ISSN 1004-4140
CN 11-3017/P

食管癌CT影像组学研究进展

周健文, 冯峰

周健文, 冯峰. 食管癌CT影像组学研究进展[J]. CT理论与应用研究, 2022, 31(5): 687-696. DOI: 10.15953/j.ctta.2021.006.
引用本文: 周健文, 冯峰. 食管癌CT影像组学研究进展[J]. CT理论与应用研究, 2022, 31(5): 687-696. DOI: 10.15953/j.ctta.2021.006.
ZHOU J W, FENG F. Research progress on CT radiomics of esophageal cancer[J]. CT Theory and Applications, 2022, 31(5): 687-696. DOI: 10.15953/j.ctta.2021.006. (in Chinese).
Citation: ZHOU J W, FENG F. Research progress on CT radiomics of esophageal cancer[J]. CT Theory and Applications, 2022, 31(5): 687-696. DOI: 10.15953/j.ctta.2021.006. (in Chinese).

食管癌CT影像组学研究进展

详细信息
    作者简介:

    周健文: 女,东台市人民医院影像科主治医师,主要从事食管癌影像学诊断和研究,E-mail:813452668@qq.com

    冯峰: 男,南通大学附属肿瘤医院影像科主任医师、硕士生导师,主要从事肿瘤影像诊断和研究,E-mail:drfengfeng@163.com

  • 中图分类号: R  814;R  735.1

Research Progress on CT Radiomics of Esophageal Cancer

  • 摘要: 食管癌是全球最常见的癌症之一,具有较高的死亡率。CT影像组学是从CT图像中提取大量影像组学特征,进行高通量定量分析,从而获得更多有关肿瘤异质性的信息。近年来已逐步应用于食管癌临床分期、病理分化的预测,治疗疗效评估及预后评价等方面。本文围绕CT影像组学在食管癌中的应用及进展进行综述。
    Abstract: Esophageal cancer which results in a relatively higher death rate is one of the most common cancers throughout the world. CT radiomics is a study to extract radiomics characteristics which are generalized from a large amount of CT images. These characteristics then underwent high-throughput quantitative analysis so that more heterogeneity information of the caner can be obtained. CT radiomics has been gradually used in forecast clinical stages and pathological differentiation of esophageal cancer in recent years, and applied in assessment of treatment effect and prognosis evaluation as well. This paper focuses on the application of CT radiomics in esophageal cancer and its progress.
  • 尘肺病是我国危害严重的一类职业病,诊断和分期主要依靠高仟伏胸片,在临床诊断中需要X胸片和CT结合[1],CT在尘肺病的早期诊断、肺气肿分布范围和大小以及小阴影类型和密集度等检出率明显优于高仟伏X线胸片[2]。肺功能检查用于检测呼吸道的通畅程度、肺容量的大小及气体交换能力已作为评估尘肺病患者的肺功能的“金标准”[3]

    目前已有研究表明肺气肿程度与通气及弥散功能相关指标呈负相关;小阴影密集度越高及分布肺区越多,患者肺功能越差[4-5],但两者与肺功能之间的相关性对比暂无研究,因此本文研究尘肺患者合并不同程度肺气肿及小阴影密集度与肺功能的相关性。

    在关于慢性阻塞性肺疾病(chronic obstructive pulmonary disease,COPD)合并肺气肿与肺功能的影响研究中,将CT值<-950 HU定义为低密度衰减容量(low attenuation volume,LAV)[6],以低密度衰减区占肺容积的百分比(LAV%)作为评估尘肺患者肺气肿的严重程度。

    张雨洁等[7]将LAV%=15% 作为轻度及重度肺气肿的界限,而Frith等[8]研究提出当肺组织损伤大于30% 肺功能才表现异常,因此本研究参考这两项研究,96名患者分为A组:LAV%<15%,B组:LAV%>15% 且<30%;C组:LAV%>30%。

    选择2015至2020年间我院收治已确诊尘肺(符合GBZ 70-2015《职业性尘肺病的诊断》标准)的患者96例,年龄25~81岁,平均年龄(42.37+6.51)岁,接触粉尘的时间2~35年。

    纳入标准:患者病情稳定,非感染期,剔除存在肺结核、支气管扩张、重症肺炎、胸腔积液、肺部肿瘤或占位性病变、胸部外伤畸形、气胸和胸膜病变等肺部并发症等。患者均进行胸部CT检查和肺功能检查且要统一检查设备。

    采用64排螺旋CT(GE Optima CT 680)进行薄层扫描,每个层面清晰显示支气管及肺纹理,组织间对比良好。扫描参数:管电压120 kV,自动毫安(50~100 mA),层厚0.625 mm×64,螺距1.375︰1。深吸气末屏气扫描,扫描后肺窗由lung算法显示。

