Cited by Opportunity to Use Artificial Intelligence in Medicine

Tailored Self-Supervised Pretraining Improves Brain MRI Diagnostic Models DOI

Xinhao Huang,

Zihao W. Wang, Weichen Zhou

et al.

Computerized Medical Imaging and Graphics, Journal Year: 2025, Volume and Issue: 123, P. 102560 - 102560

Published: April 17, 2025

Language: Английский

Citations

Machine learning in shoulder arthroplasty DOI

Tim Schneller, Moritz Kraus,

Jan Schätz

et al.

Bone & Joint Open, Journal Year: 2025, Volume and Issue: 6(2), P. 126 - 134

Published: Feb. 4, 2025

Aims Machine learning (ML) holds significant promise in optimizing various aspects of total shoulder arthroplasty (TSA), potentially improving patient outcomes and enhancing surgical decision-making. The aim this systematic review was to identify ML algorithms evaluate their effectiveness, including those for predicting clinical used image analysis. Methods We searched the PubMed, EMBASE, Cochrane Central Register Controlled Trials databases studies applying TSA. analysis focused on dataset characteristics, relevant subspecialties, specific used, performance outcomes. Results Following final screening process, 25 articles satisfied eligibility criteria our review. Of these, 60% tabular data while remaining 40% analyzed data. Among them, 16 were dedicated developing new models nine transfer leverage existing pretrained models. Additionally, three these underwent external validation confirm reliability effectiveness. Conclusion TSA demonstrated fair good performance, as evidenced by reported metrics. Integrating into daily practice could revolutionize TSA, both precision outcome predictions. Despite potential, lack transparency generalizability many current poses a challenge, limiting utility. Future research should prioritize addressing limitations truly propel field forward maximize benefits care. Cite article: Bone Jt Open 2025;6(2):126–134.

Language: Английский

Citations

荧光光谱结合机器学习应用于乳腺癌分子分型 DOI

许诺 Xu Nuo,

李奇 Li Qi,

黄翰林 Huang Hanlin

et al.

Laser & Optoelectronics Progress, Journal Year: 2025, Volume and Issue: 62(6), P. 0617001 - 0617001

Published: Jan. 1, 2025

Citations

X-ray image classification with dual-model information fusion and improved PSO algorithm DOI

Zhi Weng,

Hailong Zuo,

Zhiqiang Zheng

et al.

Signal Image and Video Processing, Journal Year: 2025, Volume and Issue: 19(7)

Published: May 9, 2025

Language: Английский

Citations

Evaluating artificial intelligence for medical imaging: a primer for clinicians DOI

Shivank Keni

British Journal of Hospital Medicine, Journal Year: 2024, Volume and Issue: 85(7), P. 1 - 13

Published: July 30, 2024

Artificial intelligence has the potential to transform medical imaging. The effective integration of artificial into clinical practice requires a robust understanding its capabilities and limitations. This paper begins with an overview key use cases such as detection, classification, segmentation radiomics. It highlights foundational concepts in machine learning types strategies, well training evaluation process. We provide broad theoretical framework for assessing effectiveness imaging intelligence, including appraising internal validity generalisability studies, discuss barriers translation. Finally, we highlight future directions travel within field multi-modal data integration, federated explainability. By having awareness these issues, clinicians can make informed decisions about adopting imaging, improving patient care outcomes.

Language: Английский

Citations

Explainable AI based automated segmentation and multi-stage classification of gastroesophageal reflux using machine learning techniques DOI

Rudrani Maity,

V. M. Raja Sankari,

U. Snekhalatha

et al.

Biomedical Physics & Engineering Express, Journal Year: 2024, Volume and Issue: 10(4), P. 045058 - 045058

Published: June 20, 2024

Presently, close to two million patients globally succumb gastrointestinal reflux diseases (GERD). Video endoscopy represents cutting-edge technology in medical imaging, facilitating the diagnosis of various ailments including stomach ulcers, bleeding, and polyps. However, abundance images produced by video necessitates significant time for doctors analyze them thoroughly, posing a challenge manual diagnosis. This has spurred research into computer-aided techniques aimed at diagnosing plethora generated swiftly accurately. The novelty proposed methodology lies development system tailored diseases. work used an object detection method called Yolov5 identifying abnormal region interest Deep LabV3+ segmentation regions GERD. Further, features are extracted from segmented image given as input seven different machine learning classifiers custom deep neural network model multi-stage classification DeepLabV3+ attains excellent accuracy 95.2% F1 score 93.3%. dense obtained 90.5%. Among classifiers, support vector (SVM) outperformed with 87% compared all other class combination detection, learning-based enables timely identification surveillance problems associated GERD healthcare providers.

