目的构建影像组学模型,提高~(18)F-PSMA-1007 PET/CT对局灶性前列腺癌的鉴别能力。方法回顾性收集2020年7月至2024年4月西安交通大学第一附属医院经前列腺穿刺活检确诊前列腺癌、~(18)F-PSMA-1007 PET/CT显示局灶性核素浓聚的74例患者,...目的构建影像组学模型,提高~(18)F-PSMA-1007 PET/CT对局灶性前列腺癌的鉴别能力。方法回顾性收集2020年7月至2024年4月西安交通大学第一附属医院经前列腺穿刺活检确诊前列腺癌、~(18)F-PSMA-1007 PET/CT显示局灶性核素浓聚的74例患者,中位年龄为71岁,42例患者Gleason评分<8,32例患者Gleason评分≥8,根据检查时间随机选出外部验证集,并将其余患者按照7∶3随机划分为训练集和测试集。在配准图像上半自动勾画病灶感兴趣区(region of interest,ROI)并手动调整,随后将ROI对称性移至对侧非肿瘤组织,通过方差和相关性分析筛选特征,使用Logistic回归构建模型,并与视觉判断比较,通过绘制受试者工作特征(receiver operating characteristic,ROC)曲线比较各个模型的效果。基于Gleason评分、血清tPSA水平和病灶位置划分亚组,获得肿瘤组织鉴别诊断的最佳特征。结果共筛选出8个特征,视觉评价、测试集和外部验证集中曲线下面积(area under the curve,AUC)分别为0.858、0.933和0.891,鉴别前列腺肿瘤的灵敏度分别为0.757、0.800和0.917,特异度分别为0.960、0.800和0.792。亚组分析结果显示,组学特征10percentile和skewness在肿瘤鉴别中价值较高,肿瘤组织10Percentile各组均高于非肿瘤组织(P值分别为0.012、0.002、<0.001、<0.001、<0.001、<0.001);当tPSA≤10 ng/mL且Gleason评分≥8时,肿瘤与非肿瘤组织skewness无统计学差异(P=0.08);tPSA≥20 ng/mL时,非肿瘤组织的skewness稍高于肿瘤组织,但无统计学差异(P值分别为0.285、0.791);肿瘤灶位于前列腺后部(左后部、右后部)时,skewness显著高于非肿瘤组织(P均<0.001)。结论影像组学模型在区分局灶性前列腺癌肿瘤与非肿瘤组织方面灵敏度和准确性优于视觉评价,但后者特异度更高;其中skewness和10percentile对于鉴别诊断有较高价值。展开更多
Prostate cancer (PCa) is the second most common type of cancer among men worldwide and one of the leading causes of cancer-related deaths. According to data from the World Health Organization (WHO), this cancer causes...Prostate cancer (PCa) is the second most common type of cancer among men worldwide and one of the leading causes of cancer-related deaths. According to data from the World Health Organization (WHO), this cancer causes hundreds of thousands of new cases and tens of thousands of male deaths globally each year. The incidence of PCa varies across different regions and populations, generally being higher in developed countries. This disparity may be attributed to lifestyle factors and the widespread availability of screening and diagnostic technologies. Prostate-specific membrane antigen (PSMA) is a membrane-bound enzyme predominantly expressed in prostate tissue and PCa cells, with lower expression in normal tissues. This high expression makes PSMA a critical target for the diagnosis and treatment of PCa, particularly in the field of molecular imaging and radiopharmaceutical therapy. Recently, various studies have emerged on radiopharmaceuticals developed based on PSMA ligands, which can be used to specifically identify and locate PCa cells. Research on the radiomics of these novel drugs has also been updated. This article will discuss the role and limitations of PSMA PET in the diagnosis and management of PCa treatment.展开更多
文摘目的构建影像组学模型,提高~(18)F-PSMA-1007 PET/CT对局灶性前列腺癌的鉴别能力。方法回顾性收集2020年7月至2024年4月西安交通大学第一附属医院经前列腺穿刺活检确诊前列腺癌、~(18)F-PSMA-1007 PET/CT显示局灶性核素浓聚的74例患者,中位年龄为71岁,42例患者Gleason评分<8,32例患者Gleason评分≥8,根据检查时间随机选出外部验证集,并将其余患者按照7∶3随机划分为训练集和测试集。在配准图像上半自动勾画病灶感兴趣区(region of interest,ROI)并手动调整,随后将ROI对称性移至对侧非肿瘤组织,通过方差和相关性分析筛选特征,使用Logistic回归构建模型,并与视觉判断比较,通过绘制受试者工作特征(receiver operating characteristic,ROC)曲线比较各个模型的效果。基于Gleason评分、血清tPSA水平和病灶位置划分亚组,获得肿瘤组织鉴别诊断的最佳特征。结果共筛选出8个特征,视觉评价、测试集和外部验证集中曲线下面积(area under the curve,AUC)分别为0.858、0.933和0.891,鉴别前列腺肿瘤的灵敏度分别为0.757、0.800和0.917,特异度分别为0.960、0.800和0.792。亚组分析结果显示,组学特征10percentile和skewness在肿瘤鉴别中价值较高,肿瘤组织10Percentile各组均高于非肿瘤组织(P值分别为0.012、0.002、<0.001、<0.001、<0.001、<0.001);当tPSA≤10 ng/mL且Gleason评分≥8时,肿瘤与非肿瘤组织skewness无统计学差异(P=0.08);tPSA≥20 ng/mL时,非肿瘤组织的skewness稍高于肿瘤组织,但无统计学差异(P值分别为0.285、0.791);肿瘤灶位于前列腺后部(左后部、右后部)时,skewness显著高于非肿瘤组织(P均<0.001)。结论影像组学模型在区分局灶性前列腺癌肿瘤与非肿瘤组织方面灵敏度和准确性优于视觉评价,但后者特异度更高;其中skewness和10percentile对于鉴别诊断有较高价值。
文摘Prostate cancer (PCa) is the second most common type of cancer among men worldwide and one of the leading causes of cancer-related deaths. According to data from the World Health Organization (WHO), this cancer causes hundreds of thousands of new cases and tens of thousands of male deaths globally each year. The incidence of PCa varies across different regions and populations, generally being higher in developed countries. This disparity may be attributed to lifestyle factors and the widespread availability of screening and diagnostic technologies. Prostate-specific membrane antigen (PSMA) is a membrane-bound enzyme predominantly expressed in prostate tissue and PCa cells, with lower expression in normal tissues. This high expression makes PSMA a critical target for the diagnosis and treatment of PCa, particularly in the field of molecular imaging and radiopharmaceutical therapy. Recently, various studies have emerged on radiopharmaceuticals developed based on PSMA ligands, which can be used to specifically identify and locate PCa cells. Research on the radiomics of these novel drugs has also been updated. This article will discuss the role and limitations of PSMA PET in the diagnosis and management of PCa treatment.
