1.江门市中心医院放射科,广东 江门,529030
2.桂林航天工业学院电子信息与自动化学院,广西 桂林,541004
3.中山市人民医院放射科,广东 中山,528403
陈钦贤,主治医师,研究方向:腹部影像诊断,E-mail: hsimin1011@163.com
收稿:2022-04-06,
纸质出版:2022-09-20
移动端阅览
陈钦贤,刘昱,黄列彬等.MSCT影像组学对Borrmann Ⅳ型胃癌与原发性胃淋巴瘤的鉴别诊断价值[J].中山大学学报(医学科学版),2022,43(05):852-860.
CHEN Qin-xian,LIU Yu,HUANG Lie-bin,et al.The Value of MSCT Based Radiomics in Differential Diagnosis of Borrmann Ⅳ Gastric Cancer and Primary Gastric Lymphoma[J].Journal of Sun Yat-sen University(Medical Sciences),2022,43(05):852-860.
陈钦贤,刘昱,黄列彬等.MSCT影像组学对Borrmann Ⅳ型胃癌与原发性胃淋巴瘤的鉴别诊断价值[J].中山大学学报(医学科学版),2022,43(05):852-860. DOI: 10.13471/j.cnki.j.sun.yat-sen.univ(med.sci).2022.0520.
CHEN Qin-xian,LIU Yu,HUANG Lie-bin,et al.The Value of MSCT Based Radiomics in Differential Diagnosis of Borrmann Ⅳ Gastric Cancer and Primary Gastric Lymphoma[J].Journal of Sun Yat-sen University(Medical Sciences),2022,43(05):852-860. DOI: 10.13471/j.cnki.j.sun.yat-sen.univ(med.sci).2022.0520.
目的
2
探讨CT影像组学模型鉴别Borrmann Ⅳ型胃癌与原发性胃淋巴瘤的价值。
方法
2
回顾性收集2008年6月至2018年4月经手术或内镜病理确诊的Borrmann Ⅳ型胃癌或原发性胃淋巴瘤的病例共186例,其中Borrmann Ⅳ型胃癌132例,原发性胃淋巴瘤54例。采用计算机软件对CT动脉期、静脉期图像提取放射组学特征,再选择Lasso Logistic回归方法进行特征筛选,并建立CT影像组学模型,此外亦筛选CT主观征象构建CT主观征象模型,并同时利用CT主观征象及组学特征构建联合模型。应用受试者工作特征(ROC)曲线评估CT主观征象模型、组学模型以及联合模型的性能。
结果
2
浆膜亮线征、浆膜侧不规则结节状外突两个征象进入了CT主观征象模型,而在组学特征中分别选出9个静脉期特征、8个动脉期特征以及14个动静脉期组合特征与病灶相关,分别构建相应组学模型。鉴别Borrmann Ⅳ型胃癌与原发性胃淋巴瘤,CT主观征象模型的截断值为0.188时,曲线下面积(AUC)为0.846,敏感性为61.9%,特异性为81.7%,准确性为76.5%;组学模型中的动脉期、静脉期以及动静脉期的截断值分别为-0.315、-0.669和-0.858,AUC分别为0.864、0.955和0.890,敏感性分别为71.4%、95.2%和81.0%,特异性分别为85.0%、88.3%和80.0%,准确性分别为81.5%、90.1%和80.3%;联合模型中的动脉期、静脉期以及动静脉期的截断值分别为0.257、0.556和0.497,
AUC
分别为0.883、0.956和0.918,敏感性分别为71.4%、90.5%和71.4%,特异性为85.0%、93.3%和90.0%,准确性为81.5%、92.6%和85.2%。经统计检验,模型诊断效能:联合模型
>
组学模型
>
CT主观征象模型(
P
<
0.001),CT静脉期图像对于鉴别诊断2种肿瘤效能更好。
结论
2
基于CT动、静脉期的影像组学模型能够较准确地鉴别Borrmann Ⅳ型胃癌与原发性胃淋巴瘤。
Objective
2
To explore the predictive value of CT based radiomics model in differentiating Borrmann type Ⅳ gastric cancer (GC) from primary gastric lymphoma (PGL).
