Revista ANACEM., Год журнала: 2024, Номер 18(1), С. 11 - 13
Опубликована: Окт. 31, 2024
Desde la invención de rueda, pasando por creación imprenta y hasta el desarrollo teoría atómica, historia ha estado llena múltiples momentos que nos enseñan que, al momento del lanzamiento estos, humanidad pareciera nunca haber en facultad poder lidiar con ellos impacto estos podrían generar. El advenimiento las inteligencias artificiales (IA) no son excepción.
Radiotherapy and Oncology, Год журнала: 2024, Номер 201, С. 110542 - 110542
Опубликована: Сен. 17, 2024
Язык: Английский
Процитировано
8
Algorithms, Год журнала: 2024, Номер 17(10), С. 432 - 432
Опубликована: Сен. 27, 2024
The rapid advancement of artificial intelligence (AI) technology has catalyzed unprecedented innovation in the healthcare industry, transforming medical practices and patient care. However, this progress brings significant ethical challenges, highlighting need for a comprehensive exploration algorethics—the intersection algorithm design considerations. This study aimed to conduct narrative review reviews field algorethics with specific key questions. utilized standardized checklist reviews, including ANDJ Narrative Checklist, ensure thoroughness consistency. Searches were performed on PubMed, Scopus, Google Scholar. revealed growing emphasis integrating fairness, transparency, accountability into AI systems, alongside development. importance collaboration between different domains scientific production, such as social sciences standardization (like IEEE), development guidelines is significantly emphasized, demonstrated direct impact health domain. gaps persist, particularly lack evaluation methods challenges posed by complex sectors like healthcare. findings underscore robust data governance prevent biases highlight cross-disciplinary creating frameworks AI. important applications domain, there increase attention, focus addressing issues seeking both practical theoretical solutions. Future research should prioritize establishing AI, fostering interdisciplinary collaboration, developing sector-specific guidelines, exploring AI’s long-term societal impacts, enhancing training developers. Continued attention emerging standards also crucial aligning technologies evolving principles.
Язык: Английский
Процитировано
5
Cancers, Год журнала: 2024, Номер 16(17), С. 2988 - 2988
Опубликована: Авг. 28, 2024
In spinal oncology, integrating deep learning with computed tomography (CT) imaging has shown promise in enhancing diagnostic accuracy, treatment planning, and patient outcomes. This systematic review synthesizes evidence on artificial intelligence (AI) applications CT for tumors. A PRISMA-guided search identified 33 studies: 12 (36.4%) focused detecting malignancies, 11 (33.3%) classification, 6 (18.2%) prognostication, 3 (9.1%) 1 (3.0%) both detection classification. Of the classification studies, 7 (21.2%) used machine to distinguish between benign malignant lesions, evaluated tumor stage or grade, 2 (6.1%) employed radiomics biomarker Prognostic studies included three that predicted complications such as pathological fractures AI's potential improving workflow efficiency, aiding decision-making, reducing is discussed, along its limitations generalizability, interpretability, clinical integration. Future directions AI oncology are also explored. conclusion, while technologies promising, further research necessary validate their effectiveness optimize integration into routine practice.
Язык: Английский
Процитировано
3
Applied Radiation and Isotopes, Год журнала: 2025, Номер 220, С. 111718 - 111718
Опубликована: Фев. 20, 2025
Язык: Английский
Процитировано
0
Tomography, Год журнала: 2025, Номер 11(5), С. 51 - 51
Опубликована: Апрель 27, 2025
Objectives: To evaluate the medical image segmentation performance of monochromatic images in various energy levels. Methods: The low-density module (25 mm diameter, 6 Hounsfield Unit (HU) density difference from background) ACR464 phantom was scanned at both 10 mGy and 5 dose Virtual monoenergetic (VMIs) different levels 40, 50, 60, 68, 74, 100 keV were generated. reconstructed with 50% adaptive statistical iterative reconstruction veo (ASIR-V50%) used to train an model based on U-Net. evaluation set VMIs algorithms: FBP, ASIR-V50%, ASIR-V100%, deep learning (DLIR) low (DLIR-L), medium (DLIR-M), high (DLIR-H) strength U-Net employed as a tool compare algorithm performance. Image noise metrics, such DICE coefficient, intersection over union (IOU), sensitivity, Hausdorff distance, calculated assess quality Results: DLIR-M DLIR-H consistently achieved lower better performance, highest results observed 60 keV, had lowest across all including IOU, DICE, ranked descending order 68 50 74 40 keV. Specifically, average IOU values for each method 0.60 0.67 0.68 0.72 DLIR-L, 0.75 DLIR-M, DLIR-H. 0.75, 0.80, 0.82, 0.83, 0.85, 0.86. sensitivity 0.93, 0.91, 0.96, 0.95, 0.98, 0.98. Conclusions: For low-density, non-enhancing objects under dose, performed automatic segmentation. algorithms delivered best results, whereas provided sensitivity.