    采用肺功能测定仪(Type Master Screen-Body/Dift)进行肺功能测定,严格执行质量控制标准,确保用力肺活量外推容积<5% 或<150 mL,呼气时间≥6 s,曲线起始无犹豫,PEF尖峰迅速出现,呼气无中断,无咳嗽,曲线平滑,流量环闭合。

    弥散、残气检测采用一口气法,执行国际标准(ATS/ERS),憋气时间10 s,肺功能测量值包括第1 s用力呼气容积(forced expiratory volume in the first second,FEV1)、第1 s用力呼气量占用力肺活量比值(ratio of forced expiratory volume to forced vital capacity in the first second,FEV1%)、用力肺活量(forced vital capacity,FVC)、一氧化碳弥散量(carbon monoxide diffusion capacity,DLCO)、功能残气量(residual volume,RV)、肺总量(total lung capacity,TLC)、残气量与肺总量的比值(residual volume/Total lung capacity,RV/TLC)、呼气峰值流速(peak expiratory flow,PEF)、75% 肺活量时的最大呼气流速(maximum expiratory flow after 75% of the FVC has not been exhaled,MEF75%)、50% 肺活量时的最大呼气流速(maximum expiratory flow after 50% of the FVC has not been exhaled,MEF50%)和25% 肺活量时的最大呼气流速(maximum expiratory flow after 25% of the FVC has not been exhaled,MEF25%)。

    采用GE AW 4.6工作站及特定分析软件将深吸气末0.625 mm层厚的图像进行后处理,设定肺气肿的测量阈值为<-950 HU[6],肺部CT图像由气管纵向水平的冠状面上用等分点的水平线将左右肺各分为上、中、下3个肺野,取得全肺、左右肺及各个肺野低密度衰减区占肺容积百分比(low attenuation volume,LAV%)(图1),其中A组42名,B组29名,C组25名。同一患者肺部三维图像经后处理软件分析后得到的各肺野LAV%(表1)。

    图  1  分别为A、B、C组部分尘肺患者肺部CT冠状位图像及轴位图像,冠状位图像由气管纵向水平上用等分点的水平线将左右肺各分为上、中、下3个肺野,蓝色区域为肺气肿低衰减区三维图像
    Figure  1.  Coronal and axial CT images of some patients with pneumoconiosis in groups A, B, and C. The left and right lungs were divided into upper, middle, and lower lung fields from the vertical level of the trachea using equidistant horizontal lines; blue areas present emphysema as three-dimensional images of low-attenuation areas
    表  1  各肺野LAV% 数据表
    Table  1.  LAV% data for each lung field
    数据范围右肺 左肺
    右肺上野中野下野左肺上野中野下野
    -1024~-950/%24.03024.12022.42825.237 23.08023.05319.10526.269
    -950~3071/%75.97075.88177.57274.76376.92076.94780.89573.731
    Total/L4.3000.9841.4561.8603.3840.8431.1281.413
    下载: 导出CSV 
    | 显示表格

    由3位有尘肺病诊断资格的影像科医师进行阅片,肺部CT图像由气管纵向水平的冠状面上用等分点的水平线将左右肺各分为上、中、下3个肺野,取得CT图像的全肺、左右肺及各个肺野的小阴影密集度(small shadow density,SSD),其中SSD的评分方法参考GBZ 70-2015《职业性尘肺病诊断》[9]及翟荣存等[10]胸片密集度分级方法应用于CT,将SSD分为0、1、2和3级4个等级。

    使用SPSS 23.0软件包,非正态肺部计量资料M(Q25,Q75)表示,组间比较采用2个独立样本非参数检验,LAV%、SSD与肺功能的相关性采用Spearman相关分析或Pearson相关性分析,以P<0.05为差异有统计学意义。

    对96名尘肺患者左右肺、左右肺上、中、下肺野及上、中、下3个肺野间SSD、LAV% 进行组间两两对比,其中左右肺、左右肺上、中、下肺野SSD组间差异无统计学意义;左右肺3个肺野间SSD进行组间对比差异有统计学意义;A、B、C三组组间全肺总体SSD间对比差异均无统计学意义(表2)。

    表  2  A、B、C组组间总体SSD间差异性分析
    Table  2.  Comparison of the total SSD among groups A, B, and C
    项目SSD
    ABBCAC
    M(Q25,Q75)2(1,3)2(2,3)2(2,3)2(1,3)2(1,3)2(1,3)
    Z-0.454-0.373-0.537
    P 0.650 0.767 0.591
     注:M(Q25,Q75)为A、B、C三组总体小阴影密集度中位数及四分位数,组间对比不符合正态分布采用非参数检验得到P>0.05,
       3组总体小阴影密集度对比差异无统计学意义。
    下载: 导出CSV 
    | 显示表格

