Radiography最新文献_第3页

Radiomics evaluation for the early detection of Alzheimer's dementia using T1-weighted MRI 利用 T1 加权磁共振成像对早期检测阿尔茨海默氏症痴呆症的放射组学评估。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.06.016

Introduction

Alzheimer's disease (AD), the most common cause of dementia, presents a global health crisis with its prevalence expected to triple worldwide by 2050, emphasizing the urgent need for early diagnosis to delay progression and improve patient quality of life. Our project aims to detect AD in its early phase by identifying subtle neuroanatomical changes with Radiomics features, offering a more accurate diagnosis.

Methods

The AssemblyNet segmentation model was used to analyze brain changes by employing anonymized T1 MRI scans from 416 patients. For each segmented label we extracted Radiomic features. After preprocessing of Radiomic features we trained four models, Gradient Booster, Random Forest, Support Vector Classifier, and XGBoost, in a 70%/20%/10% train, validation and test split. All models were hyperparameter tuned with GridSearch, Cross validation and evaluated with accuracy on the test data.

Results

208 T1-weighted MRI scans were segmented, with 132 segmentation labels per patient, 1130 Radiomic features per segmentation, totalling in over 31 million features. For all four models we achieved accuracies between 0.71 and 0.86, and the machine learning model with highest accuracy were XGBoost, achieving an accuracy at 0.86 on the segmentation of the left inferior lateral ventricle.

Conclusion

Our study's use of segmentation on T1-weighted MRI scans resulted promising accuracies for early AD diagnosis with the machine learning model XGBoost, peaking at 0.86 accuracy. Future research should aim to expand datasets and refine methodologies for broader applicability.

Implication for practice

Implementing Radiomics for early AD detection using T1-weighted MRI scans could substantially improve diagnostic accuracy, enabling earlier interventions that may delay disease progression and improve outcomes, thereby requiring radiographers to adopt more advanced imaging techniques and analysis tools, as well as additional training to effectively interpret complex Radiomic data.

导言：阿尔茨海默病（AD）是导致痴呆症的最常见病因，是一种全球性健康危机，预计到 2050 年全球发病率将增加两倍，因此迫切需要早期诊断以延缓病情发展并改善患者的生活质量。我们的项目旨在通过放射组学特征识别细微的神经解剖学变化，在早期阶段检测出痴呆症，从而提供更准确的诊断：方法：我们采用 AssemblyNet 分割模型，利用 416 名患者的匿名 T1 MRI 扫描图像分析大脑变化。对于每个分割标签，我们都提取了辐射组学特征。在对 Radiomic 特征进行预处理后，我们以 70%/20%/10% 的训练、验证和测试比例对梯度助推器、随机森林、支持向量分类器和 XGBoost 四种模型进行了训练。结果：我们对 208 个 T1 加权核磁共振成像扫描进行了分割，每个患者有 132 个分割标签，每个分割有 1130 个 Radiomic 特征，总计超过 3100 万个特征。所有四种模型的准确率都在 0.71 到 0.86 之间，其中准确率最高的机器学习模型是 XGBoost，对左下侧脑室的分割准确率达到了 0.86：结论：我们的研究利用T1加权核磁共振成像扫描进行分割，结果发现机器学习模型XGBoost对早期AD诊断的准确率很高，最高准确率达到0.86。未来的研究应着眼于扩大数据集和完善方法，以实现更广泛的适用性：对实践的启示：使用T1加权核磁共振成像扫描进行早期AD检测的放射组学可大幅提高诊断准确性，从而实现早期干预，延缓疾病进展并改善预后，因此需要放射技师采用更先进的成像技术和分析工具，并接受额外培训，以有效解读复杂的放射组学数据。

{"title":"Radiomics evaluation for the early detection of Alzheimer's dementia using T1-weighted MRI","authors":"","doi":"10.1016/j.radi.2024.06.016","DOIUrl":"10.1016/j.radi.2024.06.016","url":null,"abstract":"<div><h3>Introduction</h3><p>Alzheimer's disease (AD), the most common cause of dementia, presents a global health crisis with its prevalence expected to triple worldwide by 2050, emphasizing the urgent need for early diagnosis to delay progression and improve patient quality of life. Our project aims to detect AD in its early phase by identifying subtle neuroanatomical changes with Radiomics features, offering a more accurate diagnosis.</p></div><div><h3>Methods</h3><p>The AssemblyNet segmentation model was used to analyze brain changes by employing anonymized T1 MRI scans from 416 patients. For each segmented label we extracted Radiomic features. After preprocessing of Radiomic features we trained four models, Gradient Booster, Random Forest, Support Vector Classifier, and XGBoost, in a 70%/20%/10% train, validation and test split. All models were hyperparameter tuned with GridSearch, Cross validation and evaluated with accuracy on the test data.</p></div><div><h3>Results</h3><p>208 T1-weighted MRI scans were segmented, with 132 segmentation labels per patient, 1130 Radiomic features per segmentation, totalling in over 31 million features. For all four models we achieved accuracies between 0.71 and 0.86, and the machine learning model with highest accuracy were XGBoost, achieving an accuracy at 0.86 on the segmentation of the left inferior lateral ventricle.</p></div><div><h3>Conclusion</h3><p>Our study's use of segmentation on T1-weighted MRI scans resulted promising accuracies for early AD diagnosis with the machine learning model XGBoost, peaking at 0.86 accuracy. Future research should aim to expand datasets and refine methodologies for broader applicability.</p></div><div><h3>Implication for practice</h3><p>Implementing Radiomics for early AD detection using T1-weighted MRI scans could substantially improve diagnostic accuracy, enabling earlier interventions that may delay disease progression and improve outcomes, thereby requiring radiographers to adopt more advanced imaging techniques and analysis tools, as well as additional training to effectively interpret complex Radiomic data.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1078817424001640/pdfft?md5=770f385230dd5d196634d5d9df5cb5c2&pid=1-s2.0-S1078817424001640-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141471566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A systematic review and meta-analysis of correlation of automated breast density measurement 自动乳腺密度测量相关性的系统回顾和荟萃分析。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.08.003

Introduction

Breast cancer is the most common cancer in women and a leading cause of mortality. This systematic review and meta-analysis aims to evaluate the correlation between breast density measurements obtained from various software and visual assessments by radiologists using full-field digital mammography (FFDM).

