SACM - United Kingdom
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9667
Browse
3 results
Search Results
Item Restricted Assessing artificial intelligence MRI autocontouring in Raystation and the AutoConfidence uncertainty model for brain radiotherapy(The University of Leeds, 2024-10) Alzahrani, Nouf; Henry, Ann; Nix, Michael; Murray, Louise; Al-qaisieh, BasharAbstract: Background: In radiotherapy, deep learning autosegmentation (DL-AS) and automation of quality assurance (QA) have the potential to efficiently standardize and enhance the quality of contours. Aim: To assess the performance of DL-AS in delineating organs-at-risk (OARs) in brain RT using the RayStation Treatment Planning System. Secondly, to build and test a novel artificial intelligence QA model called AutoConfidence (ACo). Methods: Retrospective MRI and CT cases were randomly selected for training and testing. DL-AS models were evaluated from geometric and dosimetric perspectives, focusing on the impact of pre-training editing. The ACo model was evaluated using two sources of autosegmentation: internal autosegmentations (IAS) produced from the ACo generator and two external DL-AS with different qualities (high and low quality) produced from RayStation models. Results: The edited DL-AS models generated more segmentations than the unedited models. Editing pituitary, orbits, optic nerves, lenses, and optic chiasm on MRI before training significantly improved at least one geometry metric. MRI-based DL-AS performed worse than CT-based in delineating the lacrimal gland, whereas the CT-based performed worse in delineating the optic chiasm. Except for the right orbit, when delineated using MRI models, the dosimetric statistical analysis revealed no superior model in terms of the dosimetric accuracy between the MR and CT DL-AS models. The number of patients where the clinical significance threshold was exceeded was higher for the optic chiasm D1% than for other OARs, for all models. ACo had excellent performance on both internal and external segmentations across all OARs (except lenses). Mathews Correlation Coefficient was higher on IAS and low-quality external segmentations than high-quality ones. Conclusion: MRI DL-AS in RT may improve consistency, quality, and efficiency but requires careful editing of training contours. ACo was a reliable predictor of uncertainty and errors on DL-AS, demonstrating its potential as an independent, reference-free QA tool.13 0Item Restricted The impact of risk and uncertainty on healthcare project delivery and its effect on intra-group conflict in the context of Saudi Arabia(The University of Manchester, 2024-07-25) Kheel, Metib Khalifa; Kirkham, RichardHealthcare construction projects are characterised by temporal risks and uncertainties, which may give rise to conflict. Decision-making within project teams is therefore an important focus of academic enquiry, particularly in a post-COVID-19 era, where healthcare projects play a crucial role in supporting pandemic recovery. Understanding the landscape that characterises projects in the healthcare setting could provide useful insights into broader project delivery issues and the effects of decision-making in situations of risk and uncertainty. This thesis describes a qualitative exploratory single case study situated within the King Faisal Specialist Hospital and Research Centre (KFSHRC) in the Kingdom of Saudi Arabia; semi-structured interviews provide an evidence base by which to understand the presence of risk, uncertainty, and intra-group conflict. The findings of this study identify the prevalence of conflict within project teams, exposing the detrimental effects of inconsistent decision-making. Moreover, the study uncovers how risk and uncertainty may directly impact decision-making processes and project delivery schedules, and thus contributing to the existing body of knowledge in the broader field of project studies. The findings illustrate the impacts of regulatory changes, supply chain disruptions, unexpected delays, and cost overruns. In order to moderate the effects of these impacts, the thesis offers recommendations for healthcare construction stakeholders, emphasising the development of robust mitigation strategies and contingency plans. These recommendations advocate for targeted training in project management, risk assessment, and crisis management. By embracing these measures, stakeholders may proactively manage the multifaceted challenges, thus enabling the successful completion of healthcare construction projects in the dynamic landscape of risk and uncertainty.17 0Item Restricted Creating value using Big Data applications in complex projects: a systematic review of the construction sector in a risk management perspective(Saudi Digital Library, 2023-09-04) Yamour, Jenaideb S; Qazi, KamalThe study delineates several key objectives: a comprehensive exploration of Big Data's integration in the sector; an assessment of its merits and challenges; a historical mapping of its evolution; and proffering trajectories for future scholarly and practical endeavours. It underscores the inherent inadequacy of conventional risk assessment tools, particularly for contemporary construction undertakings characterized by intricate designs and stringent timelines, emphasizing the revolutionary potential of Big Data in bolstering industry resilience and predictive prowess. The methodology underpinning this research is anchored in a systemic literature review, aiming to holistically encapsulate the extant body of knowledge on the subject. Pivotal inquiries driving this investigation include the value-addition of Big Data in construction risk management, and its interplay with project complexity. A methodological flowchart shows the research's steps. Key revelations from this investigation points up the reputation of Big Data-centric technologies in risk detection and mitigation throughout construction phases. Techniques like Monte Carlo simulations using Big Data, employing probabilistic assessments for diverse scenarios, have gained prominence. Furthermore, Building Information Modelling (BIM) leverages Big Data for enhanced design fidelity, minimizing design-associated risks. The research also highlights the potency of the MapReduce Hadoop programming paradigm in fortifying risk identification and management. The study also sheds light on Big Data's instrumental role in improving the occupational environment for construction personnel. Conclusively, the paper clarifies the expanding potential of Big Data in refining construction processes, risk mitigating, and bolstering the efficacy and foresight of project management. In essence, this review offers a holistic perspective on Big Data's role in the construction sector's risk management, enhancing existing literature through the discussion of contemporary frameworks. The insights garnered will undoubtedly prove invaluable to researchers and industry practitioners keen on refining risk management strategies through Big Data integrations29 0