A. Marey, Abdelrahman M. Saad, Benjamin D Killeen, Catalina Gomez, Mariia Tregubova, Mathias Unberath, Muhammad Umair
Cardiovascular disease (CVD) is a major cause of mortality worldwide, especially in resource-limited countries with limited access to healthcare resources. Early detection and accurate imaging are vital for managing CVD, emphasizing the significance of patient education. Generative AI, including algorithms to synthesize text, speech, images, and combinations thereof given a specific scenario or prompt, offer promising solutions for enhancing patient education. By combining vision and language models, generative AI enables personalized multimedia content generation through natural language interactions, benefiting patient education in cardiovascular imaging. Simulations, chat-based interactions, and voice-based interfaces can enhance accessibility, especially in resource-limited settings. Despite its potential benefits, implementing generative AI in resource-limited countries faces challenges like data quality, infrastructure limitations, and ethical considerations. Addressing these issues is crucial for successful adoption. Ethical challenges related to data privacy and accuracy must also be overcome to ensure better patient understanding, treatment adherence, and improved healthcare outcomes. Continued research, innovation, and collaboration in generative AI have the potential to revolutionize patient education. This can empower patients to make informed decisions about their cardiovascular health, ultimately improving healthcare outcomes in resource-limited settings.
{"title":"Gen-AI: Enhancing Patient Education in Cardiovascular Imaging","authors":"A. Marey, Abdelrahman M. Saad, Benjamin D Killeen, Catalina Gomez, Mariia Tregubova, Mathias Unberath, Muhammad Umair","doi":"10.1093/bjro/tzae018","DOIUrl":"https://doi.org/10.1093/bjro/tzae018","url":null,"abstract":"\u0000 Cardiovascular disease (CVD) is a major cause of mortality worldwide, especially in resource-limited countries with limited access to healthcare resources. Early detection and accurate imaging are vital for managing CVD, emphasizing the significance of patient education. Generative AI, including algorithms to synthesize text, speech, images, and combinations thereof given a specific scenario or prompt, offer promising solutions for enhancing patient education.\u0000 By combining vision and language models, generative AI enables personalized multimedia content generation through natural language interactions, benefiting patient education in cardiovascular imaging. Simulations, chat-based interactions, and voice-based interfaces can enhance accessibility, especially in resource-limited settings.\u0000 Despite its potential benefits, implementing generative AI in resource-limited countries faces challenges like data quality, infrastructure limitations, and ethical considerations. Addressing these issues is crucial for successful adoption. Ethical challenges related to data privacy and accuracy must also be overcome to ensure better patient understanding, treatment adherence, and improved healthcare outcomes.\u0000 Continued research, innovation, and collaboration in generative AI have the potential to revolutionize patient education. This can empower patients to make informed decisions about their cardiovascular health, ultimately improving healthcare outcomes in resource-limited settings.","PeriodicalId":516196,"journal":{"name":"BJR|Open","volume":" 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141831514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lucy Siew Chen Davies, L. Mchugh, Sally Falk, Jacqui Bridge, P. Fendall Amaro, L. Whiteside, Rachael Bailey, Julie Webb, Cynthia L Eccles
This paper is an evaluation of the current trial processes within a national proton beam therapy (PBT) clinical trial service in the UK. The work within the paper identifies priority challenges associated with the implementation of PBT trials with a view to improving patient trial processes. The nominal group technique (NGT) was used. Five Clinical Trials Radiographers were asked the target question “what are the major challenges when implementing PBT clinical trials and facilitating PBT trial-related activities?” Participants individually and silently listed their challenges to the target question. Following this, group discussion clarified and refined responses. Participants then individually selected five challenges that they deemed most pertinent to the target question, giving a weighted score (out of 10). Individual scores were combined to provide a ranked, weighted order of challenges. Further group discussion identified improvement strategies to the highest scored challenges. After combining lists generated by participants, 59 challenges were identified. Group discussion eliminated 27 responses. Eighteen were merged, resulting in 14 challenges. The two challenges that ranked highest were: i) lack of initial understanding of the responsibilities of teams and who the relevant stakeholders were, ii) that a national PBT service requires the provision of shared care across multi-disciplinary teams and sites. Improvement areas include the development of shared protocols, clarifying stakeholder responsibilities and improving communication between centres to streamline PBT trial processes. This work has identified priority areas requiring development to improve the conduct of a national PBT clinical trials programme. This is the first publication to evaluate current clinical trial processes for the UK’s PBT service.