    全肺SSD与FEV1、TLC、PEF、MEF75%、MEF25%呈负相关,与RV/TLC呈正相关(r=-0.248、-0.244、-0.268、-0.217、-0.246、0.219)。右上中、左中下肺野SSD与FVC呈负相关(r=-0.209、-0.294、-0.258、-0.278);右下肺野SSD与FVC、TLC、PEF、MEF25%呈负相关(r=-0.291、-0.232、-0.209、-0.213);左上肺野SSD与RV/TLC呈正相关(r=0.204)。

    A组全肺、右上中、左上、B组总体、右上中下肺野、左上中下肺野、C组全肺、右上、左上SSD与肺功能各指标间无相关性,A组右下肺野、左中肺野SSD与FEV1、FVC呈负相关(r=-0.330、-0.388、-0.317、-0.501),A组左下肺野SSD与FVC呈负相关(r=-0.385);C组左右肺中下肺野SSD均与DLCO呈正相关(r=0.511、0.420、0.492、0.648);C组左下肺野SSD与RV呈负相关(r=-0.563)(表3表5)。

    表  3  A组各肺野SSD、LAV% 与肺功能指标的相关性分析
    Table  3.  Analysis of correlation between SSD and LAV% of the lung field and lung function indexes in group A
    A组右上右中右下左上左中左下
    SSDLAV%SSDLAV%SSDLAV%SSDLAV%SSDLAV%SSDLAV%
     FEV1-0.0990.019-0.157-0.093-0.330*-0.073-0.2280.132-0.317*-0.203-0.1720.065
     FEV1%0.159-0.0680.0370.060-0.124-0.159-0.0370.005-0.085-0.337*-0.0760.082
     FVC-0.2580.020-0.374*-0.034-0.388*-0.047-0.2960.084-0.501**-0.231-0.385*0.123
     DLCO0.035-0.022-0.007-0.0550.0530.119-0.077-0.0910.011-0.233-0.0790.268
     RV-0.0790.192-0.124-0.0480.0270.070-0.0360.194-0.0820.082-0.019-0.060
     TLC-0.0040.256-0.030-0.030-0.1520.080-0.0100.386*-0.0820.262-0.0020.008
     RV/TLC0.1400.0890.058-0.1990.187-0.1620.176-0.0250.1640.1790.171-0.148
     PEF0.020-0.034-0.144-0.145-0.267-0.083-0.0910.134-0.250-0.253-0.1220.057
     MEF75%-0.055-0.059-0.055-0.127-0.262-0.250-0.0610.048-0.225-0.322*-0.1060.097
     MEF50%-0.057-0.018-0.057-0.032-0.249-0.189-0.1100.048-0.213-0.310*-0.1650.114
     MEF25%-0.1160.040-0.1160.218-0.2510.107-0.0950.121-0.227-0.253-0.2860.106
     注:* 为P<0.05,**为P<0.01。
    下载: 导出CSV 
    | 显示表格
    表  4  B组各肺野SSD、LAV% 与肺功能指标的相关性分析
    Table  4.  Analysis of correlation between SSD and LAV% of the lung field and lung function indexes in group B
    B组右上右中右下左上左中左下
    SSDLAV%SSDLAV%SSDLAV%SSDLAV%SSDLAV%SSDLAV%
     FEV1-0.0530.247-0.149-0.036-0.096-0.314-0.1230.102-0.009-0.211-0.080-0.521*
     FEV1%-0.0240.314-0.1900.025-0.075-0.304-0.0740.128-0.104-0.133-0.147-0.615*
     FVC-0.179-0.078-0.263-0.177-0.079-0.133-0.209-0.038-0.009-0.111-0.161-0.407*
     DLCO0.0620.157-0.365-0.269-0.1540.0200.041-0.0250.239-0.227-0.288-0.224
     RV-0.170-0.095-0.024-0.1120.0480.035-0.227-0.025-0.069-0.1380.0090.009
     TLC-0.1490.155-0.056-0.020-0.268-0.270-0.2190.1960.147-0.038-0.041-0.113
     RV/TLC0.170-0.0920.187-0.1790.1910.450*0.118-0.1480.0390.0510.1200.321
     PEF0.0850.215-0.153-0.015-0.235-0.152-0.0440.0600.028-0.121-0.140-0.280
     MEF75%0.0720.266-0.0550.084-0.002-0.155-0.0330.0600.021-0.1330.013-0.478*
     MEF50%0.0480.201-0.067-0.1120.015-0.243-0.0180.037-0.004-0.259-0.043-0.533*
     MEF25%-0.1520.199-0.2140.024-0.162-0.180-0.2380.012-0.176-0.201-0.174-0.479*
     注:* 为P<0.05。
    下载: 导出CSV 
    | 显示表格
    表  5  C组各肺野SSD、LAV% 与肺功能指标的相关性分析
    Table  5.  Analysis of correlation between SSD and LAV% of the lung field and lung function indexes in group C
    C组右上右中右下左上左中左下
    SSDLAV%SSDLAV%SSDLAV%SSDLAV%SSDLAV%SSDLAV%
     FEV10.324-0.453*0.242-0.435*-0.126-0.555*0.030-0.575*0.053-0.554*0.149-0.519*
     FEV1%0.302-0.513*0.209-0.420*-0.007-0.532*0.076-0.552*0.068-0.581*0.205-0.389*
     FVC-0.1380.010-0.181-0.086-0.284-0.2050.036-0.137-0.042-0.156-0.102-0.291
     DLCO0.338-0.2820.511*-0.506*0.420*-0.503*0.395-0.3260.492*-0.523*0.648*-0.410*
     RV-0.3580.065-0.3150.2210.2600.347-0.1910.268-0.1990.490*-0.563*0.325
     TLC-0.033-0.2850.0430.085-0.362-0.110-0.248-0.414*-0.136-0.203-0.136-0.233
     RV/TLC0.1500.0420.0480.130-0.1340.2110.2420.1510.1970.2990.1150.332
     PEF0.250-0.535*0.069-0.324-0.211-0.469*-0.111-0.575*-0.069-0.476*0.003-0.530*
     MEF75%0.161-0.498*-0.036-0.297-0.266-0.423*-0.199-0.529*-0.178-0.395-0.053-0.496*
     MEF50%0.136-0.376-0.077-0.229-0.338-0.329-0.201-0.367-0.153-0.286-0.139-0.431*
     MEF25%0.040-0.312-0.031-0.202-0.377-0.298-0.221-0.306-0.114-0.239-0.141-0.404*
     注:* 为P<0.05。
    下载: 导出CSV 
    | 显示表格