Methods

Following the PRISMA 2020 guidelines, five databases (Pubmed, Google Scholar, Science Direct, Cochrane Library, and MEDLINE) were searched for studies correlating volumetric breast density with breast cancer risk. The Newcastle–Ottawa Scale and the Joanna Briggs Institute Checklist were used to assess the quality of the included studies. Meta-analysis of correlation was applied to aggregate correlation coefficients using a random-effects model using MedCalc Statistical Software version 19.2.6.

Results

The review included 22 studies with a total of 58,491 women. The pooled correlation coefficient for volumetric breast density amongst Volpara™ and Quantra™ was found to be 0.755 (95% CI 0.496–0.890, p < 0.001), indicating a high positive correlation, albeit with a significant heterogeneity (I² = 99.89%, p < 0.0001). Subgroup analyses based on study origin, quality, and methodology were performed but did not reveal the heterogeneity cause. Egger's and Begg's tests showed no significant publication bias.

Conclusion

Volumetric breast density is strongly correlated with breast cancer risk, underscoring the importance of accurate breast density assessment in screening programs. Automated volumetric measurement tools like Volpara™ and Quantra™ provide reliable assessments, potentially improving breast cancer risk prediction and management.

Implications for practice

Implementing fully automated breast density assessment tools could enhance consistency in clinical practice, minimizing observer variability and improving screening accuracy. These tools should be further validated against standardized criteria to ensure reliability in diverse clinical settings.

导言乳腺癌是女性最常见的癌症，也是导致女性死亡的主要原因。本系统综述和荟萃分析旨在评估通过各种软件获得的乳腺密度测定结果与放射科医生使用全场数字乳腺X光摄影术（FFDM）进行的目测评估之间的相关性：按照 PRISMA 2020 指南，在五个数据库（Pubmed、Google Scholar、Science Direct、Cochrane Library 和 MEDLINE）中搜索乳腺体积密度与乳腺癌风险相关的研究。采用纽卡斯尔-渥太华量表（Newcastle-Ottawa Scale）和乔安娜-布里格斯研究所核对表（Joanna Briggs Institute Checklist）评估纳入研究的质量。采用随机效应模型，使用MedCalc统计软件19.2.6版对相关性进行元分析，以汇总相关系数：综述包括 22 项研究，共涉及 58 491 名妇女。结果发现，Volpara™ 和 Quantra™ 的乳腺容积密度的汇总相关系数为 0.755（95% CI 0.496-0.890，P 2 = 99.89%，P 结论：Volpara™ 和 Quantra™ 的乳腺容积密度与乳腺癌的发病率密切相关：乳腺容积密度与乳腺癌风险密切相关，这说明在筛查项目中准确评估乳腺密度的重要性。Volpara™和Quantra™等自动体积测量工具可提供可靠的评估，有望改善乳腺癌风险预测和管理：实施全自动乳腺密度评估工具可提高临床实践的一致性，最大限度地减少观察者的变异性并提高筛查的准确性。应根据标准化标准对这些工具进行进一步验证，以确保其在不同临床环境中的可靠性。

{"title":"A systematic review and meta-analysis of correlation of automated breast density measurement","authors":"","doi":"10.1016/j.radi.2024.08.003","DOIUrl":"10.1016/j.radi.2024.08.003","url":null,"abstract":"<div><h3>Introduction</h3><p>Breast cancer is the most common cancer in women and a leading cause of mortality. This systematic review and meta-analysis aims to evaluate the correlation between breast density measurements obtained from various software and visual assessments by radiologists using full-field digital mammography (FFDM).</p></div><div><h3>Methods</h3><p>Following the PRISMA 2020 guidelines, five databases (Pubmed, Google Scholar, Science Direct, Cochrane Library, and MEDLINE) were searched for studies correlating volumetric breast density with breast cancer risk. The Newcastle–Ottawa Scale and the Joanna Briggs Institute Checklist were used to assess the quality of the included studies. Meta-analysis of correlation was applied to aggregate correlation coefficients using a random-effects model using MedCalc Statistical Software version 19.2.6.</p></div><div><h3>Results</h3><p>The review included 22 studies with a total of 58,491 women. The pooled correlation coefficient for volumetric breast density amongst Volpara™ and Quantra™ was found to be 0.755 (95% CI 0.496–0.890, p < 0.001), indicating a high positive correlation, albeit with a significant heterogeneity (I<sup>2</sup> = 99.89%, p < 0.0001). Subgroup analyses based on study origin, quality, and methodology were performed but did not reveal the heterogeneity cause. Egger's and Begg's tests showed no significant publication bias.</p></div><div><h3>Conclusion</h3><p>Volumetric breast density is strongly correlated with breast cancer risk, underscoring the importance of accurate breast density assessment in screening programs. Automated volumetric measurement tools like Volpara™ and Quantra™ provide reliable assessments, potentially improving breast cancer risk prediction and management.</p></div><div><h3>Implications for practice</h3><p>Implementing fully automated breast density assessment tools could enhance consistency in clinical practice, minimizing observer variability and improving screening accuracy. These tools should be further validated against standardized criteria to ensure reliability in diverse clinical settings.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142009698","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}

