CT影像组学标签预测局部进展期胃癌新辅助化疗疗效的多中心分析

目的 通过多中心研究探讨基于CT图像的影像组学在治疗前预测局部进展期胃癌新辅助化疗疗效的价值。方法 选取两家不同省份肿瘤医院从2013年6月～2020年11月接受新辅助化疗并行根治性手术的312例胃癌患者。根据术后病理组织学评估,将所有的患者分为新辅助化疗反应良好组和反应不良组。手动勾画每例患者图像病灶最大区域并提取2164个特征,经可重复性分析及支持向量机递归特征消除算法最终选出4个特征,利用逻辑回归模型构建影像组学标签。另外,通过多因素Logisitc回归分析患者的临床病理资料,预测新辅助治疗反应的价值。结果 影像组学标签在训练集上预测胃癌新辅助化疗反应良好的ROC曲线下面积、敏感度、特异度、准确度分别为0.786(95%CI:0.679～0.894)、0.722、0.833、0.778,在验证集上分别为0.759(95%CI:0.656～0.863)、0.821、0.631、0.679。多因素Logistic回归显示临床病理学因素不是胃癌新辅助化疗疗效的独立预测因子。结论 CT影像组学标签可作为预测胃癌新辅助化疗疗效的一种新型生物标记物,具有较好的预测效能。     

CT影像组学联合炎症指标构建逻辑回归模型预测食管鳞癌新辅助化疗疗效

【摘要】目的：探究基于CT影像组学联合血液学炎症指标构建逻辑回归模型预测食管鳞癌新辅助化疗（NAC）疗效的可行性。方法：回顾性分析两家医院经病理证实的54例食管鳞癌患者在术前规范化NAC前、后两次胸部CT增强图像及NAC前一周内的血液学炎症指标检测结果。测量治疗前、后病灶的最长径,计算其变化率,并根据实体肿瘤疗效评价标准（RECIST 1.1）,将患者分为NAC有效组（30例）及无效组（24例）。采用独立样本t检验或Mann-Whitney U检验筛选血液学炎症指标中与疗效相关的因素。在患者治疗前静脉期图像上沿肿瘤边界逐层手工勾画ROI,最终生成三维感兴趣区（VOI）并提取其影像组学特征,使用最小冗余最大相关及Boruta工具包进行特征筛选并构建影像组学标签。分别建立影像组学特征、血液学炎症指标、影像组学标签联合血液学炎症指标的逻辑回归模型,采用混淆矩阵和ROC曲线分析模型对NAC疗效的预测效能,采用DCA曲线评估其临床实用价值。结果：外周血淋巴细胞计数及淋巴细胞数与单核细胞数的比值被纳入炎症指标模型。于治疗前静脉期图像上共提取了1168个组学特征,经降维后共筛选出5个影像组学特征（wavelet-HLL_gldm_DependenceEntropy、wavelet-HHL_gldm_LargeDependenceLowGrayLevelEmphasis、wavelet-HHH_glrlm_HighGrayLevelRunEmphasis、wavelet-HHH_glrlm_LowGrayLevelRunEmphasis和wavelet-HLL_glszm_ZoneEntropy）用于构建影像组学标签。基于影像组学、血液学炎症指标以及联合模型预测NAC疗效的的AUC分别为0.77、0.72和0.80。结论：基于新辅助化疗前的增强CT影像组学及血液学炎症指标特征构建的预测模型可较好的预测食管鳞癌患者新辅助化疗疗效,以联合模型的效能最优,可为临床制订个性化治疗方案提供参考。     