Methods
2
A total of 186 cases (Borrmann type Ⅳ GC: 132; PGL: 86) pathologically diagnosed by surgical resection and/or endoscopic biopsy were enrolled from June 2008 to April 2018 retrospectively. Radiomics features were extracted from CT arterial phase and venous phase images by computed algorithm, and selected by least absolute shrinkage and selection operator (Lasso) logistic regression, and then the CT-based radiomics models were established. CT subjective signs were reviewed to build CT subjective signs model, while CT subjective signs and radiomics signature were assembled to build combined model. The receiver operating characteristic (ROC) curve was used to evaluate the performance of CT subjective sign model, radiomics model and the combined model.
Results
2
Two signs(the bright line sign of serosa and the irregular nodular protrusion on the serosa side)were selected into the CT subjective sign model. Among the radiomics features, 9 venous phase features, 8 arterial phase features and 14 arteriovenous combination features related to tumor classification were selected, and the corresponding radiomics models were constructed respectively. When the cut-off value of CT subjective sign model was 0.188, the area under curve (AUC) was 0.846, the sensitivity was 61.9%, the specificity was 81.7%, and the accuracy was 76.5%. The cut-off values of arterial phase, venous phase and arteriovenous phase radiomics model were -0.315, -0.669 and -0.858, respectively, and the AUCs were 0.864, 0.955 and 0.890, the sensitivity were 71.4%, 95.2% and 81.0%, the specificity were 85.0%, 88.3% and 80.0%, the accuracy were 81.5%, 90.1% and 80.3%, respectively. The cut-off values of arterial phase, venous phase and arteriovenous phase in the combined model were 0.257, 0.556 and 0.497, respectively, and the AUCs were 0.883, 0.956 and 0.918, the sensitivity was 71.4%, 90.5% and 71.4%, the specificity was 85.0%, 93.3% and 90.0% and the accuracy were 81.5%, 92.6% and 85.2%, respectively. The diagnostic performance of the models from high to low were the combined model, radiomics model and CT subjective finding model (
P< 0.001
), and CT venous phase images were more effective in the differential diagnosis of the two tumors.
Conclusions
2
The radiomics model based on the arterial and venous phases CT images could differentiate Borrmann type Ⅳ gastric carcinoma from primary gastric lymphoma effectively.
郑于平 . 多层螺旋CT动态增强扫描对胃淋巴瘤与进展期胃癌的对比分析 [J]. 实用医学影像杂志 , 2015 , 16 ( 3 ): 201 - 204 .
Zheng YP . Comparison of dynamic enhanced scanning of multislice spiral CT between infiltrative gastric cancer and gastric lymphoma [J]. JPMI , 2015 , 16 ( 3 ): 201 - 204 .
林少帆 , 林黛英 , 吴先衡 , 等 . 进展期胃癌与胃淋巴瘤的CT鉴别诊断及其判别模型的初步建立 [J]. 放射学实践 , 2020 , 35 ( 5 ): 624 - 628 .
Lin SF , Lin DY , Wu XH , et al . Preliminary establishment of CT-based model for differentiation between advanced gastric cancer and gastric lymphoma [J]. Radiologic Pract , 2020 , 35 ( 5 ): 624 - 628 .
陶金 , 林颖 , 李建忠 , 等 . 原发性胃恶性淋巴瘤临床与病理研究 [J]. 中山大学学报(医学科学版) , 2012 , 33 ( 6 ): 803 - 807 .
Tao J , Lin Y , Li JZ , et al . Study of clinic and pathology on primary gastric malignant lymphoma [J]. J Sun Yat-Sen Univ (Med Sci) , 2012 , 33 ( 6 ): 803 - 807 .
崔建芳 , 王亚丹 , 吴静 , 等 . 原发性胃淋巴瘤临床病理特征及内镜诊断分析 [J]. 胃肠病学和肝病学杂志 , 2021 , 30 ( 5 ): 567 - 570 .
Cui JF , Wang YD , Wu J , et al . Clinicopathologic features and endoscopic presentations of primary gastric lymphoma [J]. Chin J Gastroenterol Hepatol , 2021 , 30 ( 5 ): 567 - 570 .