    右肺上中下肺野、左肺上下及中下肺野LAV% 组间差异有统计学意义,左右肺、左肺上中肺野LAV% 间差异无统计学意义。A、B、C组中各肺野LAV% 间对比差异有统计学意义。

    A组左上肺野LAV% 与TLC呈正相关,左中肺野LAV% 与FEV1%、MEF75%、MEF50%呈负相关,左中肺野与FEV1、MEF75%、MEF50% 呈负相关;B组左下肺野LAV% 与FEV1、FEV1%、MEF75%、MEF50%、MEF25% 呈负相关,右下肺野LAV% 与RV/TLC呈正相关;C组左右肺上肺野LAV% 与FEV1、 FEV1%、PEF、MEF75% 呈负相关,左下肺野LAV% 与FEV1、FEV1%、DLCO、PEF、MEF75%、MEF50%、MEF25% 呈负相关,右下肺野LAV% 与FEV1、FEV1%、DLCO、PEF、MEF75% 呈负相关,左中肺野LAV% 与FEV1、FEV1%、DLCO、PEF呈负相关,与RV呈正相关;右中肺野LAV% 与FEV1、FEV1%、DLCO呈负相关(表3表5)。

    尘肺是一种对社会和患者家庭带来沉重负担及严重威胁患者身体健康的一种职业病。尘肺患者早期多无症状,胸部CT影像学可表现为小阴影、大阴影、肺气肿、胸膜改变及蜂窝状等,且CT征象与肺功能分级呈正相关。由于目前临床有部分尘肺患者影像学肺组织损伤程度较轻,但肺功能测值却严重受损,而部分患者CT影像学阴影明显,肺功能检查却无明显改变,呈现肺功能与阴影影像学改变的不匹配,因此本研究探索比较肺部CT阴影及肺气肿表现对肺功能的影响,以期找出对尘肺患者肺功能损伤高效、适用的评估方法,提高基层对尘肺的认识、指导临床诊疗。

    肺气肿是肺部的一种病理状态,主要病理改变为细支气管远端持续气道异常扩大,同时支气管壁不同程度破坏,严重影响患者的生活质量。早期诊断肺气肿对改善尘肺患者预后非常重要。对本研究中96名患者SSD纵向分布对比后发现几乎所有患者肺气肿分布在上肺野居多,中肺野次之,下肺野分布最少,可能与下肺野胸膜腔分压较中上肺野小,此压力梯度造成上肺野气体潴留较多;此外肺血管重塑易发生于上肺的说法也是肺气肿形成的重要原因[11]

    全肺、左右肺及各肺野LAV% 与FEV1、FEV1%、PEF、MEF75%、MEF50%、MEF25% 间均呈负相关,随LAV% 升高,肺功能上述指标呈明显下降趋势,肺通气功能下降,可能与随着肺气肿程度加重,气道壁破坏纤维化更加严重,导致气流受限从而使通气功能下降有关;与RV、RV/TLC呈正相关,即随着LAV% 的升高,肺容积参数增大,与肺气肿时终末细支气管远端过度扩张导致残气量及肺容积增大有关,与既往研究一致[12-13]