CT影像组学预测胰腺导管腺癌患者术后无病生存期的价值

【摘要】目的：探讨基于平扫和三期增强CT的影像组学模型及临床-组学综合模型对胰腺导管腺癌（PDAC）患者术后无病生存期（DFS）的预测价值。方法：回顾性分析2013年12月－2021年6月在本院经术后病理证实的124例胰腺导管腺癌患者的病例资料。所有DFS患者术后随访时间大于3个月。采用随机分组法,按照7:3的比例将患者分为训练集（n=87）和验证集（n=37）。所有患者术前行腹部CT平扫及三期（动脉期、静脉期、延迟期）增强扫描。使用ITK-SNAP软件分别在四期CT图像上沿胰腺肿瘤边缘逐层勾画ROI并融合生成三维容积ROI（VOI）,然后导入FAE软件中提取影像组学特征。采用单因素Cox回归分析及LASSO-Cox回归分析进行纹理特征的筛选,然后分别构建各期和多期联合（动脉期+静脉期+延迟期）影像组学模型并计算相应的影像组学标签得分。采用单因素和多因素Cox回归分析筛选临床特征和CT形态学特征并构建临床模型。采用多因素Cox回归分析结合临床模型变量及影像组学标签构建临床-组学综合模型并绘制其诺莫图。采用一致性指数（C-index）、时间依赖性（time-dependent）ROC曲线、校正曲线和决策曲线分析（DCA）对模型的诊断效能及临床效益进行评价。利用R语言计算临床-组学综合模型的最佳截断值,并据此将患者分为高风险组和低风险组,采用Kaplan-Meier法分析生存资料并进行log-rank检验。结果：基于平扫、动脉期、静脉期和延迟期及多期联合分别筛选得到5、16、4、12和17个组学特征,分别建立相应的组学模型并获得影像组学标签值。经log-rank检验,所有组学标签均与DFS具有相关性（P<0.05）,其中多期联合模型的预测效能最佳（训练集：C-index=0.786,6~24个月AUC=0.850~0.928;验证集：C-index=0.802,6~24个月AUC=0.796~0.874）;而临床模型的预测效能较低（训练集：C-index=0.635,6~24个月AUC=0.647~0.679;验证集：C-index=0.596,6~24个月AUC=0.545~0.656）。临床-组学综合模型的预测效能（训练集：C-index=0.812,6~24个月AUC=0.883~0.958;验证集：C-index=0.796,6~24个月AUC=0.813~0.894）明显优于临床模型;校准曲线显示临床-组学综合模型的拟合度好;DCA显示临床-组学综合模型的临床净收益优于临床模型。临床-组学综合模型的截断值为2.738。Kaplan-Meier生存分析显示在训练集和验证集中,高风险组患者的DFS明显短于低分风险组。结论：基于多期CT扫描的影像组学模型结合临床特征构建的临床-组学综合模型在预测胰腺导管腺癌患者术后DFS方面,相较于临床模型和影像组学模型具有更好的预测效能,有助于指导临床制订个体化的治疗策略和改善患者的预后。     

多方位MRI影像组学预测局部进展期直肠癌新辅助放化疗疗效

目的:采用MRI影像组学方法,提取局部进展期直肠癌(LARC)病灶影像组学特征,并联合临床及常规影像特征构建预测模型,探讨模型对新辅助放化疗(nCRT)疗效的预测效能。方法:回顾性分析209例LARC患者nCRT前的临床及影像资料。LARC患者在nCRT后6～8周行全系膜切除术(TME),并评估肿瘤病理退缩分级(TRG)。按疗效分为nCRT反应良好组(TRG0～1级)和反应不良组(TRG2～3级),按照1:1随机分为训练组和验证组对模型进行内部验证。手动勾画T₂WI序列横轴面(TRA)、矢状面(SAG)及冠状面(COR)图像提取影像组学特征,采用LASSO回归筛选特征并构建影像组学标签。通过多因素logistics分析筛选nCRT疗效的独立预测因子并构建联合预测模型,采用ROC曲线及校正曲线对模型进行评估,并使用临床决策曲线评价模型的临床价值。结果:209例患者中nCRT反应良好组61例,反应不良组148例。T₂WI序列横轴面、矢状面、冠状面图像各提取379个影像组学特征,ICC为0.9的特征中TRA 96个,SAG 88个,COR 91个。...     

