Assessing Patient Health Dynamics by Comparative CT Analysis: An Automatic Approach to Organ and Body Feature Evaluation DOI Creative Commons
Dominik Müller, Jakob Voran, M.M.A. de Macedo

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2760 - 2760

Published: Dec. 8, 2024

Background/Objectives: The integration of machine learning into the domain radiomics has revolutionized approach to personalized medicine, particularly in oncology. Our research presents RadTA (RADiomics Trend Analysis), a novel framework developed facilitate automatic analysis quantitative imaging biomarkers (QIBs) from time-series CT volumes. Methods: is designed bridge technical gap for medical experts and enable sophisticated radiomic analyses without deep expertise. core includes an automated command line interface, streamlined image segmentation, comprehensive feature extraction, robust evaluation mechanisms. utilizes advanced segmentation models, specifically TotalSegmentator Body Composition Analysis (BCA), accurately delineate anatomical structures scans. These models extraction wide variety features, which are subsequently processed compared assess health dynamics across timely corresponding series. Results: effectiveness was tested using HNSCC-3DCT-RT dataset, scans oncological patients undergoing radiation therapy. results demonstrate significant changes tissue composition provide insights physical effects treatment. Conclusions: demonstrates step clinical adoption field radiomics, offering user-friendly, robust, effective tool patient dynamics. It can potentially also be used other specialties.

Language: Английский

Challenges and limitations in applying radiomics to PET imaging: Possible opportunities and avenues for research DOI Creative Commons
Alessandro Stefano

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 179, P. 108827 - 108827

Published: July 3, 2024

Radiomics, the high-throughput extraction of quantitative imaging features from medical images, holds immense potential for advancing precision medicine in oncology and beyond. While radiomics applied to positron emission tomography (PET) offers unique insights into tumor biology treatment response, it is imperative elucidate challenges constraints inherent this domain facilitate their translation clinical practice. This review examines limitations applying PET imaging, synthesizing findings last five years (2019-2023) highlights significance addressing these realize full molecular imaging. A comprehensive search was conducted across multiple electronic databases, including PubMed, Scopus, Web Science, using keywords relevant issues Only studies published peer-reviewed journals were eligible inclusion review. Although many have highlighted predicting assessing heterogeneity, enabling risk stratification, personalized therapy selection, various regarding practical implementation proposed models still need be addressed. illustrates cancer types, encompassing both phantom investigations. The analyzed highlight importance reproducible segmentation methods, standardized pre-processing post-processing methodologies, create large multicenter registered a centralized database promote continuous validation integration

Language: Английский

Citations

17
Integrating ChatGPT, Bard, and leading-edge generative artificial intelligence in architectural design and engineering: applications, framework, and challenges DOI

Nitin Rane,

Saurabh Choudhary, Jayesh Rane

et al.

SSRN Electronic Journal, Journal Year: 2023, Volume and Issue: unknown

Published: Jan. 1, 2023

This research paper delves into the integration of advanced generative artificial intelligence (AI) models, such as ChatGPT, Bard, and similar architectures, within realms architectural design engineering. The comprehensive study explores various aspects, including applications, frameworks, challenges, prospective developments in context In domain design, investigates transformative impact on Architectural Theory, highlighting how AI fosters creativity innovation thinking. Design Process is scrutinized, showcasing models streamline ideation, iteration, collaboration among teams. role Representation Visualization explored, emphasizing its capacity to generate immersive realistic visualizations. Furthermore, examines influence Interior Design, Urban Planning, considers nuanced aspects Cultural Social factors, elucidating these technologies contribute inclusive context-sensitive practices. Within realm engineering, assesses Structural Engineering, demonstrating potential optimize innovate structural analysis designs for enhanced safety efficiency. It applications Building Systems Construction Management, illustrating can project workflows resource allocation. compliance with Codes Regulations analyzed, error reduction adherence standards. Additionally, probes Materials Technology, advancements material selection construction methodologies. also promoting Sustainability Environmental energy efficiency, reduce environmental impact, enhance overall sustainability. While presenting critically evaluates challenges posed by integrating domains, ethical considerations, bias mitigation, user adaptability. Finally, it outlines future directions development, necessity interdisciplinary collaboration, guidelines, ongoing fully harness shaping

Language: Английский

Citations

20
Integrating ChatGPT, Bard, and Leading-Edge Generative Artificial Intelligence in Architectural Design and Engineering: Applications, Framework, and Challenges DOI Open Access
Nitin Liladhar Rane,

Saurabh P. Choudhary,

Jayesh Rane

et al.

International Journal of Architecture and Planning, Journal Year: 2023, Volume and Issue: 3(2), P. 92 - 124

Published: Sept. 5, 2023

This research paper investigates the integration of advanced generative artificial intelligence (AI) models, such as ChatGPT, Bard, and similar architectures, in architectural design engineering.The comprehensive study explores various aspects, including applications, frameworks, challenges, prospective developments context engineering.In design, transformative impact on Architectural Theory, highlighting how AI fosters creativity innovation thinking.The Design Process is scrutinized, showcasing models streamline ideation, iteration, collaboration among teams.Furthermore, examines influence Interior Design, Urban Planning, considers nuanced aspects Cultural Social factors, elucidating these technologies contribute to inclusive context-sensitive practices.In engineering, assesses Structural Engineering, demonstrating its potential optimize innovate structural analysis designs for enhanced safety efficiency.It applications Building Systems Construction Management, illustrating can project workflows resource allocation.The compliance with Codes Regulations analyzed, emphasizing error reduction adherence standards.Additionally, probes into Materials Technology, advancements material selection construction methodologies.The also role promoting Sustainability Environmental energy efficiency, reduce environmental impact, enhance overall sustainability.Finally, outlines challenges future directions development fully harness shaping engineering.