    不同肺野组间比较结果显示下肺野LAV% 与FEV1、PEF、MEF75%、MEF50%、MEF25% 等指标相关性均大于上中肺叶,一定程度说明下叶肺气肿对肺通气功能影响更大,考虑与下肺呼吸动度较中上肺大,下肺病变对肺顺应性影响更大有关。C组中除左、右肺上肺野LAV% 与DLCO无相关性外,其余各肺野LAV% 均与DLCO有较强的相关性,96名患者中、下肺野LAV% 与DLCO相关性均大于上肺叶,可能与当肺气肿多分布于上叶时气体交换少,导致通气/血流比例失调,从而不会引起肺弥散功能变化有关,说明中、下肺野与肺弥散功能相关性较高。

    综合以上结果提示下叶肺部病变特别是存在肺气肿时更容易导致肺功能指标的变化,从而反映肺损伤的程度,此研究与王雷等[13]、兰长青等[14]研究结果部分一致。

    本研究中A组仅左中肺野LAV% 与FEV1%、MEF75%、MEF50% 有弱负相关性,表明当LAV%<15% 时,肺气肿与肺功能之间的相关性较小,说明多层螺旋CT及后处理技术较肺功能更早的发现肺气肿,并能快速对肺气肿进行定位定量分析[15]。B组中仅左下肺野LAV%与FEV1、FEV1%、MEF75%、MEF50%、MEF25% 呈负相关,右下肺野与RV/TLC呈正相关,表明下肺野肺气肿较上中肺野更早反映肺功能变化及肺组织损伤程度。

    与X线相比,CT扫描所见阴影要比X线平片显示范围广,尤其对纵隔和心影后的特殊部位的小阴影显示更有优势。也有研究表明CT与X线胸片对总体小阴影密集度的判定存在高度一致,但对于上、下肺野的病变显示多于X线胸片,右中肺野病变显示少于X线胸片,考虑与上、下肺野体积所占总体积比例小,病变数量相对较少,CT在横断面更能清楚显示小阴影数量,导致CT对小阴影密集度判定比X线胸片更准确;右中肺野因与右侧胸大肌重叠导致小阴影密集度增高[16]

    本研究96名患者上肺野SSD值普遍较中下肺野SSD值大,小阴影多分布于上肺野,可能与上肺及肺的后部淋巴引流缓慢使粉尘清除能力较弱粉尘沉积有关[17-18]。全肺总体SSD与FEV1、PEF、MEF75%、MEF25% 呈负相关,与RV/TLC呈正相关,说明随着肺部小阴影密集度的升高,会逐渐引起肺通气功能下降,且可能合并小气道的病变,与粉尘滞留在肺泡与支气管内不断被巨噬细胞吞噬、释放,反复炎性渗出导致肺小血管、肺泡间隔等纤维化引起肺通气功能下降。

    在A、B、C三组中仅A组右下肺野、左中肺野与FEV1、FVC呈弱负相关性,A组左下肺野SSD与FVC呈负相关,C组右中肺野、左中下肺野SSD与DLCO呈正相关,研究结果表明当LAV%<30%时小阴影密集度对肺功能影响较小,即使CT表现为弥漫性小阴影,但肺功能仍可无明显异常;仅当LAV>30% 时,小阴影密集度与弥散功能有一定相关性。C组小阴影密集度、肺气肿与肺功能间相关性均较A组和B组强,表明当LAV%>30% 时,肺通气功能会受到严重损伤超过肺组织代偿能力后出现肺功能指标异常。

    综上所述,CT定量分析评价肺气肿是可行的,LAV% 与FEV1、FEV1%、DLCO、PEF、MEF75%、MEF50%、MEF25% 呈负相关,LAV% 与肺功能的相关性较SSD强,LAV% 一定程度上可反映尘肺患者肺损伤程度,且肺气肿比小阴影密集度与肺功能相关性更好,结合CT影像检查能够更精准的诊断尘肺病,评估肺损伤程度,并在尘肺病的临床诊断与治疗评估上也有重要的指导价值。

  • [1]

    UHLENHOPP D J, THEN E O, SUNKARA T, et al. Epidemiology of esophageal cancer: Update in global trends, etiology and risk factors[J]. Clinical Journal of Gastroenterol, 2020, 13(6): 1010−1021. doi: 10.1007/s12328-020-01237-x

    [2]

    SHAO D, VOGTMANN E, LIU A, et al. Microbial characterization of esophageal squamous cell carcinoma and gastric cardia adenocarcinoma from a high-risk region of China[J]. Cancer, 2019, 125(22): 3993−4002. doi: 10.1002/cncr.32403

    [3]

    OU J, LI R, ZENG R, et al. CT radiomic features for predicting resectability of oesophageal squamous cell carcinoma as given by feature analysis: A case control study[J]. Cancer Imaging, 2019, 19(1): 66. doi: 10.1186/s40644-019-0254-0

    [4]

    HE H, CHEN N, HOU Y, et al. Trends in the incidence and survival of patients with esophageal cancer: A SEER database analysis[J]. Thoracic Cancer, 2020, 11(5): 1121−1128. doi: 10.1111/1759-7714.13311

    [5]

    SCHLOTTMANN F, GABER C, STRASSLE P D, et al. Disparities in esophageal cancer: Less treatment, less surgical resection, and poorer survival in disadvantaged patients[J]. Diseases of the Esophagus, 2020, 33(2): 1−9.