基于MRI影像组学构建新辅助放化疗后局部进展期直肠癌的预测模型

目的 探讨MRI影像组学模型、临床模型和综合模型对局部进展期直肠癌(LARC)新辅助放化疗(n CRT)疗效的预测价值。资料与方法 回顾性收集2017年1月—2021年12月在河南中医药大学第一附属医院行n CRT后行根治性手术的140例LARC患者的临床病理和影像资料,其中病理完全缓解(p CR)108例、无病理完全缓解(np CR)32例,以7∶3随机分为训练组99例和验证组41例。所有患者治疗前均行直肠MRI检查,收集、提取并筛选患者的：(1)临床特征,包括年龄、性别、癌胚抗原、糖类抗原199、血管通透性参数(K^trans、K_ep、V_e)等;(2)MRI影像组学特征;构建临床模型、影像组学模型及影像组学标签与临床特征相结合的综合模型。采用受试者工作特征曲线下面积(AUC)评估临床、影像组学和综合模型的预测效能,采用决策曲线分析法评价3种模型的临床获益情况,并构建疗效预测的诺模图。结果 训练组中,pCR和np CR患者的K_ep差异有统计学意义(t=3.862,P<0.000 1);验证组中...     

CT影像组学模型预测CNLC Ⅰ～Ⅱ期肝细胞癌切除术后早期复发的研究

目的 建立术前CT影像组学预测模型对中国肝癌分期(CNLC)Ⅰ～Ⅱ期肝细胞癌(HCC)切除术后早期复发进行预测。方法 回顾性分析接受手术切除的CNLCⅠ～Ⅱ期HCC患者153例的资料。用3D slicer软件勾画肿瘤感兴趣区(ROI),用pyradiomics包提取影像组学特征。基于LASSO算法进行特征筛选、并建立影像组学标签(Rad-score)。采用单因素Logistic回归和多因素Logistic逐步回归法确立独立预测因子,构建影像组学预测模型和临床预测模型。用受试者工作特征曲线(ROC)曲线下面积(AUC)来比较模型的区分度,用校准曲线评估模型的校准度,用临床决策曲线分析(DCA)评估模型的临床应用价值。结果 Rad-score、瘤内供血动脉、肝功能白蛋白-胆红素分级(ALBI分级)、性别是独立预测因子。影像组学模型具有良好的预测效能(AUC:训练组0.900,验证组0.853),优于临床模型(AUC:训练组0.823,验证组0.741)。校准曲线显示影像组学模型具有良好的校准度。DCA显示阈值概率在0.1～1.0时,影像组学模型的净获益要高于临床模型。结论 基于CT影像组学...     

基于胰腺周围脂肪间隙CT影像组学预测早期急性胰腺炎进展的价值

目的:探讨基于胰周脂肪间隙CT影像组学预测早期急性胰腺炎(AP)进展的价值。方法:回顾性分析123例根据新修订的亚特兰大分类诊断为AP的患者(进展组39例,非进展组84例),所有患者均接受腹部平扫及增强CT扫描。采用完全随机方法将患者按7:3的比例分为训练组和验证组。对各期手动勾画距炎症胰腺前缘3～5 mm范围的单层感兴趣区(ROI),采用AK软件提取CT纹理特征,使用最小冗余最大相关(mRMR)和最小绝对值收敛和选择算子(LASSO)回归分析对纹理特征降维、建立影像组学标签,并运用100次留组交叉验证(LGOCV)对模型的可靠性进行验证。将临床资料、CT特征及影像组学标签采用多因素Logistic回归分析建立影像组学模型。利用受试者工作特征(ROC)曲线评价模型的预测效能,应用决策曲线分析(DCA)评估模型的临床应用价值。结果:临床模型、平扫序列影像组学标签、联合序列影像组学标签、平扫序列个性化模型及联合序列个性化模型在训练组中的AUC分别为0.70、0.94、0.94、0.94及0.97,在验证组中的AUC分别为0.83、0.95、0.96、0.99、0.98。DCA显示平扫、联合...     

