Can algorithmically assessed MRI features predict which patients with a preoperative diagnosis of ductal carcinoma in situ are upstaged to invasive breast cancer?

Can algorithmically assessed MRI features predict which patients with a preoperative diagnosis of ductal carcinoma in situ are upstaged to invasive breast cancer?
复制标题

DOI:
10.1002/jmri.25655
复制
发表时间:
2017-11
期刊:
Journal of magnetic resonance imaging : JMRI
影响因子:
--
通讯作者:
Mazurowski MA
Mazurowski MA
中科院分区:
其他
文献类型:
--
作者:
Harowicz MR;Saha A;Grimm LJ;Marcom PK;Marks JR;Hwang ES;Mazurowski MA

文献摘要

参考文献

被引文献

相似文献

评估算法评估的磁共振成像(MRI)特征预测新诊断的导管原位癌(DCIS)升级为浸润性癌的可能性的能力。我们确定了2000年至2014年在我们机构进行的131例患者,这些患者经空芯针活检确诊为纯DCIS,术前双侧乳腺MRI采用非脂肪饱和T1加权MRI序列进行1.5或3 T扫描,乳腺MRI前未接受术前治疗,既往无乳腺癌病史。一名接受过研究员培训的放射科医生使用边界框在每个乳腺MRI上识别病变。然后使用基于放射科医生注释的计算机算法自动计算29个成像特征。本研究中DCIS向浸润癌的升级率为26.7%(35/131)。在测试的所有成像变量中,相关性1的信息度量(其量化了肿瘤相邻体素的空间依赖性)显示出最高的预测值,曲线下面积(AUC)= 0.719(95%置信区间[Cl]:0.609-0.829)。校正肿瘤大小后,该特征具有统计学显著性(P < 0.001)。自动评估的MRI特征可能在分类中发挥作用,术前诊断为DCIS的患者发生隐匿性浸润性疾病的风险最高。4
To assess the ability of algorithmically assessed magnetic resonance imaging (MRI) features to predict the likelihood of upstaging to invasive cancer in newly diagnosed ductal carcinoma in situ (DCIS). We identified 131 patients at our institution from 2000–2014 with a core needle biopsy-confirmed diagnosis of pure DCIS, a 1.5 or 3T preoperative bilateral breast MRI with nonfat-saturated T1-weighted MRI sequences, no preoperative therapy before breast MRI, and no prior history of breast cancer. A fellowship-trained radiologist identified the lesion on each breast MRI using a bounding box. Twenty-nine imaging features were then computed automatically using computer algorithms based on the radiologist’s annotation. The rate of upstaging of DCIS to invasive cancer in our study was 26.7% (35/131). Out of all imaging variables tested, the information measure of correlation 1, which quantifies spatial dependency in neighboring voxels of the tumor, showed the highest predictive value of upstaging with an area under the curve (AUC) = 0.719 (95% confidence interval [Cl]: 0.609–0.829). This feature was statistically significant after adjusting for tumor size (P < 0.001). Automatically assessed MRI features may have a role in triaging which patients with a preoperative diagnosis of DCIS are at highest risk for occult invasive disease. 4
通过血氧水平依赖性磁共振成像评估碘对比度诱导的急性肾损伤敏感大鼠的肾内充氧。
DOI: 10.1097/rli.0000000000000031
发表时间: 2014-06
影响因子: 6.7
作者:
Li LP;Lu J;Zhou Y;Papadopoulou MV;Franklin T;Bokhary U;Solomon R;Sen A;Prasad PV
通讯作者: Prasad PV
DOI: 10.1371/journal.pone.0063573
发表时间: 2013
期刊: PloS one
影响因子: 3.7
作者:
Kaimori JY;Iwai S;Hatanaka M;Teratani T;Obi Y;Tsuda H;Isaka Y;Yokawa T;Kuroda K;Ichimaru N;Okumi M;Yazawa K;Rakugi H;Nonomura N;Takahara S;Kobayashi E
通讯作者: Kobayashi E
DOI: 10.1186/1471-2369-14-146
发表时间: 2013-07-13
期刊: BMC nephrology
影响因子: 2.3
作者:
Koo HM;Doh FM;Ko KI;Kim CH;Lee MJ;Oh HJ;Han SH;Kim BS;Yoo TH;Kang SW;Choi KH
通讯作者: Choi KH
DOI: 10.1097/rli.0b013e31822311a9
发表时间: 2011-11-01
影响因子: 6.7
作者:
Ladwig, Mechthild;Flemming, Bert;Persson, Pontus B.
通讯作者: Persson, Pontus B.
DOI: 10.1016/j.lfs.2014.03.030
发表时间: 2014-05-17
期刊: LIFE SCIENCES
影响因子: 6.1
作者:
Ulusoy, Sukru;Ozkan, Gulsum;Yucesan, Fulya Balaban
通讯作者: Yucesan, Fulya Balaban