizes recent developments impact potential future effectiveness care beyond.

Language: Английский

Citations

0
Assessment of Deep Learning Models for Cutaneous Leishmania Parasite Diagnosis Using Microscopic Images DOI Creative Commons

Ali Mansour Abdul Hafid ABDELMULA,

Omid Mırzaeı, Emrah Güler

et al.

Diagnostics, Journal Year: 2023, Volume and Issue: 14(1), P. 12 - 12

Published: Dec. 20, 2023

Cutaneous leishmaniasis (CL) is a common illness that causes skin lesions, principally ulcerations, on exposed regions of the body. Although neglected tropical diseases (NTDs) are typically found in areas, they have recently become more along Africa’s northern coast, particularly Libya. The devastation healthcare infrastructure during 2011 war and following conflicts, as well governmental apathy, may be causal factors associated with this catastrophic event. main objective study to evaluate alternative diagnostic strategies for recognizing amastigotes cutaneous parasites at various stages using Convolutional Neural Networks (CNNs). research additionally aimed testing different classification models employing dataset ultra-thin smear images Leishmania parasite-infected people leishmaniasis. pre-trained deep learning including EfficientNetB0, DenseNet201, ResNet101, MobileNetv2, Xception used leishmania parasite diagnosis task. To assess models’ effectiveness, we employed five-fold cross-validation approach guarantee consistency outputs when applied portions full dataset. Following thorough assessment contrast models, DenseNet-201 proved most suitable choice. It attained mean accuracy 0.9914 outstanding results sensitivity, specificity, positive predictive value, negative F1-score, Matthew’s correlation coefficient, Cohen’s Kappa coefficient. model surpassed other based comprehensive evaluation these key performance metrics.

Language: Английский

Citations

9