引用次数: 0

Prelim ii - EFRS Member 初步 ii - EFRS 成员

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/S1078-8174(24)00211-6

引用次数: 0

Role of green and sustainable practices in shaping the future of medical imaging technology: A cross-sectional multi-stakeholder analysis among students, radiographers, and academic experts 绿色和可持续实践在塑造未来医学影像技术中的作用：对学生、放射技师和学术专家等多方利益相关者的横向分析。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.07.017

Introduction

The detection and treatment of diseases like COVID, diabetes, cancer, cardiovascular conditions, etc., have made medical imaging technology more necessary, so it is expected that the demands of imaging modalities are also increasing and are major contributors to carbon emissions in the healthcare industry. Hence, the Radiology departments, like the rest of the healthcare industry should adapt the procedures to become more sustainable.

Methods

A total of 1016 respondents completed the online survey to assess the perception, current practices, and challenges in adopting green and sustainable practices in medical imaging. The radio technologists, teaching faculties, and students of medical imaging were recruited for the study. The survey tool was distributed to the closed groups through social media and emails.

Results

The majority of participants (66.6%) highlighted the importance of green and sustainable practices in medical imaging whereas only 21.06% of participants seem to have implemented these practices. Most of the participants give positive responses on the use of zero-lead aprons (77%), refurbished medical systems (85.8%), and eco-friendly packaging (89.5%). The mixed response was received from waste segregation and energy-saving measures. The majority (60.3%) of them have no formal education or training. However, they have a good attitude towards the willingness to adopt green practices.

Conclusions

There is a gap between perception and implementation of green and sustainable practices due to leadership and information barriers. Comprehensive training for stakeholders of medical imaging is crucial to fully integrate sustainability practices, possibly through webinars or educational modules.

Implications for practice

The study's findings shed light on how important medical imaging stakeholders view green and sustainable practices as well as potential obstacles to their implementation at the local level whilst suggesting the need for exclusive training on these practices to promote sustainability.

导言：COVID、糖尿病、癌症、心血管疾病等疾病的检测和治疗使得医学影像技术变得更加必要，因此预计对影像模式的需求也会增加，这也是医疗行业碳排放的主要原因。因此，放射科应与其他医疗行业一样，调整工作程序，使其更具可持续性：共有 1016 名受访者完成了在线调查，以评估在医学影像领域采用绿色和可持续做法的观念、当前做法和挑战。研究招募了无线电技术人员、教学人员和医学影像专业的学生。调查工具通过社交媒体和电子邮件分发给封闭小组：大多数参与者（66.6%）强调了绿色和可持续实践在医学影像中的重要性，而只有 21.06% 的参与者似乎已经实施了这些实践。大多数参与者对使用零铅围裙（77%）、翻新医疗系统（85.8%）和环保包装（89.5%）给予了积极回应。对废物分类和节能措施的反应不一。他们中的大多数（60.3%）没有受过正规教育或培训。然而，他们对采用绿色做法的意愿态度良好：结论：由于领导力和信息方面的障碍，在绿色和可持续实践的认知和实施之间存在差距。对医学影像相关人员的全面培训对于全面融入可持续发展实践至关重要，可以通过网络研讨会或教育模块的方式进行：研究结果揭示了医学影像相关人员对绿色和可持续发展实践的重要看法，以及在地方层面实施这些实践的潜在障碍，同时建议有必要就这些实践开展专门培训，以促进可持续发展。

{"title":"Role of green and sustainable practices in shaping the future of medical imaging technology: A cross-sectional multi-stakeholder analysis among students, radiographers, and academic experts","authors":"","doi":"10.1016/j.radi.2024.07.017","DOIUrl":"10.1016/j.radi.2024.07.017","url":null,"abstract":"<div><h3>Introduction</h3><p>The detection and treatment of diseases like COVID, diabetes, cancer, cardiovascular conditions, etc., have made medical imaging technology more necessary, so it is expected that the demands of imaging modalities are also increasing and are major contributors to carbon emissions in the healthcare industry. Hence, the Radiology departments, like the rest of the healthcare industry should adapt the procedures to become more sustainable.</p></div><div><h3>Methods</h3><p>A total of 1016 respondents completed the online survey to assess the perception, current practices, and challenges in adopting green and sustainable practices in medical imaging. The radio technologists, teaching faculties, and students of medical imaging were recruited for the study. The survey tool was distributed to the closed groups through social media and emails.</p></div><div><h3>Results</h3><p>The majority of participants (66.6%) highlighted the importance of green and sustainable practices in medical imaging whereas only 21.06% of participants seem to have implemented these practices. Most of the participants give positive responses on the use of zero-lead aprons (77%), refurbished medical systems (85.8%), and eco-friendly packaging (89.5%). The mixed response was received from waste segregation and energy-saving measures. The majority (60.3%) of them have no formal education or training. However, they have a good attitude towards the willingness to adopt green practices.</p></div><div><h3>Conclusions</h3><p>There is a gap between perception and implementation of green and sustainable practices due to leadership and information barriers. Comprehensive training for stakeholders of medical imaging is crucial to fully integrate sustainability practices, possibly through webinars or educational modules.</p></div><div><h3>Implications for practice</h3><p>The study's findings shed light on how important medical imaging stakeholders view green and sustainable practices as well as potential obstacles to their implementation at the local level whilst suggesting the need for exclusive training on these practices to promote sustainability.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141861290","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}

引用次数: 0

Ultrasound as a triaging tool for the diagnosis of malaria and typhoid in a resource constrained setting: A proposed frame-work 在资源有限的情况下，将超声波作为诊断疟疾和伤寒的分流工具：拟议框架。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.08.010

Introduction

Ultrasound has proven to have great potentials in the diagnosis and work-up of patients affected by tropical diseases. Its role in the diagnosis of malaria and typhoid abounds, but its value as a triaging tool in a resource-constrained settings is indistinct. Our review aimed is aimed at assessing the utility of ultrasound in diagnosis and prognosis of malaria and typhoid.