Language: Английский

Citations

The use of artificial intelligence in radiology: new possibilities for diagnostic imaging. A literature review DOI

Weronika Stawska, Magdalena Miłek, Ksenia Kwaśniak

et al.

Quality in Sport, Journal Year: 2024, Volume and Issue: 16, P. 52215 - 52215

Published: July 7, 2024

Introduction and purpose: Rapid advances in technology enable innovative solutions to be implemented modern medicine, relieving healthcare workers by speeding up diagnosis improving the quality of treatment. The subject this review is Artificial Intelligence (AI), an form help daily practice doctors. It offers opportunity relieve accelerating process effectiveness aim paper present current state knowledge, assess algorithms recognition interpretation abnormalities medical images compared specialists radiology discuss challenges associated with implementation AI various specialties. Brief description knowledge: intelligence, especially through machine learning deep techniques, has found wide application radiology. Many facilities around world use advanced systems day-to-day work radiologists, including Mayo Clinic, Massachusetts General Hospital, University Tokyo Hospital. Summary: Studies show that while can perform worse than radiologists some areas, they are at forefront others, detecting subtle abnormalities. effective artificial intelligence requires addressing regulatory, ethical, training issues. Despite these challenges, potential play a key role future revolutionize practice, opening new perspectives health care.

Language: Английский

Citations

Enhancing Diagnostic Accuracy with SE-Inception Model Integration in Pressure Ulcer Detection DOI

Zongying Gui,

Jingnan Wang,

Youfen Fan

et al.

Annali Italiani di Chirurgia, Journal Year: 2024, Volume and Issue: 95(4), P. 609 - 620

Published: Aug. 20, 2024

Language: Английский

Citations

Comparativa de diferentes modelos radiómicos para la clasificación de lesiones adrenales indeterminadas diagnosticadas de forma incidental en TC con contraste DOI

Daniel Prieto,

Miguel Ángel Gómez Bermejo,

E. Canales Lachén

et al.

Revista de Física Médica, Journal Year: 2024, Volume and Issue: 25(2), P. 11 - 23

Published: Nov. 4, 2024

Purpose: A comparison of different machine learning models to discriminate adrenal incidentalomas by CT studies was performed. Methods: Sixty-two features were obtained from a sample 61 using the free license software LIFEx and 19 radiomic performed with feature selection methods obtain most efficient determination possible malignancy. For all them, four cross-validation evaluated. Adenoma contouring in duplicate radiologists evaluating both groups. Results: ROC AUC between 0.42 (0.09-0.81) 0.92 (0.63-1.00), accuracy 0.63 (0.43-0.79) 0.94 (0.82-1.00). The best-performing model balanced logistic regression applied 14 an intraclass coefficient greater than 0.9, which (0.74-1.00), 0.917 benign recall (0.65-1.00) malignant 1.00 (0.71-1.00) obtained. Conclusions: evaluation validation has allowed us for discrimination

Language: Английский

Citations

Unveiling Lung Diseases in CT Scan Images With a Hybrid Bio‐Inspired Mutated Spider‐Monkey and Crow Search Algorithm DOI

Anupam Kumar, Faiyaz Ahmad, Bashir Alam

et al.

Expert Systems, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 3, 2024

ABSTRACT Bio‐inspired computer‐aided diagnosis (CAD) has garnered significant attention in recent years due to the inherent advantages of bio‐inspired evolutionary algorithms (EAs) handling small datasets with elevated precision and reduced computational complexity. Traditional CAD models face limitations as they can only be developed post‐outbreak, relying on that become available during such events COVID‐19 pandemic. The scarcity data for emerging diseases poses a substantial challenge achieving conventional deep‐learning algorithms. Furthermore, even when are available, employing deep learning class‐based classification is arduous, necessitating model retraining, this paper, we propose novel hybrid algorithm leverages strengths crow search (CSA) spider monkey optimization (SMO) create an optimised (OSM‐CS) algorithm. We tool maps each input CT image high‐dimensional vector by extracting four categories features: high contrast, polynomial decomposition, textural, pixel statistics. proposed OSM‐CS employed feature selection method. Our experimental results demonstrate effectiveness algorithm, impressive accuracy 98.2% coupled AdaBoost classifier multi‐class 99.93% binary classification. This performance surpasses state‐of‐the‐art (SOTA) recently published algorithms, underscoring potential powerful realm CAD.

Language: Английский

Citations