    [6]

    Van TIMMEREN J E, CESTER D, TANADINI-LANG S, et al. Radiomics in medical imaging—“how-to”guide and critical reflection[J]. Insights into Imaging, 2020, 11(1): 91. doi: 10.1186/s13244-020-00887-2

    [7]

    DING H, WU C, LIAO N, et al. Radiomics in oncology: A 10-year bibliometric analysis[J]. Frontiers in Oncology, 2021, 11: 689802. doi: 10.3389/fonc.2021.689802

    [8]

    LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: Extracting more information from medical images using advanced feature analysis[J]. European Journal of Cancer, 2012, 48(4): 441−446. doi: 10.1016/j.ejca.2011.11.036

    [9]

    MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. The Journal of Nuclear Medicine, 2020, 61(4): 488−495. doi: 10.2967/jnumed.118.222893

    [10]

    ORLHAC F, FROUIN F, NIOCHE C, et al. Validation of a method to compensate multicenter effects affecting CT radiomics[J]. Radiology, 2019, 291(1): 53−59. doi: 10.1148/radiol.2019182023

    [11]

    BIBAULT J E, XING L, GIRAUD P, et al. Radiomics: A primer for the radiation oncologist[J]. Cancer Radiother, 2020, 24(5): 403−410. doi: 10.1016/j.canrad.2020.01.011

    [12]

    BERENGUER R, PASTOR-JUAN M D R, CANALES-VÁZQUEZ J, et al. Radiomics of CT features maybe nonreproducible and redundant: Influence of CT acquisition parameters[J]. Radiology, 2018, 288(2): 407−415. doi: 10.1148/radiol.2018172361

    [13]

    AERTS H J W L. Data science in radiology: A path forward[J]. Clinical Cancer Research, 2018, 24(3): 532−534. doi: 10.1158/1078-0432.CCR-17-2804

    [14]

    JAYAPRAKASAM V S, YEH R, KU G Y, et al. Role of imaging in esophageal cancer management in 2020: Update for radiologists[J]. American Journal of Roentgenology, 2020, 215(5): 1072−1084. doi: 10.2214/AJR.20.22791

    [15]

    HUANG F L, YU S J. Esophageal cancer: Risk factors, genetic association, and treatment[J]. Asian Journal of Surgery, 2018, 41(3): 210−215. doi: 10.1016/j.asjsur.2016.10.005

    [16]

    WU L, WANG C, TAN X, et al. Radiomics approach for preoperative identification of stages Ⅰ-Ⅱ and Ⅲ-Ⅳ of esophageal cancer[J]. Chinese Journal of Cancer Research, 2018, 30(4): 396−405. doi: 10.21147/j.issn.1000-9604.2018.04.02

    [17] 朱宗明, 冯银波, 陶广宇, 等. 基于CT图像纹理分析方法对胸段食管癌术前T分期的研究价值[J]. 临床放射学杂志, 2019,38(3): 72−76. DOI: 10.13437/j.cnki.jcr.2019.01.016.

    ZHU Z M, FEN Y B, TAO G Y, et al. The value of CT image texture analysis for preoperative T staging of thoracic esophageal cancer[J]. Journal of Clinical Radiology, 2019, 38(3): 72−76. DOI: 10.13437/j.cnki.jcr.2019.01.016. (in Chinese).

    [18] 杨耀华, 樊斌. 基于增强CT扫描成像的灰度共生矩阵纹理分析不同T分期食管鳞状细胞癌[J]. 临床放射学杂志, 2017,36(9): 1275−1278. DOI: 10.13437/j.cnki.jcr.2017.09.018.

    YANG Y H, FAN B. Assessment of T staging of esophageal squamous cell carcinoma by using GLCM texture analysis: Contrast-enhanced CT texture[J]. Journal of Clinical Radiology, 2017, 36(9): 1275−1278. DOI: 10.13437/j.cnki.jcr.2017.09.018. (in Chinese).

    [19]

    LIU J, WANG Z, SHAO H, et al. Improving CT detection sensitivity for nodal metastases in oesophageal cancer with combination of smaller size and lymph node axial ratio[J]. European Radiology, 2018, 28(1): 188−195. doi: 10.1007/s00330-017-4935-4

    [20]

    YUKAWA N, AOYAMA T, TAMAGAWA H, et al. The lymph node ratio is an independent prognostic factor in esophageal cancer patients who receive curative surgery[J]. In Vivo, 2020, 34(4): 2087−2093. doi: 10.21873/invivo.12012

    [21]

    TAN X, MA Z, YAN L, et al. Radiomics nomogram outperforms size criteria in discriminating lymph node metastasis in resectable esophageal squamous cell carcinoma[J]. European Radiology, 2019, 9(1): 392−400.

