图像处理可导致部分恶性软组织病变在数字乳腺X线摄影图像中被遗漏
本研究通过观察者研究评估图像处理对乳腺X线摄影中癌症检测的影响,使用349幅数字乳腺X线图像(含191例细微癌症),比较FlavourA(标准)与FlavourB(增强)两种处理方式。结果显示,钙化检测的JAFROC FOM均为0.86;软组织病变检测FlavourA(0.81)优于FlavourB(0.78),差异显著(p=0.001)。FlavourA在致密乳腺(体积密度>7.5%时p=0.04)中改善软组织病变检测。结论认为FlavourA对恶性软组织病变(主要为浸润性)的检测显著优于FlavourB,尽管FlavourB具有更高对比度外观。
要点
- FlavourA对软组织病变的JAFROC FOM为0.81,FlavourB为0.78,差异显著(p=0.001)。
- 钙化检测的JAFROC FOM在两种处理下均为0.86。
- FlavourA在体积密度>7.5%的致密乳腺中改善软组织病变检测(p=0.04)。
核心结论
- FlavourA图像处理对恶性软组织病变(主要为浸润性)的检测显著优于FlavourB,尽管FlavourB具有更高对比度外观;临床选择图像处理应基于客观指标。
研究设计与样本
- 观察者研究,使用349幅数字乳腺X线图像(正常乳腺、钙化簇或软组织病变,含191例细微癌症),6名观察者共4188次观察,采用JAFROC分析。
关键影像表现/征象
- FlavourB具有更高对比度外观,常为放射科医生所偏好。
- FlavourA检测到所有级别和大小的癌症数量多于FlavourB。
诊断标准与关键数值
- 钙化检测JAFROC FOM:FlavourA 0.86 vs FlavourB 0.86。
- 软组织病变检测JAFROC FOM:FlavourA 0.81 vs FlavourB 0.78,差异显著(p=0.001)。
- 致密乳腺(体积密度>7.5%)中FlavourA改善软组织病变检测(p=0.04)。
临床应用与阅片要点
- 临床选择图像处理方式应基于客观指标,而非仅凭对比度外观偏好。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
AIM: To investigate the effect of image processing on cancer detection in mammography.
METHODS AND MATERIALS: An observer study was performed using 349 digital mammography images of women with normal breasts, calcification clusters, or soft-tissue lesions including 191 subtle cancers. Images underwent two types of processing: FlavourA (standard) and FlavourB (added enhancement). Six observers located features in the breast they suspected to be cancerous (4,188 observations). Data were analysed using jackknife alternative free-response receiver operating characteristic (JAFROC) analysis. Characteristics of the cancers detected with each image processing type were investigated.
RESULTS: For calcifications, the JAFROC figure of merit (FOM) was equal to 0.86 for both types of image processing. For soft-tissue lesions, the JAFROC FOM were better for FlavourA (0.81) than FlavourB (0.78); this difference was significant (p=0.001). Using FlavourA a greater number of cancers of all grades and sizes were detected than with FlavourB. FlavourA improved soft-tissue lesion detection in denser breasts (p=0.04 when volumetric density was over 7.5%) CONCLUSIONS: The detection of malignant soft-tissue lesions (which were primarily invasive) was significantly better with FlavourA than FlavourB image processing. This is despite FlavourB having a higher contrast appearance often preferred by radiologists. It is important that clinical choice of image processing is based on objective measures.
引用
- Warren LM, Halling-Brown MD, Looney PT, et al. Image processing can cause some malignant soft-tissue lesions to be missed in digital mammography images. Clin Radiol. 2017. PMID: 28457521. doi:10.1016/j.crad.2017.03.024
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。