Ultrasound Quarterly, Год журнала: 2024, Номер 40(2), С. 93 - 97
Опубликована: Май 3, 2024
From the Department of Radiology, University Kentucky, Lexington, KY. Address correspondence to: Adrian Dawkins, MD, 800 Rose Street, KY 40536-0293 (e-mail: [email protected]). The authors declare no conflict interest.
Язык: Английский
International Journal of Management & Entrepreneurship Research, Год журнала: 2024, Номер 6(1), С. 200 - 215
Опубликована: Янв. 25, 2024
In the rapidly evolving landscape of entrepreneurship, integration Artificial Intelligence (AI) has emerged as a transformative force, reshaping traditional business paradigms and offering unprecedented opportunities for success. This paper provides comprehensive critical review AI-driven strategies employed by entrepreneurs to enhance their ventures. The encompasses thorough analysis key AI applications, impact on various aspects potential benefits challenges associated with implementation. first section explores role in market analysis, highlighting how advanced data analytics predictive modelling contribute informed decision-making forecasting. discussion then extends innovations product development, emphasizing acceleration ideation, prototyping, customization through machine learning algorithms. Next, scrutinizes influence customer engagement relationship management. It delves into personalized experiences facilitated chatbots, recommendation systems, sentiment while also addressing ethical considerations surrounding privacy algorithmic biases. Entrepreneurial operations efficiency gains are examined subsequent section, AI's supply chain management, logistics, resource optimization. underscores increased productivity cost-effectiveness implementation AI-powered automation smart systems. Despite myriad advantages, critically examines such concerns, job displacement, digital divide. emphasizes need balanced approach that addresses societal adoption fostering inclusive entrepreneurial ecosystems. conclusion, this not only overview current entrepreneurship but offers insights future developments challenges. Entrepreneurs, policymakers, researchers can leverage navigate intersection sustainable ethically sound environment success era. Keywords: (AI), Entrepreneurship, Strategic Implementation, Innovation, Market Analysis, Predictive Modelling.
Язык: Английский
Процитировано
61
Bioengineering, Год журнала: 2025, Номер 12(3), С. 288 - 288
Опубликована: Март 13, 2025
The integration of artificial intelligence (AI) into ultrasound medicine has revolutionized medical imaging, enhancing diagnostic accuracy and clinical workflows. This review focuses on the applications, challenges, future directions AI technologies, particularly machine learning (ML) its subset, deep (DL), in diagnostics. By leveraging advanced algorithms such as convolutional neural networks (CNNs), significantly improved image acquisition, quality assessment, objective disease diagnosis. AI-driven solutions now facilitate automated analysis, intelligent assistance, education, enabling precise lesion detection across various organs while reducing physician workload. AI’s error capabilities further enhance accuracy. Looking ahead, with is expected to deepen, promoting trends standardization, personalized treatment, healthcare, underserved areas. Despite potential, comprehensive assessments ethical implications remain limited, necessitating rigorous evaluations ensure effectiveness practice. provides a systematic evaluation technologies medicine, highlighting their transformative potential improve global healthcare outcomes.
Язык: Английский
Процитировано
1
Scientific Reports, Год журнала: 2024, Номер 14(1)
Опубликована: Март 9, 2024
Abstract This study aimed to develop a deep learning model assess the quality of fetal echocardiography and perform prospective clinical validation. The was trained on data from 18–22-week anomaly scan conducted in seven hospitals 2008 2018. Prospective validation involved 100 patients two hospitals. A total 5363 images 2551 pregnancies were used for training model's segmentation accuracy depended image measured by score (QS). It achieved an overall average 0.91 (SD 0.09) across test set, with having above-average QS scoring 0.97 0.03). During 192 images, clinicians rated 44.8% 9.8) as equal quality, 18.69% 5.7) favoring auto-captured 36.51% 9.0) preferring manually captured ones. Images above showed better agreement segmentations ( p < 0.001) medicine experts. Auto-capture saved additional planes beyond protocol requirements, resulting more comprehensive echocardiographies. Low had adverse effect both performance clinician’s feedback. findings highlight importance developing evaluating AI models based ‘noisy’ real-life rather than pursuing highest possible retrospective academic-grade data.
Язык: Английский
Процитировано
9
Computers in Biology and Medicine, Год журнала: 2024, Номер 175, С. 108501 - 108501
Опубликована: Апрель 22, 2024
Язык: Английский
Процитировано
8
Scientific Data, Год журнала: 2024, Номер 11(1)
Опубликована: Май 2, 2024
Abstract During the process of labor, intrapartum transperineal ultrasound examination serves as a valuable tool, allowing direct observation relative positional relationship between pubic symphysis and fetal head (PSFH). Accurate assessment descent prediction most suitable mode delivery heavily rely on this relationship. However, achieving an objective quantitative interpretation images necessitates precise PSFH segmentation (PSFHS), task that is both time-consuming demanding. Integrating potential artificial intelligence (AI) in field medical image segmentation, development evaluation AI-based models significantly access to comprehensive meticulously annotated datasets. Unfortunately, publicly accessible datasets tailored for PSFHS are notably scarce. Bridging critical gap, we introduce dataset comprising 1358 images, at pixel level. The annotation adhered standardized protocols involved collaboration among experts. Remarkably, stands expansive resource date.