Materials and method

Extensive literature search was conducted using the PubMed electronic database, for original peer reviewed articles in English language within 1964–2023. Keywords like “malaria”, “typhoid”, “S. Typhi”, “Salmonella Typhi”, “enteric fever”, “ultrasound”, “sonography” and “ultrasonography” were searched, using Boolean operators such as (OR, AND) applying the following filters (English, Human). A systematic synthesis of the literature was done.

Result

Our initial search yielded 749 potentially relevant references out of which 55 were found to be eligible. Organs assessed include the liver, spleen, kidneys, intestines, mesenteric lymph nodes, among others. For malaria, pathognomonic conditions like splenic enlargement, hepatomegaly, renal abnormalities as well as mesenteric lymph nodes and intestinal wall thickening in patients with typhoid fever.

Conclusion

Ultrasound by experienced clinicians adds significantly to the diagnosis and work-up of patients with malaria and typhoid fever. However, it is important to note that ultrasound alone may not be sufficient for definitive diagnosis as laboratory tests may still be required for confirmatory diagnosis.

Implication for practice

This study provide information on ultrasound in diagnosis of Malaria and typhoid by evaluating the morphological changes in abdominal and other organs of the body. This can be a guide to clinicians and other healthcare providers for early diagnosis and work-up of patients in endemic areas where resources are scarce.

导言：事实证明，超声波在诊断和检查热带疾病患者方面具有巨大潜力。超声波在疟疾和伤寒的诊断中发挥着重要作用，但在资源有限的环境中，超声波作为分诊工具的价值尚不明确。我们的综述旨在评估超声波在疟疾和伤寒的诊断和预后中的作用：我们使用 PubMed 电子数据库对 1964-2023 年间的英文原创同行评审文章进行了广泛的文献检索。关键词包括 "疟疾"、"伤寒"、"伤寒沙门氏菌"、"伤寒沙门氏菌"、"肠道热"、"超声"、"超声检查 "和 "超声造影"，使用布尔运算符如（OR、AND），并应用以下筛选条件（英语、人类）进行搜索。对文献进行了系统综合：我们的初步搜索结果显示有 749 篇可能相关的参考文献，其中 55 篇符合条件。评估的器官包括肝脏、脾脏、肾脏、肠道、肠系膜淋巴结等。就疟疾而言，伤寒患者的脾脏肿大、肝脏肿大、肾脏异常以及肠系膜淋巴结和肠壁增厚等病理情况均可作为诊断依据：结论：由经验丰富的临床医生对疟疾和伤寒患者进行超声波检查可大大提高诊断和检查效果。然而，需要注意的是，仅靠超声波检查可能不足以做出明确诊断，因为可能还需要进行实验室检查才能确诊：这项研究通过评估腹部和身体其他器官的形态变化，为疟疾和伤寒的超声诊断提供了信息。对实践的启示：这项研究通过评估腹部和身体其他器官的形态变化，为疟疾和伤寒的诊断提供了信息，可以指导临床医生和其他医疗服务提供者对资源匮乏的疟疾流行地区的病人进行早期诊断和检查。

{"title":"Ultrasound as a triaging tool for the diagnosis of malaria and typhoid in a resource constrained setting: A proposed frame-work","authors":"","doi":"10.1016/j.radi.2024.08.010","DOIUrl":"10.1016/j.radi.2024.08.010","url":null,"abstract":"<div><h3>Introduction</h3><p>Ultrasound has proven to have great potentials in the diagnosis and work-up of patients affected by tropical diseases. Its role in the diagnosis of malaria and typhoid abounds, but its value as a triaging tool in a resource-constrained settings is indistinct. Our review aimed is aimed at assessing the utility of ultrasound in diagnosis and prognosis of malaria and typhoid.</p></div><div><h3>Materials and method</h3><p>Extensive literature search was conducted using the PubMed electronic database, for original peer reviewed articles in English language within 1964–2023. Keywords like “malaria”, “typhoid”, “S. Typhi”, “Salmonella Typhi”, “enteric fever”, “ultrasound”, “sonography” and “ultrasonography” were searched, using Boolean operators such as (OR, AND) applying the following filters (English, Human). A systematic synthesis of the literature was done.</p></div><div><h3>Result</h3><p>Our initial search yielded 749 potentially relevant references out of which 55 were found to be eligible. Organs assessed include the liver, spleen, kidneys, intestines, mesenteric lymph nodes, among others. For malaria, pathognomonic conditions like splenic enlargement, hepatomegaly, renal abnormalities as well as mesenteric lymph nodes and intestinal wall thickening in patients with typhoid fever.</p></div><div><h3>Conclusion</h3><p>Ultrasound by experienced clinicians adds significantly to the diagnosis and work-up of patients with malaria and typhoid fever. However, it is important to note that ultrasound alone may not be sufficient for definitive diagnosis as laboratory tests may still be required for confirmatory diagnosis.</p></div><div><h3>Implication for practice</h3><p>This study provide information on ultrasound in diagnosis of Malaria and typhoid by evaluating the morphological changes in abdominal and other organs of the body. This can be a guide to clinicians and other healthcare providers for early diagnosis and work-up of patients in endemic areas where resources are scarce.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142093968","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}

引用次数: 0

Authors’ Reply to Letter to Editor: Promoting sustainability activities in clinical radiography practice and education in resource-limited countries: A discussion paper 作者对致编辑信的回复：在资源有限的国家促进临床放射学实践和教育的可持续性活动：讨论文件。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.07.007

引用次数: 0

An observational cross-sectional study of pharmaceutical waste disposal practices in Australian medical imaging departments: A comparison of community versus hospital practice 澳大利亚医学影像部门药物废物处理方法的横断面观察研究：社区与医院实践的比较。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.07.009

Introduction

Pharmaceuticals are used widely in radiography practice but pose an environmental risk. This study explored Australian radiographers’ environmental attitude, pharmaceutical waste disposal practices, and knowledge and concern regarding the environmental impact of these pharmaceuticals.