{"title":"Clinical trials radiographers identifying priority challenges associated with implementing a national programme of clinical trials in the UK’s first proton beam therapy Centre","authors":"Lucy Siew Chen Davies, L. Mchugh, Sally Falk, Jacqui Bridge, P. Fendall Amaro, L. Whiteside, Rachael Bailey, Julie Webb, Cynthia L Eccles","doi":"10.1093/bjro/tzae012","DOIUrl":"https://doi.org/10.1093/bjro/tzae012","url":null,"abstract":"\u0000 \u0000 \u0000 This paper is an evaluation of the current trial processes within a national proton beam therapy (PBT) clinical trial service in the UK. The work within the paper identifies priority challenges associated with the implementation of PBT trials with a view to improving patient trial processes.\u0000 \u0000 \u0000 \u0000 The nominal group technique (NGT) was used. Five Clinical Trials Radiographers were asked the target question “what are the major challenges when implementing PBT clinical trials and facilitating PBT trial-related activities?” Participants individually and silently listed their challenges to the target question. Following this, group discussion clarified and refined responses. Participants then individually selected five challenges that they deemed most pertinent to the target question, giving a weighted score (out of 10). Individual scores were combined to provide a ranked, weighted order of challenges. Further group discussion identified improvement strategies to the highest scored challenges.\u0000 \u0000 \u0000 \u0000 After combining lists generated by participants, 59 challenges were identified. Group discussion eliminated 27 responses. Eighteen were merged, resulting in 14 challenges. The two challenges that ranked highest were: i) lack of initial understanding of the responsibilities of teams and who the relevant stakeholders were, ii) that a national PBT service requires the provision of shared care across multi-disciplinary teams and sites. Improvement areas include the development of shared protocols, clarifying stakeholder responsibilities and improving communication between centres to streamline PBT trial processes.\u0000 \u0000 \u0000 \u0000 This work has identified priority areas requiring development to improve the conduct of a national PBT clinical trials programme.\u0000 \u0000 \u0000 \u0000 This is the first publication to evaluate current clinical trial processes for the UK’s PBT service.\u0000","PeriodicalId":516196,"journal":{"name":"BJR|Open","volume":"11 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141105178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ola Kvist, Laura A. Santos, Francesca de Luca, Diego Jaramillo
“How tall will I be?” Every paediatrician has been asked this during their career. The growth plate is the main site of longitudinal growth of the long bones. The chondrocytes in the growth plate have a columnar pattern detectable by diffusion tensor imaging (DTI). DTI shows the diffusion of water in a tissue and whether it is iso- or anisotropic. By detecting direction and magnitude of diffusion, DTI gives information about the microstructure of the tissue. DTI metrics include tract volume, length, and number, fractional anisotropy (FA)and mean diffusivity. DTI metrics, particularly tract volume, provide quantitative data regarding skeletal growth and, in conjunction with the fractional anisotropy, be used to determine whether a growth plate is normal. Tractography is a visual display of the diffusion, depicting its direction and amplitude. Tractography gives a more qualitative visualization of cellular orientation in a tissue and reflects the activity in the growth plate. These two components of DTI can be used to assess the growth plate without ionizing radiation or pain. Further refinements in DTI will improve prediction of post-imaging growth and growth plate closure, and assessment of the positive and negative effect of treatments like cis-retinoic acid and growth hormone administration.