基于多期CT影像组学鉴别卵巢良、恶性肿瘤的临床应用价值

【摘要】目的：探讨基于多期CT影像组学模型及联合模型鉴别卵巢良、恶性肿瘤的临床应用价值。方法：回顾性搜集2018年1月-2022年7月经术后病理证实的144例良性及182例恶性卵巢肿瘤患者的临床及CT多期影像组学资料，将患者随机按7:3分为训练组228例及验证组98例。图像预处理并利用ITK-SNAP勾画肿瘤病灶区域，用PY提取组学特征，将提取特征正则化，采用Spearman相关分析，相关系数大于0.9，保留其一特征, 使用最小绝对收缩与选择算子（LASSO）回归分析对组学特征降维，建立影像组学标签。将影像组学的优势期相与临床指标结合建立联合模型，利用列线图分析预测效能。结果：筛选出平扫、动脉期、静脉期及延迟期的特征数分别为22、7、10、22个，构建各期影像组学模型，结果显示延迟期为最优模型，在训练组中，其受试者工作特征（ROC）曲线的曲线下面积（AUC）为0.857。将临床特征与延迟期影像组学特征构建联合模型，其ROC的AUC值为0.870，优于临床模型，且差异有统计学意义（Z=3.376，P=0.0007）。验证组中，联合模型ROC的AUC值为0.844，优于临床模型，差异无统计学意义（Z=1.650，P=0.0989）。结论：CT扫描的延迟期影像组学特征鉴别卵巢良性与恶性肿瘤的效能优于其它期相，延迟期影像组学标签与临床特征相结合的联合模型有较高的鉴别诊断效能。     

CT影像组学预测早期急性胰腺炎进展的价值

目的探讨基于CT的影像组学预测早期急性胰腺炎(AP)进展的价值。方法回顾性分析2013年11月至2021年2月皖南医学院弋矶山医院109例根据新修订的亚特兰大分类诊断为AP的患者, 根据随诊结果分为进展组(40例)和非进展组(69例)。所有患者初次发病1周内行腹部平扫及增强CT扫描。采用计算机完全随机方法将患者按7∶3的比例分为训练集(77例, 进展组28例, 非进展组49例)和验证集(32例, 进展组12例, 非进展组20例)。在平扫、动脉期、静脉期和延迟期图像上, 对胰腺实质全部层面沿胰腺边缘手动勾画感兴趣区并进行三维融合, 采用AK软件提取纹理特征, 使用最小冗余最大相关和最小绝对收缩和选择算子回归分析对纹理特征降维, 建立平扫、动脉期、静脉期、延迟期和4个序列联合的影像组学标签。采用多因素logistic回归分析, 联合临床特征和CT特征建立临床模型, 联合临床、CT特征和影像组学标签建立综合模型。使用受试者操作特征(ROC)曲线评价各模型预测早期AP进展的效能, 应用决策曲线分析(DCA)评估模型的临床应用价值。结果在训练集中, logistic回归结果显示边缘是AP进展的独...     

基于CT影像组学构建术前预测胰腺癌神经周围侵犯模型的研究

目的 探讨基于增强CT影像组学特征联合传统影像特征、临床信息建立的模型术前预测胰腺癌发生神经周围侵犯(PNI)的可行性及价值。方法 回顾性分析137例术后病理证实为胰腺癌患者的增强CT影像特征及临床资料,其中有PNI患者98例,无PNI患者39例,按照7∶3比例随机分为训练组96例,验证组41例。利用3D Slicer分别在术前增强CT动、静脉期图像上手动勾画肿瘤,Pyradiomics提取特征,最小冗余最大相关算法(mRMR)、最小绝对收缩和选择算子(LASSO)进行特征的降维、筛选,在训练组分别构建独立组学模型、临床-传统影像模型及融合组学模型,验证组验证模型效能。绘制ROC曲线评价预测模型的效能。结果 最终动脉期、静脉期、动脉期联合静脉期分别筛选出3个、2个、2个组学特征,3个期相分别建立的独立组学模型、临床-传统影像模型及融合组学模型中均是融合组学模型性能最高,动脉期、静脉期、动脉期联合静脉期融合组学模型在训练组AUC值分别为0.83、0.85、0.80,在验证组AUC值分别为0.78、0.76、0.80。结论 基于增强CT影像组学特征联合血管侵犯构建的融合组学模型能在术前有效...     