Methods

This study utilised an anonymous, online questionnaire developed from two validated questionnaires. Participants (n = 150) held current registration with the Medical Radiation Practice Board of Australia and were working eight or more hours per week in a medical imaging practice (public or private).

Results

Participants did not answer all questions, hence percentages reported reflect the number of counts for each question. Most participants (71.4%; 105/147) disposed of contaminated pharmaceutical waste in clinical waste bins with 17.1% (15/146) disposing of it down drains. More hospital radiographers 13.54% (13/96) reported this disposal compared with 2.08% (1/48) of community-based radiographers (Fisher's Exact Test, p = 0.035). There was no difference in disposal of non-contaminated waste between practice settings - general waste bin (68.5%; 100/150), recycling bin (28.8%; 42/146), and clinical waste bin (41.8%; 61/146). Participants lacked knowledge of impacts on the food chain and the health of humans and wildlife. Only 34.7% (48/138) of participants expressed concern regarding the impacts of human excreted pharmaceuticals on the environment compared with 65.8% (98/149) regarding impacts from incorrect disposal. Many (18.4%; 25/136) reported having received no information on correct disposal of pharmaceutical waste.

Conclusion

This study highlighted participants’ lack of knowledge on how pharmaceuticals enter the natural environment and the subsequent impacts on the environment and on the health of humans, and flora and fauna. They lacked knowledge of correct pharmaceutical waste disposal methods, but most agreed it was their professional responsibility to dispose of waste correctly.

Implications for practice

Improving radiographers’ pharmaceutical waste disposal practices through education and professional support will reduce environmental impacts and also provide financial co-benefits if non-contaminated waste is recycled where possible and not incinerated.

简介：药品在放射学实践中被广泛使用，但会对环境造成危害。本研究探讨了澳大利亚放射技师的环保态度、药品废物处理方法以及对这些药品对环境影响的了解和关注：本研究使用了一份匿名在线问卷，该问卷由两份经过验证的问卷发展而来。参与者（n = 150）目前已在澳大利亚医学放射实践委员会注册，每周在医学影像实践机构（公立或私立）工作 8 小时或以上：结果：参与者没有回答所有问题，因此报告的百分比反映了每个问题的统计人数。大多数参与者（71.4%；105/147）将受污染的药物废物扔进医疗废物箱，17.1%（15/146）扔进下水道。与社区放射技师的 2.08%（1/48）相比，更多医院放射技师（13.54%，13/96）报告了这种处理方式（费雪精确检验，p = 0.035）。在处理未受污染的废物方面，不同执业环境的参与者没有差异--一般废物箱（68.5%；100/150）、回收箱（28.8%；42/146）和临床废物箱（41.8%；61/146）。参与者缺乏对食物链以及人类和野生动物健康影响的了解。只有 34.7%（48/138）的参与者对人类排泄的药物对环境的影响表示担忧，而 65.8%（98/149）的参与者对错误处置药物对环境的影响表示担忧。许多人（18.4%；25/136）表示没有收到过关于正确处置药物废物的信息：本研究强调了参与者对药物如何进入自然环境以及随后对环境、人类健康和动植物健康的影响缺乏了解。他们缺乏正确处理药物废物方法的知识，但大多数人都认为正确处理废物是他们的职业责任：实践启示：通过教育和专业支持改善放射技师的药物废物处理方法将减少对环境的影响，如果尽可能回收未受污染的废物而不是进行焚烧，还将带来经济上的共同利益。

{"title":"An observational cross-sectional study of pharmaceutical waste disposal practices in Australian medical imaging departments: A comparison of community versus hospital practice","authors":"","doi":"10.1016/j.radi.2024.07.009","DOIUrl":"10.1016/j.radi.2024.07.009","url":null,"abstract":"<div><h3>Introduction</h3><p>Pharmaceuticals are used widely in radiography practice but pose an environmental risk. This study explored Australian radiographers’ environmental attitude, pharmaceutical waste disposal practices, and knowledge and concern regarding the environmental impact of these pharmaceuticals.</p></div><div><h3>Methods</h3><p>This study utilised an anonymous, online questionnaire developed from two validated questionnaires. Participants (n = 150) held current registration with the Medical Radiation Practice Board of Australia and were working eight or more hours per week in a medical imaging practice (public or private).</p></div><div><h3>Results</h3><p>Participants did not answer all questions, hence percentages reported reflect the number of counts for each question. Most participants (71.4%; 105/147) disposed of contaminated pharmaceutical waste in clinical waste bins with 17.1% (15/146) disposing of it down drains. More hospital radiographers 13.54% (13/96) reported this disposal compared with 2.08% (1/48) of community-based radiographers (Fisher's Exact Test, p = 0.035). There was no difference in disposal of non-contaminated waste between practice settings - general waste bin (68.5%; 100/150), recycling bin (28.8%; 42/146), and clinical waste bin (41.8%; 61/146). Participants lacked knowledge of impacts on the food chain and the health of humans and wildlife. Only 34.7% (48/138) of participants expressed concern regarding the impacts of human excreted pharmaceuticals on the environment compared with 65.8% (98/149) regarding impacts from incorrect disposal. Many (18.4%; 25/136) reported having received no information on correct disposal of pharmaceutical waste.</p></div><div><h3>Conclusion</h3><p>This study highlighted participants’ lack of knowledge on how pharmaceuticals enter the natural environment and the subsequent impacts on the environment and on the health of humans, and flora and fauna. They lacked knowledge of correct pharmaceutical waste disposal methods, but most agreed it was their professional responsibility to dispose of waste correctly.</p></div><div><h3>Implications for practice</h3><p>Improving radiographers’ pharmaceutical waste disposal practices through education and professional support will reduce environmental impacts and also provide financial co-benefits if non-contaminated waste is recycled where possible and not incinerated.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1078817424001834/pdfft?md5=f2a2c647bf234f5f37c641e77afe05bd&pid=1-s2.0-S1078817424001834-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141876309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The role of shared decision-making in enhancing patient experience: Insights from a cohort of curative head and neck cancer patients 共同决策在改善患者体验中的作用：来自头颈部癌症治愈患者群组的启示。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.07.020