{"title":"Can diffusion tensor imaging unlock the secrets of the growth plate?","authors":"Ola Kvist, Laura A. Santos, Francesca de Luca, Diego Jaramillo","doi":"10.1093/bjro/tzae005","DOIUrl":"https://doi.org/10.1093/bjro/tzae005","url":null,"abstract":"\u0000 “How tall will I be?” Every paediatrician has been asked this during their career.\u0000 The growth plate is the main site of longitudinal growth of the long bones. The chondrocytes in the growth plate have a columnar pattern detectable by diffusion tensor imaging (DTI). DTI shows the diffusion of water in a tissue and whether it is iso- or anisotropic. By detecting direction and magnitude of diffusion, DTI gives information about the microstructure of the tissue. DTI metrics include tract volume, length, and number, fractional anisotropy (FA)and mean diffusivity. DTI metrics, particularly tract volume, provide quantitative data regarding skeletal growth and, in conjunction with the fractional anisotropy, be used to determine whether a growth plate is normal. Tractography is a visual display of the diffusion, depicting its direction and amplitude. Tractography gives a more qualitative visualization of cellular orientation in a tissue and reflects the activity in the growth plate. These two components of DTI can be used to assess the growth plate without ionizing radiation or pain. Further refinements in DTI will improve prediction of post-imaging growth and growth plate closure, and assessment of the positive and negative effect of treatments like cis-retinoic acid and growth hormone administration.","PeriodicalId":516196,"journal":{"name":"BJR|Open","volume":"1 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139962749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andrew D Weedall, A. Dallaway, John Hattersley, Michael Diokno, Charles E Hutchinson, Adrian J Wilson, S. Wayte
To investigate differences in diffusion tensor imaging (DTI) parameters and proton density fat fraction (PDFF) in the spinal muscles of younger and older adult males, Twelve younger (19-30years) and 12 older (61-81years) healthy, physically active male participants underwent T1W, T2W, Dixon and Diffusion Tensor imaging of the lumbar spine. The eigenvalues (λ1, λ2, λ3) fractional anisotropy (FA) and mean diffusivity (MD) from the DTI together with the PDFF were determined in the multifidus (MF), medial and lateral erector spinae (ESmed, ESlat) and quadratus lumborum (QL) muscles. A two-way ANOVA was used to investigate differences with age and muscle and t-tests for differences in individual muscles with age. The ANOVA gave significant differences with age for all DTI parameters and the PDFF (p < 0.01) and with muscle (p < 0.01) for all DTI parameters except for λ1 and for the PDFF. The mean of the eigenvalues and MD were lower and the FA higher in the older age group with differences reaching statistical significance for all DTI measures for ESlat and QL (p < 0.01) but only in ESmed for λ3 and MD (p < 0.05). Differences in DTI parameters of muscle with age result from changes in both in the intra- and extra-cellular space and cannot be uniquely explained in terms of fibre length and diameter. Previous studies looking at age have used small groups with uneven age spacing. Our study uses two well defined and separated age groups.
{"title":"Changes in lumbar muscle diffusion tensor indices with age","authors":"Andrew D Weedall, A. Dallaway, John Hattersley, Michael Diokno, Charles E Hutchinson, Adrian J Wilson, S. Wayte","doi":"10.1093/bjro/tzae002","DOIUrl":"https://doi.org/10.1093/bjro/tzae002","url":null,"abstract":"\u0000 \u0000 \u0000 To investigate differences in diffusion tensor imaging (DTI) parameters and proton density fat fraction (PDFF) in the spinal muscles of younger and older adult males,\u0000 \u0000 \u0000 \u0000 Twelve younger (19-30years) and 12 older (61-81years) healthy, physically active male participants underwent T1W, T2W, Dixon and Diffusion Tensor imaging of the lumbar spine. The eigenvalues (λ1, λ2, λ3) fractional anisotropy (FA) and mean diffusivity (MD) from the DTI together with the PDFF were determined in the multifidus (MF), medial and lateral erector spinae (ESmed, ESlat) and quadratus lumborum (QL) muscles. A two-way ANOVA was used to investigate differences with age and muscle and t-tests for differences in individual muscles with age.\u0000 \u0000 \u0000 \u0000 The ANOVA gave significant differences with age for all DTI parameters and the PDFF (p < 0.01) and with muscle (p < 0.01) for all DTI parameters except for λ1 and for the PDFF. The mean of the eigenvalues and MD were lower and the FA higher in the older age group with differences reaching statistical significance for all DTI measures for ESlat and QL (p < 0.01) but only in ESmed for λ3 and MD (p < 0.05).