Язык: Английский
Процитировано
0
medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown
Опубликована: Май 13, 2024
Abstract Background/purpose The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack clinician trust AI models, underscoring the need for effective uncertainty quantification (UQ) methods. purpose this study was to scope existing literature related UQ RT, identify areas improvement, and determine future directions. Methods We followed PRISMA-ScR scoping review reporting guidelines. utilized population (human cancer patients), concept (utilization UQ), context (radiotherapy applications) framework structure our search screening process. conducted systematic spanning seven databases, supplemented by manual curation, up January 2024. Our yielded total 8980 articles initial review. Manuscript data extraction performed Covidence. Data categories included general characteristics, RT characteristics. Results identified 56 published from 2015-2024. 10 domains applications were represented; most studies evaluated auto-contouring (50%), image-synthesis (13%), multiple simultaneously (11%). 12 disease sites represented, with head neck being common site independent application space (32%). Imaging used 91% studies, while only 13% incorporated dose information. Most focused on failure detection as main (60%), Monte Carlo dropout commonly implemented method (32%) ensembling (16%). 55% did not share code or datasets. Conclusion revealed diversity beyond auto-contouring. Moreover, clear additional methods, such conformal prediction. results may incentivize development guidelines implementation RT.
Язык: Английский
Процитировано
1
Journal of Personalized Medicine, Год журнала: 2024, Номер 14(9), С. 963 - 963
Опубликована: Сен. 10, 2024
(Background) Over the years, there has been increasing interest in adopting a quality approach radiology, leading to strategic pursuit of specific and key performance indicators (KPIs). These radiology can have significant impacts ranging from radiation protection integration into digital healthcare. (Purpose) This study aimed conduct narrative review on (KPIs) with questions. (Methods) utilized standardized checklist for reviews, including ANDJ Narrative Checklist, ensure thoroughness consistency. Searches were performed PubMed, Scopus, Google Scholar using combination keywords related KPIs, Boolean logic refine results. From an initial yield 211 studies, 127 excluded due lack focus KPIs. The remaining 84 studies assessed clarity, design, methodology, 26 ultimately selected detailed review. evaluation process involved multiple assessors minimize bias rigorous analysis. (Results Discussion) overview highlights following: KPIs are crucial advancing by supporting evolution imaging technologies (e.g., CT, MRI) integrating emerging like AI AR/VR. They high standards diagnostic accuracy, image quality, operational efficiency, enhancing capabilities streamlining workflows. vital radiological safety, measuring adherence protocols that exposure protect patients. effective healthcare systems requires systematic development, validation, standardization, supported national international initiatives. Addressing challenges CAD-CAM technology home-based is essential. Developing specialized new will be continuous improvement patient care practices. (Conclusions) In conclusion, essential while future research should improving data access developing address challenges. Future expanding documentation sources, web search methods, establishing direct connections scientific associations.
Язык: Английский
Процитировано
1
Опубликована: Июнь 5, 2024
In this section, AI’s impact on medicine, specifically radiation treatment processes, is highlighted. AI in radiotherapy has led to significant innovations, enhancing the precision and efficiency of cancer treatments. Advanced algorithms enable automated more accurate tumor detection delineation imaging, optimizing dose distribution while minimizing exposure healthy tissues. AI-driven planning reduces time required for complex calculations improves personalized strategies. Machine learning models predict patient responses potential side effects, allowing proactive adjustments. Overall, revolutionizing by improving accuracy, reducing time, outcomes.
Язык: Английский
Процитировано
0
Revista ANACEM., Год журнала: 2024, Номер 18(1), С. 11 - 13
Опубликована: Окт. 31, 2024
Desde la invención de rueda, pasando por creación imprenta y hasta el desarrollo teoría atómica, historia ha estado llena múltiples momentos que nos enseñan que, al momento del lanzamiento estos, humanidad pareciera nunca haber en facultad poder lidiar con ellos impacto estos podrían generar. El advenimiento las inteligencias artificiales (IA) no son excepción.
Процитировано
0