Introduction

Shared decision-making (SDM) is on the NHS policy agenda, and the preferred model for preference-sensitive decisions. This study establishes baseline patient-perceived SDM in a radical head and neck cohort, and explores patients’ views on SDM in a large, specialist trust.

Methods

An SDM questionnaire was distributed to all radical head and neck radiotherapy patients (N = 165), June–December 2023. This combined a well-validated instrument for measuring SDM from the patient perspective, SDM-Q-9, with additional questions exploring patient views. Thematic analysis was used to construct and interpret themes.

Results

65/165 (39%) questionnaires were returned. SDM-Q-9 mean standardised score was 78.6 (SD 26.3). There was a moderate ceiling effect (26%). Scores were not sensitive to sex (p = 0.64) or age (ρ = 0.1). Higher levels of SDM were perceived by participants who stated SDM was very important (51/65, 79%) than somewhat or not at all important (82.4 vs. 62.7; p = 0.02; Cohen d = 0.75). Individuals who discussed their personal priorities with the clinician (46/65, 70.8%), were more likely to be very satisfied with their involvement in SDM (89.1% vs. 52.9%). Thematic analysis generated three themes: Control, Desire for Transparency and Understanding, and Doctor as the Expert.

Conclusion

Patient-perceived SDM levels are high for head and neck patients. Participants who value SDM also perceive higher levels of SDM. Patient satisfaction increases when individuals discuss their personal priorities. The modest response rate and self-selection bias affect the generalisability of the results. Only radiotherapy patients were included; those who chose alternative treatment may perceive different levels of SDM. The moderate ceiling effect may limit the use of SDM-Q-9 to measure impact of future interventions to improve SDM.

Implications for practice

SDM-Q-9 should be combined with an objective, observer measure of SDM.

导言：共同决策（SDM）已列入英国国家医疗服务体系（NHS）的政策议程，也是对偏好敏感的决策的首选模式。本研究确定了头颈部根治术队列中患者感知的 SDM 基线，并探讨了一家大型专科信托机构中患者对 SDM 的看法：在 2023 年 6 月至 12 月期间，向所有头颈部放射治疗根治术患者（N = 165）发放了 SDM 问卷。该问卷结合了从患者角度测量 SDM 的有效工具 SDM-Q-9，以及探索患者观点的附加问题。采用主题分析法构建和解释主题：共收回 65/165 份问卷（39%）。SDM-Q-9 的平均标准化得分为 78.6（SD 26.3）。存在中度上限效应（26%）。得分对性别（p = 0.64）或年龄（ρ = 0.1）不敏感。认为 SDM 非常重要的参与者（51/65，79%）的 SDM 水平高于认为 SDM 有点重要或完全不重要的参与者（82.4 vs. 62.7；p = 0.02；Cohen d = 0.75）。与临床医生讨论过个人优先事项的患者（46/65，70.8%）更有可能对参与 SDM 感到非常满意（89.1% 对 52.9%）。主题分析产生了三个主题：控制、希望透明和理解以及医生是专家：结论：头颈部患者的 SDM 水平较高。重视 SDM 的参与者也认为 SDM 水平较高。当个人讨论其个人优先事项时，患者的满意度会提高。响应率不高和自我选择偏差影响了结果的普遍性。研究只纳入了接受放射治疗的患者；选择其他治疗方法的患者对 SDM 的认识水平可能不同。适度的上限效应可能会限制使用SDM-Q-9来衡量未来干预措施对改善SDM的影响：对实践的启示：SDM-Q-9 应与客观的 SDM 观察指标相结合。