基于MR T2WI的影像组学对直肠癌新辅助治疗疗效的评估

目的:探讨基于高分辨T2WI的影像组学模型对评估直肠癌新辅助治疗疗效的价值。方法:回顾性分析2018年1月-2018年12月经手术病理证实且在接受新辅助治疗前、后均行MRI检查的80例直肠癌患者的病例资料。根据术后病理检查确定的肿瘤退缩分级(TRG),将TRG为0、1级者纳入疗效良好组,2、3级者纳入疗效不良组。在高分辨T2WI上勾画病灶的三维容积兴趣区(VOI)并使用两种模型提取影像组学特征,模型1:仅提取治疗前基线影像组学特征;模型B2:提取基线和治疗后的影像组学特征。随机选取70%的病例作为训练集,30%的病例作为测试集进行验证。对两种模型分别利用LASSO(least absolute shrinkage and selection operator)算法进行特征降维后,与TRG标签建立随机森林(RF)分类器,并分别进行受试者操作特征(ROC)曲线分析,比较两种模型的曲线下面积(AUC)并分析其诊断效能(敏感度、特异度、准确度、阳性预测值、阴性预测值、阳性似然比、阴性似然比)。采用决策曲线分析(DCA)评估临床获益。结果:模型1经降维后得到28个组学特征,模型2共获得3个组学特征,分别建立RF分类器模型,ROC曲线分析得到测试集模型1、2的AUC分别为0.943和0.950,两者间的差异无统计学意义(P>0.05)。模型1的特异度及阳性似然比较高,模型B的敏感度及阴性似然比较高。DCA显示总体上两种方法均可以临床获益。结论:基于治疗前及综合治疗前、后MR T2WI高分辨率图像的影像组学模型均可较准确地预测直肠癌新辅助治疗后的肿瘤退缩程度,可应用于临床上对直肠癌新辅助治疗疗效的评估。     

基于乳腺X线图像影像组学列线图对乳腺癌腋窝淋巴结转移的预测价值

目的:探讨基于乳腺X线图像影像组学列线图对乳腺癌腋窝淋巴结(ALN)转移的预测价值.方法:回顾性分析188例乳腺癌患者的乳腺X线图像和临床资料,按照7:3的比例将患者随机分割为训练组(n=130)和验证组(n=58).使用MaZda软件在乳腺X线图像内提取影像组学特征,应用方差选择法和最小绝对收缩与选择算子算法(LAS...     

CT影像组学对中轴骨脊索瘤与骨巨细胞瘤的鉴别诊断价值

目的:建立术前鉴别中轴骨脊索瘤与骨巨细胞瘤的影像组学模型,并验证其诊断效能.方法:回顾性纳入中轴骨脊索瘤59例、骨巨细胞瘤33例共92例患者,64例为训练集,28例为验证集.基于CT图像进行影像组学特征提取,采用LASSO模型进行特征选择,构建影像组学模型,并计算影像组学得分(Rad-score).通过Logistic...     

Development and validation of a MRI-based radiomics signature for prediction of KRAS mutation in rectal cancer

To develop a T2-weighted (T2W) image-based radiomics signature for the individual prediction of KRAS mutation status in patients with rectal cancer. Three hundred four consecutive patients from center I with pathologically diagnosed rectal adenocarcinoma (training dataset, n = 213; internal validation dataset, n = 91) were enrolled in our retrospective study. The patients from center II (n = 86) were selected as an external validation dataset. A total of 960 imaging features were extracted from high-resolution T2W images for each patient. Five steps, mainly univariate statistical tests, were applied for feature selection. Subsequently, three classification methods, i.e., logistic regression (LR), decision tree (DT), and support vector machine (SVM) algorithm, were applied to develop the radiomics signature for KRAS prediction in the training dataset. The predictive performance was evaluated by receiver operating characteristics curve (ROC) analysis, calibration curve, and decision curve analysis (DCA). Seven radiomics features were screened as a KRAS-associated radiomics signature of rectal cancer. Our best prediction model was obtained with SVM classifiers with AUC of 0.722 (95%CI, 0.654–0.790) in the training dataset. This was validated in the internal and external validation datasets with good calibration, and the corresponding AUCs were 0.682 (95% CI, 0.569–0.794) and 0.714 (95% CI, 0.602–0.827), respectively. DCA confirmed its clinical usefulness. The proposed T2WI-based radiomics signature has a moderate performance to predict KRAS status, and may be useful for supplementing genomic analysis to determine KRAS expression in rectal cancer patients. • T2WI-based radiomics showed a moderate diagnostic significance for KRAS status. • The best prediction model was obtained with SVM classifier. • The baseline clinical and histopathological characteristics were not associated with KRAS mutation.     