Language: Английский

Citations

11
MRI and CT radiomics for the diagnosis of acute pancreatitis DOI

Caterina Tartari,

Fabio Ramos Poroes, Sabine Schmidt

et al.

European Journal of Radiology Open, Journal Year: 2025, Volume and Issue: 14, P. 100636 - 100636

Published: Jan. 31, 2025

Language: Английский

Citations

0
Making sense of radiomics: insights on human–AI collaboration in medical interaction from an observational user study DOI Creative Commons
Jakub Mlynář, Adrien Depeursinge, John O. Prior

et al.

Frontiers in Communication, Journal Year: 2024, Volume and Issue: 8

Published: Feb. 12, 2024

Technologies based on “artificial intelligence” (AI) are transforming every part of our society, including healthcare and medical institutions. An example this trend is the novel field in oncology radiology called radiomics, which extracting mining large-scale quantitative features from imaging by machine-learning (ML) algorithms. This paper explores situated work with a radiomics software platform, QuantImage (v2), interaction around it, educationally framed hands-on trial sessions where pairs novice users (physicians technicians) task consisting developing predictive ML model co-present tutor. Informed ethnomethodology conversation analysis (EM/CA), results show that learning about more generally how to use platform specifically deeply intertwined. Common-sense knowledge (e.g., meanings colors) can interfere visual representation standards established professional domain. Participants' skills using routinely displayed assessment performance measures resulting models, monitoring platform's pace operation for possible problems, ascribing independent actions related algorithms) platform. The findings relevant current discussions explainability AI medicine as well issues machinic agency.

Language: Английский

Citations

3
Reproducibility of lung cancer radiomics features extracted from data-driven respiratory gating and free-breathing flow imaging in [18F]-FDG PET/CT DOI Creative Commons
Daphné Faist, Mario Jreige, Valentin Oreiller

et al.

European Journal of Hybrid Imaging, Journal Year: 2022, Volume and Issue: 6(1)

Published: Oct. 29, 2022

Abstract Background Quality and reproducibility of radiomics studies are essential requirements for the standardisation models. As recent data-driven respiratory gating (DDG) [ 18 F]-FDG has shown superior diagnostic performance in lung cancer, we evaluated impact DDG on features derived from PET/CT comparison to free-breathing flow (FB) imaging. Methods Twenty four nodules 20 patients were delineated. Radiomics FB corresponding reconstruction using QuantImage v2 platform. Lin’s concordance factor ( C b ) mean difference percentage (DIFF%) calculated each feature delineated which also classified by anatomical localisation volume. Non-reproducible defined as having a bias correction < 0 . 8 and/or DIFF% > 10. Results In total 141 computed analysis, 10 non-reproducible all pulmonary lesions. Those first-order Laplacian Gaussian (LoG)-filtered images (sigma = 1 mm): Energy, Kurtosis, Minimum, Range, Root Mean Squared, Skewness Variance; Texture Gray Level Cooccurence Matrix (GLCM): Cluster Prominence Difference First-order Standardised Uptake Value (SUV) feature: Kurtosis. Pulmonary lesions located lobes had only stable features, ones lower parts 25 features. with greater size (defined long axis length median) showed higher (9 features) than smaller (20 features). Conclusion Calculated lesions, 131 out can be used interchangeably between acquisitions. inferior subject variability well size.

Language: Английский

Citations

7
The Impact and Integration of Cloud Computing for Enhanced Patient Care and Operational Efficiency DOI

M. Prabu,

M. Diviya,

R. Bhuvaneswari

et al.

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 277 - 299

Published: June 21, 2024

Cloud computing is reshaping healthcare by offering a flexible solution for stakeholders to access data remotely. It revolutionizes creation, storage, and sharing, enabling professionals patient information from anywhere, enhancing care streamlining operations. Adoption increasing due its efficiency innovation benefits. Services like SaaS, PaaS, IaaS offer flexibility, driving adoption. Challenges include breaches, necessitating robust security measures. Despite challenges, cloud has transformed healthcare, improving decision-making, security, record automation. During COVID-19, it been crucial, highlighting importance in advancing healthcare. Providers must embrace technology potential enhance medical analysis improve services.

Language: Английский

Citations

0
Assessing Patient Health Dynamics by Comparative CT Analysis: An Automatic Approach to Organ and Body Feature Evaluation DOI Creative Commons
Dominik Müller, Jakob Voran, M.M.A. de Macedo

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2760 - 2760

Published: Dec. 8, 2024

Background/Objectives: The integration of machine learning into the domain radiomics has revolutionized approach to personalized medicine, particularly in oncology. Our research presents RadTA (RADiomics Trend Analysis), a novel framework developed facilitate automatic analysis quantitative imaging biomarkers (QIBs) from time-series CT volumes. Methods: is designed bridge technical gap for medical experts and enable sophisticated radiomic analyses without deep expertise. core includes an automated command line interface, streamlined image segmentation, comprehensive feature extraction, robust evaluation mechanisms. utilizes advanced segmentation models, specifically TotalSegmentator Body Composition Analysis (BCA), accurately delineate anatomical structures scans. These models extraction wide variety features, which are subsequently processed compared assess health dynamics across timely corresponding series. Results: effectiveness was tested using HNSCC-3DCT-RT dataset, scans oncological patients undergoing radiation therapy. results demonstrate significant changes tissue composition provide insights physical effects treatment. Conclusions: demonstrates step clinical adoption field radiomics, offering user-friendly, robust, effective tool patient dynamics. It can potentially also be used other specialties.

Language: Английский

Citations

0