{"title":"The role of shared decision-making in enhancing patient experience: Insights from a cohort of curative head and neck cancer patients","authors":"","doi":"10.1016/j.radi.2024.07.020","DOIUrl":"10.1016/j.radi.2024.07.020","url":null,"abstract":"<div><h3>Introduction</h3><p>Shared decision-making (SDM) is on the NHS policy agenda, and the preferred model for preference-sensitive decisions. This study establishes baseline patient-perceived SDM in a radical head and neck cohort, and explores patients’ views on SDM in a large, specialist trust.</p></div><div><h3>Methods</h3><p>An SDM questionnaire was distributed to all radical head and neck radiotherapy patients (N = 165), June–December 2023. This combined a well-validated instrument for measuring SDM from the patient perspective, SDM-Q-9, with additional questions exploring patient views. Thematic analysis was used to construct and interpret themes.</p></div><div><h3>Results</h3><p>65/165 (39%) questionnaires were returned. SDM-Q-9 mean standardised score was 78.6 (SD 26.3). There was a moderate ceiling effect (26%). Scores were not sensitive to sex (p = 0.64) or age (ρ = 0.1). Higher levels of SDM were perceived by participants who stated SDM was very important (51/65, 79%) than somewhat or not at all important (82.4 vs. 62.7; p = 0.02; Cohen d = 0.75). Individuals who discussed their personal priorities with the clinician (46/65, 70.8%), were more likely to be very satisfied with their involvement in SDM (89.1% vs. 52.9%). Thematic analysis generated three themes: Control, Desire for Transparency and Understanding, and Doctor as the Expert.</p></div><div><h3>Conclusion</h3><p>Patient-perceived SDM levels are high for head and neck patients. Participants who value SDM also perceive higher levels of SDM. Patient satisfaction increases when individuals discuss their personal priorities. The modest response rate and self-selection bias affect the generalisability of the results. Only radiotherapy patients were included; those who chose alternative treatment may perceive different levels of SDM. The moderate ceiling effect may limit the use of SDM-Q-9 to measure impact of future interventions to improve SDM.</p></div><div><h3>Implications for practice</h3><p>SDM-Q-9 should be combined with an objective, observer measure of SDM.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141890418","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}

引用次数: 0

Assessing the predictive value of first trimester ultrasound and biochemical markers in miscarriage: A scoping review 评估妊娠头三个月超声和生化指标对流产的预测价值：范围综述。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.07.022

Introduction

Vaginal bleeding in the first trimester of pregnancy generates anxiety and uncertainty for expecting parents. The ability to determine pregnancy outcome through a first trimester ultrasound scan remains a challenge in obstetrics. Several first trimester ultrasound markers used individually or in combination, as well as ultrasound markers used in combination with biochemical markers, have been studied to determine their predictive value in pregnancy outcome. This scoping review was performed to determine which markers have already been investigated for this purpose.

Methods

An extensive and systematic database search was performed using four different categories of keywords which were combined using Boolean terms. A total of 14 variables were included on the final data charting forms. Data was synthesised collectively for each variable and then separately for the studies analysing only one marker. For the studies which analysed multiple markers, data was synthesised based on the number of markers per study.

Results

The search yielded 3608 studies, of which 128 were ultimately used for this review. Data extraction, based on predetermined eligibility criteria, was performed by two authors independently. Seventy-seven (62.6%) studies investigated the predictive value of a single ultrasound marker. The remaining 46 (37.4%) studies explored multiple markers, of which at least one was an ultrasound marker.

Conclusion

This review identified several discrepancies among different studies. This highlights the need for better consensus among researchers to allow for the design of a predictive model which enables extrapolation of findings to all pregnant women.

Implications for practice

Through the study of ultrasound and biochemical markers in the first trimester of pregnancy, clinicians may provide a more accurate prediction of pregnancy outcome following threatened miscarriage.

导言怀孕前三个月的阴道出血会给准父母带来焦虑和不确定性。通过妊娠头三个月的超声波扫描来确定妊娠结果的能力仍然是产科领域的一项挑战。为了确定其对妊娠结局的预测价值，已经研究了几种单独或联合使用的妊娠头三个月超声标记物，以及与生化标记物联合使用的超声标记物。本综述旨在确定哪些标记物已被用于此目的：方法：使用四类不同的关键词，并使用布尔词进行组合，对数据库进行了广泛而系统的搜索。最终的数据图表共包含 14 个变量。对每个变量的数据进行了汇总，然后对只分析一种标记物的研究分别进行了汇总。对于分析多个标记物的研究，则根据每项研究的标记物数量进行数据综合：结果：搜索结果显示有 3608 项研究，其中 128 项最终用于本次综述。数据提取工作由两位作者根据预先确定的资格标准独立完成。77项（62.6%）研究调查了单一超声标记物的预测价值。其余 46 项（37.4%）研究探讨了多种标记物，其中至少有一种是超声标记物：本综述发现了不同研究之间的一些差异。结论：本综述发现了不同研究之间的一些差异，这凸显了研究人员之间需要达成更好的共识，以便设计一个预测模型，将研究结果推广到所有孕妇：对实践的启示：通过对妊娠头三个月超声波和生化指标的研究，临床医生可以更准确地预测可能流产后的妊娠结局。

{"title":"Assessing the predictive value of first trimester ultrasound and biochemical markers in miscarriage: A scoping review","authors":"","doi":"10.1016/j.radi.2024.07.022","DOIUrl":"10.1016/j.radi.2024.07.022","url":null,"abstract":"<div><h3>Introduction</h3><p>Vaginal bleeding in the first trimester of pregnancy generates anxiety and uncertainty for expecting parents. The ability to determine pregnancy outcome through a first trimester ultrasound scan remains a challenge in obstetrics. Several first trimester ultrasound markers used individually or in combination, as well as ultrasound markers used in combination with biochemical markers, have been studied to determine their predictive value in pregnancy outcome. This scoping review was performed to determine which markers have already been investigated for this purpose.</p></div><div><h3>Methods</h3><p>An extensive and systematic database search was performed using four different categories of keywords which were combined using Boolean terms. A total of 14 variables were included on the final data charting forms. Data was synthesised collectively for each variable and then separately for the studies analysing only one marker. For the studies which analysed multiple markers, data was synthesised based on the number of markers per study.</p></div><div><h3>Results</h3><p>The search yielded 3608 studies, of which 128 were ultimately used for this review. Data extraction, based on predetermined eligibility criteria, was performed by two authors independently. Seventy-seven (62.6%) studies investigated the predictive value of a single ultrasound marker. The remaining 46 (37.4%) studies explored multiple markers, of which at least one was an ultrasound marker.</p></div><div><h3>Conclusion</h3><p>This review identified several discrepancies among different studies. This highlights the need for better consensus among researchers to allow for the design of a predictive model which enables extrapolation of findings to all pregnant women.</p></div><div><h3>Implications for practice</h3><p>Through the study of ultrasound and biochemical markers in the first trimester of pregnancy, clinicians may provide a more accurate prediction of pregnancy outcome following threatened miscarriage.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1078817424001962/pdfft?md5=d210158397cf8c6ba1cf6c4458140445&pid=1-s2.0-S1078817424001962-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141914194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning-based automated liver contouring using a small sample of radiotherapy planning computed tomography images 利用小样本放疗计划计算机断层扫描图像进行基于深度学习的自动肝脏轮廓绘制。

