Objectives: This study aimed to determine whether errors in vascular measurements would affect device selection in endovascular aortic repair (EVAR) by comparing measurements obtained using non-contrast computed tomog...Objectives: This study aimed to determine whether errors in vascular measurements would affect device selection in endovascular aortic repair (EVAR) by comparing measurements obtained using non-contrast computed tomography (NCT) with those obtained using contrast-enhanced CT (CECT). Materials and Methods: This single-center, retrospective study included 25 patients who underwent EVAR for abdominal aortic aneurysm at our institution. A 1-mm horizontal cross-sectional slice of NCT and CECT from each patient was retrospectively reviewed. The area from the abdominal aorta to the common iliac artery was divided into four zones. A centerline was created using the NCT by manually plotting the center points. Subsequently, the centerlines were automatically extracted and manually corrected during the arterial phase of CECT. The diameter and length of each zone were measured for each modality. The mean diameters and lengths of the target vessels were compared between NCT and CECT. Results: The measurements obtained using both methods were reproducible and demonstrated good agreement. The mean differences in vessel length and diameter measurements for each segment between NCT and CECT were not statistically significant, indicating good consistency. Conclusion: NCT may be useful for preoperative EVAR evaluation in patients with renal dysfunction or allergies to contrast agents.展开更多
目的探讨基于锥光束乳腺CT(cone-bean breast CT,CBBCT)图像的放射组学模型对乳腺癌新辅助治疗病理完全缓解(pathological complete response,pCR)的预测价值。方法回顾性分析2022年1月至2023年5月于广西医科大学附属肿瘤医院接受新辅...目的探讨基于锥光束乳腺CT(cone-bean breast CT,CBBCT)图像的放射组学模型对乳腺癌新辅助治疗病理完全缓解(pathological complete response,pCR)的预测价值。方法回顾性分析2022年1月至2023年5月于广西医科大学附属肿瘤医院接受新辅助治疗的106例女性乳腺癌患者的CBBCT图像。将患者按8∶2的比例随机分为训练组和测试组。共提取2264个放射组学特征,采用特征筛选器与机器学习分类器交叉组合的方案建立放射组学模型。使用受试者工作特征(receiver operating characteristic,ROC)曲线评估模型的性能,利用决策曲线分析(decision curve analysis,DCA)比较训练组和测试组不同阈值概率下的净收益。结果L2范数正则化-决策树模型在训练组的曲线下面积(area under the curve,AUC)为0.941(95%CI:0.897~0.984),准确率为86.9%,特异度为94.2%,敏感度为75.0%;在测试组的AUC为0.732(95%CI:0.518~0.947),准确率为72.7%,特异度为85.7%,敏感度为50.0%。无论在训练组还是测试组均有最大净收益。结论基于CBBCT图像的L2范数正则化-决策树预测模型在预测乳腺癌新辅助治疗pCR上有较好的性能表现,可为乳腺癌个体化治疗和及时调整化疗方案提供有价值的信息。展开更多
文摘Objectives: This study aimed to determine whether errors in vascular measurements would affect device selection in endovascular aortic repair (EVAR) by comparing measurements obtained using non-contrast computed tomography (NCT) with those obtained using contrast-enhanced CT (CECT). Materials and Methods: This single-center, retrospective study included 25 patients who underwent EVAR for abdominal aortic aneurysm at our institution. A 1-mm horizontal cross-sectional slice of NCT and CECT from each patient was retrospectively reviewed. The area from the abdominal aorta to the common iliac artery was divided into four zones. A centerline was created using the NCT by manually plotting the center points. Subsequently, the centerlines were automatically extracted and manually corrected during the arterial phase of CECT. The diameter and length of each zone were measured for each modality. The mean diameters and lengths of the target vessels were compared between NCT and CECT. Results: The measurements obtained using both methods were reproducible and demonstrated good agreement. The mean differences in vessel length and diameter measurements for each segment between NCT and CECT were not statistically significant, indicating good consistency. Conclusion: NCT may be useful for preoperative EVAR evaluation in patients with renal dysfunction or allergies to contrast agents.
文摘目的探讨基于锥光束乳腺CT(cone-bean breast CT,CBBCT)图像的放射组学模型对乳腺癌新辅助治疗病理完全缓解(pathological complete response,pCR)的预测价值。方法回顾性分析2022年1月至2023年5月于广西医科大学附属肿瘤医院接受新辅助治疗的106例女性乳腺癌患者的CBBCT图像。将患者按8∶2的比例随机分为训练组和测试组。共提取2264个放射组学特征,采用特征筛选器与机器学习分类器交叉组合的方案建立放射组学模型。使用受试者工作特征(receiver operating characteristic,ROC)曲线评估模型的性能,利用决策曲线分析(decision curve analysis,DCA)比较训练组和测试组不同阈值概率下的净收益。结果L2范数正则化-决策树模型在训练组的曲线下面积(area under the curve,AUC)为0.941(95%CI:0.897~0.984),准确率为86.9%,特异度为94.2%,敏感度为75.0%;在测试组的AUC为0.732(95%CI:0.518~0.947),准确率为72.7%,特异度为85.7%,敏感度为50.0%。无论在训练组还是测试组均有最大净收益。结论基于CBBCT图像的L2范数正则化-决策树预测模型在预测乳腺癌新辅助治疗pCR上有较好的性能表现,可为乳腺癌个体化治疗和及时调整化疗方案提供有价值的信息。