    [22]

    SHEN C, LIU Z, WANG Z, et al. Building CT radiomics based nomogram for preoperative esophageal cancer patients lymph node metastasis prediction[J]. Translational Oncology, 2018, 11(3): 815−824. doi: 10.1016/j.tranon.2018.04.005

    [23]

    OU J, WU, L, LI R, et al. CT radiomics features to predict lymph node metastasis in advanced esophageal squamous cell carcinoma and to discriminate between regional and non-regional lymph node metastasis: A case control study[J]. Quantitative Imaging in Medicine and Surgery, 2021, 11(2): 628−640. doi: 10.21037/qims-20-241

    [24]

    WU L, YANG X, CAO W, et al. Multiple level CT radiomics features preoperatively predict lymph node metastasis in esophageal cancer: A multicentre retrospective study[J]. Frontiers in Oncology, 2019, 9: 1548.

    [25] 程蕾舒, 吴磊, 陈舒婷, 等. 基于CT影像组学对食管鳞状细胞癌病理分化程度的预测[J]. 中南大学学报(医学版), 2019,44(3): 251−256. DOI: 10.11817/j.issn.1672-7347.2019.03.004.

    CHENG L S, WU L, CHEN S T, et al. CT-based radiomics analysis for evaluating the differentiation degree of esophageal squamous carcinoma[J]. Journal of Central South University (Medical Science), 2019, 44(3): 251−256. DOI: 10.11817/j.issn.1672-7347.2019.03.004. (in Chinese).

    [26]

    WANG Y F, YANG Y L, SUN J W, et al. Development and validation of the predictive model for esophageal squamous cell carcinoma differentiation degree[J]. Frontiers in Genetics, 2020, 11: 595638. doi: 10.3389/fgene.2020.595638

    [27]

    KAWAHARA D, MURAKAMI Y, TANI S, et al. A prediction model for degree of differentiation for resectable locally advanced esophageal squamous cell carcinoma based on CT images using radiomics andmachine-learning[J]. British Journal of Radiology, 2021, 94: 20210525. doi: 10.1259/bjr.20210525

    [28]

    RUAN R, CHEN S, TAO Y, et al. A nomogram for predicting lymphovascular invasion in superficial esophageal squamous cell carcinoma[J]. Frontiers in Oncology, 2021, 11: 663802. doi: 10.3389/fonc.2021.663802

    [29]

    LI Y, YU M, WANG G, et al. Contrast-enhanced CT-based radiomics analysis in predicting lymphovascular invasion in esophageal squamous cell carcinoma[J]. Frontiers in Oncology, 2021, 11: 644165. doi: 10.3389/fonc.2021.644165

    [30]

    LENG X F, DAIKO H, HAN Y T, et al. Optimal preoperative neoadjuvant therapy for resectable locally advanced esophageal squamous cell carcinoma[J]. Annals of the New York Academy of Sciences, 2020, 1482(1): 213−224. doi: 10.1111/nyas.14508

    [31]

    YANG Z, HE B, ZHUANG X, et al. CT-based radiomic signatures for prediction of pathologic complete response in esophageal squamous cell carcinoma after neoadjuvant chemoradiotherapy[J]. Journal Radiation Research, 2019, 60(4): 538−545. doi: 10.1093/jrr/rrz027

    [32]

    HU Y, XIE C, YANG H, et al. Assessment of intratumoral and peritumoral computed tomography radiomics for predicting pathological complete response to neoadjuvant chemoradiation in patients with esophageal squamous cell carcinoma[J]. JAMA Network Open, 2020, 3(9): e2015927. DOI: 10.1001/jamanetworkopen.2020.15927.

    [33]

    HU Y, XIE C, YANG H, et al. Computed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma[J]. Radiotherapy and Oncology, 2021, 154: 6−13. doi: 10.1016/j.radonc.2020.09.014

    [34]

    LI N, LUO P, LI C, et al. Analysis of related factors of radiation pneumonia caused by precise radiotherapy of esophageal cancer based on random forest algorithm[J]. Mathematical Biosciences and Engineering, 2021, 18(4): 4477−4490. doi: 10.3934/mbe.2021227

    [35]

    DU F, LIU H, WANG W, et al. Correlation between lung density changes under different dose gradients and radiation pneumonitis−Based on an analysis of computed tomography scans during esophageal cancer radiotherapy[J]. Frontiers in Oncology, 2021, 11: 650764. doi: 10.3389/fonc.2021.650764

    [36]

    DU F, TANG N, CUI Y, et al. A novel nomogram model based on cone-beam CT radiomics analysis technology for predicting radiation pneumonitis in esophageal cancer patients undergoing radiotherapy[J]. Frontiers in Oncology, 2020, 10: 596013. doi: 10.3389/fonc.2020.596013