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography

Pub Date : 2024-08-01 DOI: 10.1016/j.radi.2024.08.005

Introduction

No study has yet investigated the minimum amount of data required for deep learning-based liver contouring. Therefore, this study aimed to investigate the feasibility of automated liver contouring using limited data.

Methods

Radiotherapy planning Computed tomography (CT) images were subjected to various preprocessing methods, such as denoising and windowing. Segmentation was conducted using the modified Attention U-Net and Residual U-Net networks. Two different modified networks were trained separately for different training sizes. For each architecture, the model trained with the training set size that achieved the highest dice similarity coefficient (DSC) score was selected for further evaluation. Two unseen external datasets with different distributions from the training set were also used to examine the generalizability of the proposed method.

Results

The modified Residual U-Net and Attention U-Net networks achieved average DSCs of 97.62% and 96.48%, respectively, on the test set, using 62 training cases. The average Hausdorff distances (AHDs) for the modified Residual U-Net and Attention U-Net networks were 0.57 mm and 0.71 mm, respectively. Also, the modified Residual U-Net and Attention U-Net networks were tested on two unseen external datasets, achieving DSCs of 95.35% and 95.82% for data from another center and 95.16% and 94.93% for the AbdomenCT-1K dataset, respectively.

Conclusion

This study demonstrates that deep learning models can accurately segment livers using a small training set. The method, utilizing simple preprocessing and modified network architectures, shows strong performance on unseen datasets, indicating its generalizability.

Implications for practice

This promising result suggests its potential for automated liver contouring in radiotherapy planning.

简介还没有研究调查过基于深度学习的肝脏轮廓绘制所需的最小数据量。因此，本研究旨在调查使用有限数据自动绘制肝脏轮廓的可行性：放疗计划计算机断层扫描（CT）图像经过各种预处理方法，如去噪和开窗。使用改进的注意力 U-Net 和残差 U-Net 网络进行分割。针对不同的训练规模，分别训练了两种不同的修正网络。对于每种架构，都选择了训练集规模最大、骰子相似系数（DSC）得分最高的模型进行进一步评估。此外，还使用了与训练集分布不同的两个未见外部数据集，以检验建议方法的通用性：结果：使用 62 个训练案例，经修改的残差 U-Net 和注意力 U-Net 网络在测试集上的平均 DSC 分别达到 97.62% 和 96.48%。修改后的残差 U-Net 和注意力 U-Net 网络的平均豪斯多夫距离（AHD）分别为 0.57 毫米和 0.71 毫米。此外，修改后的残差 U-Net 和注意力 U-Net 网络还在两个未见的外部数据集上进行了测试，来自另一个中心的数据和腹部 CT-1K 数据集的 DSC 分别达到了 95.35% 和 95.82%，DSC 分别达到了 95.16% 和 94.93%：本研究表明，深度学习模型可以使用少量训练集准确分割肝脏。该方法利用简单的预处理和修改后的网络架构，在未见过的数据集上表现出很强的性能，表明其具有普适性：这一充满希望的结果表明，它在放疗计划中的自动肝脏轮廓划分方面具有潜力。

{"title":"Deep learning-based automated liver contouring using a small sample of radiotherapy planning computed tomography images","authors":"","doi":"10.1016/j.radi.2024.08.005","DOIUrl":"10.1016/j.radi.2024.08.005","url":null,"abstract":"<div><h3>Introduction</h3><p>No study has yet investigated the minimum amount of data required for deep learning-based liver contouring. Therefore, this study aimed to investigate the feasibility of automated liver contouring using limited data.</p></div><div><h3>Methods</h3><p>Radiotherapy planning Computed tomography (CT) images were subjected to various preprocessing methods, such as denoising and windowing. Segmentation was conducted using the modified Attention U-Net and Residual U-Net networks. Two different modified networks were trained separately for different training sizes. For each architecture, the model trained with the training set size that achieved the highest dice similarity coefficient (DSC) score was selected for further evaluation. Two unseen external datasets with different distributions from the training set were also used to examine the generalizability of the proposed method.</p></div><div><h3>Results</h3><p>The modified Residual U-Net and Attention U-Net networks achieved average DSCs of 97.62% and 96.48%, respectively, on the test set, using 62 training cases. The average Hausdorff distances (AHDs) for the modified Residual U-Net and Attention U-Net networks were 0.57 mm and 0.71 mm, respectively. Also, the modified Residual U-Net and Attention U-Net networks were tested on two unseen external datasets, achieving DSCs of 95.35% and 95.82% for data from another center and 95.16% and 94.93% for the AbdomenCT-1K dataset, respectively.</p></div><div><h3>Conclusion</h3><p>This study demonstrates that deep learning models can accurately segment livers using a small training set. The method, utilizing simple preprocessing and modified network architectures, shows strong performance on unseen datasets, indicating its generalizability.</p></div><div><h3>Implications for practice</h3><p>This promising result suggests its potential for automated liver contouring in radiotherapy planning.</p></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142047339","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}

引用次数: 0