Язык: Английский
Процитировано
8
Anesthesia & Analgesia, Год журнала: 2023, Номер 137(4), С. 830 - 840
Опубликована: Сен. 5, 2023
Machine vision describes the use of artificial intelligence to interpret, analyze, and derive predictions from image or video data. vision–based techniques are already in clinical radiology, ophthalmology, dermatology, where some applications currently equal exceed performance specialty physicians areas interpretation. While machine anesthesia has many potential applications, its development remains infancy our specialty. Early research for focused on automated recognition anatomical structures during ultrasound-guided regional line insertion; glottic opening vocal cords laryngoscopy; prediction difficult airway using facial images; alerts endobronchial intubation detected chest radiograph. Current measuring distance between endotracheal tube tip carina have demonstrated noninferior compared board-certified physicians. The uses will only grow with advancement underlying algorithm technical developed outside medicine, such as convolutional neural networks transfer learning. This article summarizes recently published works interest, provides a brief overview used create explains frequently terms, discusses challenges encounter we embrace advantages that this technology may bring future practice patient care. As emerges onto stage, it is critically important anesthesiologists prepared confidently assess which these devices safe, appropriate, added value
Язык: Английский
Процитировано
14
Journal of Ultrasound in Medicine, Год журнала: 2024, Номер 43(5), С. 881 - 897
Опубликована: Янв. 26, 2024
The goal of this work was to develop robust techniques for the processing and identification SUA using artificial intelligence (AI) image classification models.
Язык: Английский
Процитировано
4
Frontiers in Medical Technology, Год журнала: 2024, Номер 6
Опубликована: Май 30, 2024
EDITORIAL article Front. Med. Technol., 30 May 2024Sec. Medtech Data Analytics Volume 6 - 2024 | https://doi.org/10.3389/fmedt.2024.1372358
Язык: Английский
Процитировано
3
Scientific Reports, Год журнала: 2024, Номер 14(1)
Опубликована: Июль 3, 2024
Abstract Providing adequate counseling on mode of delivery after induction labor (IOL) is utmost importance. Various AI algorithms have been developed for this purpose, but rely maternal–fetal data, not including ultrasound (US) imaging. We used retrospectively collected clinical data from 808 subjects submitted to IOL, totaling 2024 US images, train models predict vaginal (VD) and cesarean section (CS) outcomes IOL. The best overall model only (F1-score: 0.736; positive predictive value (PPV): 0.734). imaging employed fetal head, abdomen femur showing limited discriminative results. images 0.594; PPV: 0.580). Consequently, we constructed ensemble test whether could enhance the model. included 0.689; 0.693), presenting a false negative interesting trade-off. accurately predicted CS 4 additional cases, despite misclassifying 20 VD, resulting in 6.0% decrease average accuracy compared Hence, integrating into latter can be new development assisting counseling.
Язык: Английский
Процитировано
3
Quality in Sport, Год журнала: 2025, Номер 37, С. 57301 - 57301
Опубликована: Янв. 14, 2025
Introduction and objective: Breast cancer is the most diagnosed second leading cause of deaths in women globally, with rising cases mortality. Early detection via mammography, ultrasound, or MRI vital, ultrasound excelling dense breast tissue due to its safety accuracy.Review methods: A literature review utilizing databases like Scopus, Google Scholar, PubMed, keywords such as "AI use radiology" "BI-RADS scale" underscores need for advancements understanding managing graft rejection.Brief knowledge status: AI develops systems that simulate human intelligence, imaging by detecting patterns providing accurate results. Machine learning (ML) deep (DL) drive advances, DL's CNNs image analysis. aids BI-RADS lesion classification, detection, lymph node analysis, treatment response prediction, often surpassing radiologists. Its future relies on real-world validation, improved outcomes, clinical integration.Discussion: The integration artificial intelligence (AI) into marks a transformative leap diagnostic radiology, enhancing precision, efficiency, scalability. Driven machine (DL), excels analyzing complex datasets. However, adoption requires addressing key considerations nuanced approach.Summary: In conclusion, holds immense promise imaging, poised redefine field through enhanced capabilities utility. Continued validation efforts will ensure broader acceptance sustained impact medical imaging.
Язык: Английский
Процитировано
0