    [37]

    WANG L, GAO Z, LI C, et al. Computed tomography-based delta-radiomics analysis for discriminating radiation pneumonitis in patients with esophageal cancer after radiation therapy[J]. International Journal Radiation Oncology Biology Physics, 2021, 111(2): 443−455. doi: 10.1016/j.ijrobp.2021.04.047

    [38]

    HAN L, GAO Q L, ZHOU X M, et al. Characterization of CD103+CD8+tissue‑resident T cells in esophageal squamous cell carcinoma: May be tumor reactive and resurrected by anti-PD-1 lockade[J]. Cancer Immunology Immunotherapy, 2020, 69(8): 1493−1504. doi: 10.1007/s00262-020-02562-3

    [39]

    KUO H Y, GUO J C, HSU C H. Anti-PD-1 immunotherapy in advanced esophageal squamous cell carcinoma: A longawaited breakthrough finally arrives[J]. Journal Formosan Medical Association, 2020, 119(2): 565−568. doi: 10.1016/j.jfma.2019.10.010

    [40]

    WEN Q, YANG Z, ZHU J, et al. Pretreatment CT-based radiomics signature as a potential imaging biomarker for predicting the expression of PD-L1 and CD8+TILs in ESCC[J]. Onco Targets and Therapy, 2020, 13: 12003−12013. doi: 10.2147/OTT.S261068

    [41]

    GULLO R L, DAIMIEL I, MORRIS E A, et al. Combining molecular and imaging metrics in cancer: Radiogenomics[J]. Insights into Imaging, 2020, 11(1): 1. doi: 10.1186/s13244-019-0795-6

    [42]

    XIE C Y, HU Y H, HO J W, et al. Using genomics feature selection method in radiomics pipelineimproves prognostication performance in locally advanced esophageal squamous cell carcinoma−A pilot study[J]. Cancers (Basel), 2021, 13(9): 2145. doi: 10.3390/cancers13092145

    [43]

    LINDENMANN J, FEDIUK M, FINK-NEUBOECK N, et al. Hazard curves for tumor recurrence and tumor related death following esophagectomy for esophageal cancer[J]. Cancers (Basel), 2020, 12: 2066. doi: 10.3390/cancers12082066

    [44]

    QIU Q, DUAN J, DENG H, et al. Development and validation of a radiomics nomogram model for predicting postoperative recurrence in patients with esophageal squamous cell cancer who achieved pCR after neoadjuvant chemoradiotherapy followed by surgery[J]. Frontiers in Oncology, 2020, 10: 1398. doi: 10.3389/fonc.2020.01398

    [45] 王大伟, 董婷宇, 霍志云, 等. CT增强图像纹理分析对食管癌术后早期复发转移的预测价值[J]. 实用医学杂志, 2020,36(11): 1525−1529. DOI: 10.3969/j.issn.1006-5725.2020.11.023.

    WANG D W, DONG T Y, HUO Z Y, et al. Predictive value of texture analysis based on enhanced CT images for early recurrence and metastasis of esophageal squamous cell carcinoma after surgery[J]. The Journal of Practical Medicine, 2020, 36(11): 1525−1529. DOI: 10.3969/j.issn.1006-5725.2020.11.023. (in Chinese).

    [46]

    FORNACON-WOOD I, MISTRY H, ACKERMANN C J, et al. Reliability and prognostic value of radiomic features are highly dependent on choice of feature extraction platform[J]. European Radiology, 2020, 30(11): 6241−6250. doi: 10.1007/s00330-020-06957-9

  • 期刊类型引用(4)

    1. 黄费湘. 多层螺旋CT多平面重建技术与数字化X线摄影对尘肺患者的诊断及其征象分析. 现代医用影像学. 2024(06): 1025-1027 . 百度学术
    2. 年洪慧. 青海省海西州尘肺病主要特征及其CT影像表现分析. 实用医学影像杂志. 2024(03): 175-178 . 百度学术
    3. 周琅,袁梅,谢丽庄,韩磊,鲁珊珊. 尘肺病患者肺部CT特征与肺功能关联性研究进展. 职业卫生与应急救援. 2024(05): 676-679 . 百度学术
    4. 黄宁,伍武,黄建桂. MSCT对粉尘作业引起的肺部弥漫性小结节的诊断及随访价值研究. 中国现代药物应用. 2023(24): 69-72 . 百度学术

    其他类型引用(1)

计量
  • 文章访问数:  551
  • HTML全文浏览量:  236
  • PDF下载量:  64
  • 被引次数: 5
出版历程
  • 收稿日期:  2021-09-25
  • 录用日期:  2022-01-11
  • 网络出版日期:  2022-01-26
  • 发布日期:  2022-09-30

目录

/

返回文章
返回
x 关闭 永久关闭