\u0000 \u0000 \u0000 \u0000 Differences in DTI parameters of muscle with age result from changes in both in the intra- and extra-cellular space and cannot be uniquely explained in terms of fibre length and diameter.\u0000 \u0000 \u0000 \u0000 Previous studies looking at age have used small groups with uneven age spacing. Our study uses two well defined and separated age groups.\u0000","PeriodicalId":516196,"journal":{"name":"BJR|Open","volume":"24 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139530606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lasse Hokkinen, T. Mäkelä, Sauli Savolainen, M. Kangasniemi
Computed tomography angiography (CTA)-based machine learning methods for infarct volume estimation have shown a tendency to overestimate infarct core and final infarct volumes (FIV). Our aim was to assess factors influencing the reliability of these methods. The effect of collateral circulation on the correlation between convolutional neural network (CNN) estimations and FIV was assessed based on the Miteff system and hypoperfusion intensity ratio (HIR) in 121 patients with anterior circulation acute ischemic stroke (AIS) using Pearson correlation coefficients and median volumes. Correlation was also assessed between successful and futile thrombectomies. The timing of individual CTAs in relation to CTP studies was analysed. The strength of correlation between CNN estimated volumes and FIV did not change significantly depending on collateral status as assessed with the Miteff system or HIR, being poor to moderate (r = 0.09–0.50). The strongest correlation was found in patients with futile thrombectomies (r = 0.61). Median CNN estimates showed a trend for overestimation compared to FIVs. CTA was acquired in the mid arterial phase in virtually all patients (120/121). This study showed no effect of collateral status on the reliability of the CNN and best correlation was found in patients with futile thrombectomies. CTA timing in the mid arterial phase in virtually all patients can explain infarct volume overestimation. CTA timing seems to be the most important factor influencing the reliability of current CTA-based machine learning methods, emphasizing the need for CTA protocol optimization for infarct core estimation.
{"title":"Factors influencing the reliability of a computed tomography angiography-based deep learning method for infarct volume estimation","authors":"Lasse Hokkinen, T. Mäkelä, Sauli Savolainen, M. Kangasniemi","doi":"10.1093/bjro/tzae001","DOIUrl":"https://doi.org/10.1093/bjro/tzae001","url":null,"abstract":"\u0000 \u0000 \u0000 Computed tomography angiography (CTA)-based machine learning methods for infarct volume estimation have shown a tendency to overestimate infarct core and final infarct volumes (FIV). Our aim was to assess factors influencing the reliability of these methods.\u0000 \u0000 \u0000 \u0000 The effect of collateral circulation on the correlation between convolutional neural network (CNN) estimations and FIV was assessed based on the Miteff system and hypoperfusion intensity ratio (HIR) in 121 patients with anterior circulation acute ischemic stroke (AIS) using Pearson correlation coefficients and median volumes. Correlation was also assessed between successful and futile thrombectomies. The timing of individual CTAs in relation to CTP studies was analysed.\u0000 \u0000 \u0000 \u0000 The strength of correlation between CNN estimated volumes and FIV did not change significantly depending on collateral status as assessed with the Miteff system or HIR, being poor to moderate (r = 0.09–0.50). The strongest correlation was found in patients with futile thrombectomies (r = 0.61). Median CNN estimates showed a trend for overestimation compared to FIVs. CTA was acquired in the mid arterial phase in virtually all patients (120/121).\u0000 \u0000 \u0000 \u0000 This study showed no effect of collateral status on the reliability of the CNN and best correlation was found in patients with futile thrombectomies. CTA timing in the mid arterial phase in virtually all patients can explain infarct volume overestimation.\u0000 \u0000 \u0000 \u0000 CTA timing seems to be the most important factor influencing the reliability of current CTA-based machine learning methods, emphasizing the need for CTA protocol optimization for infarct core estimation.\u0000","PeriodicalId":516196,"journal":{"name":"BJR|Open","volume":"14 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139396066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：