超声影像组学标签预测三阴性乳腺癌的价值

目的 探讨基于常规超声的影像组学标签在术前诊断三阴性乳腺癌(TNBC)的价值.资料与方法 回顾性连续收集230例经手术病理证实的肿块型浸润性乳腺癌患者的临床资料和术前超声图像,按照1:2随机抽样选取TNBC与非TNBC共102例患者纳入本研究.按超声检查时间顺序,将患者分为训练组66例和验证组36例.通过ImageJ软...     

Preoperative prediction of tumour deposits in rectal cancer by an artificial neural network–based US radiomics model

To develop a machine learning–based ultrasound (US) radiomics model for predicting tumour deposits (TDs) preoperatively. From December 2015 to December 2017, 127 patients with rectal cancer were prospectively enrolled and divided into training and validation sets. Endorectal ultrasound (ERUS) and shear-wave elastography (SWE) examinations were conducted for each patient. A total of 4176 US radiomics features were extracted for each patient. After the reduction and selection of US radiomics features , a predictive model using an artificial neural network (ANN) was constructed in the training set. Furthermore, two models (one incorporating clinical information and one based on MRI radiomics) were developed. These models were validated by assessing their diagnostic performance and comparing the areas under the curve (AUCs) in the validation set. The training and validation sets included 29 (33.3%) and 11 (27.5%) patients with TDs, respectively. A US radiomics ANN model was constructed. The model for predicting TDs showed an accuracy of 75.0% in the validation cohort. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and AUC were 72.7%, 75.9%, 53.3%, 88.0% and 0.743, respectively. For the model incorporating clinical information, the AUC improved to 0.795. Although the AUC of the US radiomics model was improved compared with that of the MRI radiomics model (0.916 vs. 0.872) in the 90 patients with both ultrasound and MRI data (which included both the training and validation sets), the difference was nonsignificant (p = 0.384). US radiomics may be a potential model to accurately predict TDs before therapy. • We prospectively developed an artificial neural network model for predicting tumour deposits based on US radiomics that had an accuracy of 75.0%. • The area under the curve of the US radiomics model was improved than that of the MRI radiomics model (0.916 vs. 0.872), but the difference was not significant (p = 0.384). • The US radiomics–based model may potentially predict TDs accurately before therapy, but this model needs further validation with larger samples.     

Pancreatic ductal adenocarcinoma: a radiomics nomogram outperforms clinical model and TNM staging for survival estimation after curative resection

To identify a CT-based radiomics nomogram for survival prediction in patients with resected pancreatic ductal adenocarcinoma (PDAC). A total of 220 patients (training cohort n = 147; validation cohort n = 73) with PDAC were enrolled. A total of 300 radiomics features were extracted from CT images. And the least absolute shrinkage and selection operator algorithm were applied to select features and develop a radiomics score (Rad-score). The radiomics nomogram was constructed by multivariate regression analysis. Nomogram discrimination, calibration, and clinical usefulness were evaluated. The association of the Rad-score and recurrence pattern in PDAC was evaluated. The Rad-score was significantly associated with PDAC patient’s disease-free survival (DFS) and overall survival (OS) (both p < 0.001 in two cohorts). Incorporating the Rad-score into the radiomics nomogram resulted in better performance of the survival prediction than that of the clinical model and TNM staging system. In addition, the radiomics nomogram exhibited good discrimination, calibration, and clinical usefulness in both the training and validation cohorts. There was no association between the Rad-score and recurrence pattern. The radiomics nomogram integrating the Rad-score and clinical data provided better prognostic prediction in resected PDAC patients, which may hold great potential for guiding personalized care for these patients. The Rad-score was not a predictor of the recurrence pattern in resected PDAC patients. • The Rad-score developed by CT radiomics features was significantly associated with PDAC patients’ prognosis. • The radiomics nomogram integrating the Rad-score and clinical data has value to permit non-invasive, low-cost, and personalized evaluation of prognosis in PDAC patients. • The radiomics nomogram outperformed clinical model and the TNM staging system in terms of survival estimation.     

基于T2WI和增强MRI影像组学列线图预测宫颈鳞癌淋巴脉管间隙浸润

目的:探讨基于T₂WI和增强MRI影像组学列线图对宫颈鳞癌淋巴脉管间隙浸润(LVSI)的预测价值。方法:将92例经术后病理证实的宫颈鳞癌患者纳入研究,并按7:3的比例随机分为训练集(66例)和验证集(26例)。所有患者术前行MRI检查,在横轴面T₂WI和对比增强T₁WI(T1CE)上选取病灶最大层面沿肿瘤边缘勾画ROI,应用AK软件提取影像组学特征。采用mRMR和LASSO回归分析对提取的纹理特征进行初步筛选,然后进行多因素logistic回归分析,构建影像组学模型。使用单因素logistic回归分析筛选临床病理危险因素,并使用多因素logistic回归结合影像组学评分(Radscore)构建影像组学列线图。应用ROC曲线评估影像组学模型、临床病理危险因素模型和影像组学列线图模型的预测能力,并应用决策曲线分析评估影像组学列线图的临床应用价值。结果:在T₂WI和T1CE图像上分别提取病灶的396个影像组学特征,最终筛选出14个具有最大诊断效能的纹理特征。使用多因素logistic回归构建包含FIGO分期、分化程度和Radscore的影像组学列线图。影像组学列线图的预测效能优于临床病理危险因素模型(训练集中,AUC:0.96 vs.0.70;Delong检验:Z=4.04,P=5.415e-05;验证集中,AUC:0.87 vs.0.71;delong检验:Z=1.24,P=0.02)。决策曲线分析显示风险阈值为0.01~1.00时使用影像组学列线图对预测宫颈鳞癌LVSI情况的临床应用价值较大。结论:基于双序列MRI构建的影像组学列线图对宫颈鳞癌LVSI情况有较好的预测能力,可作为一种术前评估的无创性影像学生物标志。     

多模态功能成像及影像组学预测直肠癌放化疗疗效研究进展

既往常规影像技术及直肠指检、内窥镜等检查主要基于肿瘤形态学信息对直肠癌新辅助放化疗进行疗效预测,效果欠佳。而弥散加权成像(diffusion-weighted, DWI)、动态对比增强(dynamic contrast-enhanced, DCE)和正电子发射型计算机断层显像(positron emission com...     

Comparison of CT,MRI and FDG-PET in response prediction of patients with locally advanced rectal cancer after multimodal preoperative therapy: Is there a benefit in using functional imaging?

The aim of this study was to compare CT, MRI and FDG-PET in the prediction of outcome of neoadjuvant radiochemotherapy in patients with locally advanced primary rectal cancer. A total of 23 patients with T3/4 rectal cancer underwent a preoperative radiochemotherapy combined with regional hyperthermia. Staging was performed using four-slice CT (n=23), 1.5-T MRI (n=10), and ¹⁸F-FDG-PET (n=23) before and 2–4 weeks after completion of neoadjuvant treatment. Response criteria were a change in T category and tumour volume for CT and MRI and a change in glucose uptake (standard uptake value) within the tumour for FDG-PET. Imaging results were compared with those of pretherapy endorectal ultrasound and histopathological findings. Histopathology showed a response to neoadjuvant therapy in 13 patients whereas 10 patients were classified as nonresponders. The mean SUV reduction in responders (60±14%) was significantly higher than in nonresponders (37±31%; P=0.030). The sensitivity and specificity of FDG-PET in identifying response was 100% (CT 54%, MRI 71%) and 60% (CT 80%, MRT 67%). Positive and negative predictive values were 77% (CT 78%, MRI 83%) and 100% (CT 57%, MRI 50%) (PET P=0.002, CT P=0.197, MRI P=0.500). These results suggest that FDG-PET is superior to CT and MRI in predicting response to preoperative multimodal treatment of locally advanced primary rectal cancer.