赵倩 , 杨爱华 , 苗向阳 , 等 . 提高胃镜下活检发现早期胃癌的准确性 [J]. 精准医学杂志 , 2021 , 36 ( 5 ): 460 - 463 .
Zhao Q , Yang AH , Miao XY , et al . To improve the detect accuracy of endoscopic biopsy for early gastric cancer [J]. J Precis Med , 2021 , 36 ( 5 ): 460 - 463 .
辛悦 , 于立辉 , 张秀梅 . 原发性胃淋巴瘤内镜表现与病理特征分析 [J]. 中国实验诊断学 , 2021 , 25 ( 2 ): 188 - 191 .
Xin Y , Yu LH , Zhang XM . Endoscopic and pathologic characteristics of primary gastric lymphoma [J]. Chin J Lab Diagn , 2021 , 25 ( 2 ): 188 - 191 .
钱昆 , 张保峰 , 赵鸿 . 64排螺旋CT在胃癌术前分期诊断中的价值分析 [J]. 中国CT和MRI杂志 , 2021 , 19 ( 6 ): 144 - 146 .
Qian K , Zhang BF , Zhao H . Value of 64-slice spiral CT in preoperative staging diagnosis of gastric cancer [J]. Chin J CT and MRI , 2021 , 19 ( 6 ): 144 - 146 .
吴俊铠 , 陈燕萍 , 罗淑仪 , 等 . 原发性胃肠道淋巴瘤的多层螺旋CT诊断及鉴别诊断 [J]. 中山大学学报(医学科学版) , 2016 , 37 ( 3 ): 469 - 474 .
Wu JK , Chen YP , Luo SY , et al . MSCT diagnosis and differential diagnosis of primary gastrointestinal lymphoma [J]. J Sun Yat-Sen Univ (Med Sci) , 2016 , 37 ( 3 ): 469 - 474 .
朱湘文 , 韩志江 . CT强化模式在进展期胃癌与胃淋巴瘤鉴别诊断中的价值 [J]. 影像诊断与介入放射学 , 2018 , 27 ( 2 ): 112 - 116 .
Zhu XW, Han ZJ, Value of CT enhancement pattern for diagnosing advanced gastric carcinoma and gastric lymphoma [J]. Diagn Imaging & Interv Radiol , 2018 , 27 ( 2 ): 112 - 116 .
钟宝元 , 刘艳秀 , 黄文峰 , 等 . 64层CT三期动态增强扫描对胃癌术前TNM分期的判断价值 [J]. 中华胃肠外科杂志 , 2012 ( 7 ): 706 - 709 .
Zhong BY , Liu YX , Huang WF , et al . Clinical value of 64-slice spiral 3-phase CT enhanced scanning for preoperative TNM stagingassessment of gastric carcinoma [J]. Chin J Gastrointest Surg , 2012 ( 7 ): 706 - 709 .
杨阳 , 唐立 . MSCT三期增强扫描对胃淋巴瘤、胃间质瘤与进展期胃癌的鉴别诊断 [J]. 中国CT和MRI杂志 , 2019 , 17 ( 10 ): 120 - 123 .
Yang Y , Tang L . Differential diagnosis of gastric lymphoma, gastric stromal tumor and advanced gastric cancer by MSCT three-phase enhanced scan [J]. Chin J CT and MRI , 2019 , 17 ( 10 ): 120 - 123 .
Ma Z , Fang M , Huang Y , et al . CT-based radiomics signature for differentiating Borrmann type Ⅳ gastric cancer from primary gastric lymphoma [J]. Eur J Radiol , 2017 , 91 : 142 - 147 .
邓娇 , 谭一雄 , 顾潜彪 , 等 . CT影像组学对原发性胃淋巴瘤与Borrmann Ⅳ型胃癌的鉴别诊断价值 [J]. 中南大学学报(医学版) , 2019 , 44 ( 3 ): 257 - 263 .
Deng J , Tan YX , Gu QB , et al . Application of CT-based radiomics in differentiating primary gastric lymphoma from Borrmann type Ⅳ gastric cancer [J]. J Centr South Univ (Med Sci) , 2019 , 44 ( 3 ): 257 - 263 .
王雷 , 吴白龙 , 王小雷 , 等 . 基于增强CT影像组学在预测胃癌术前病理分级中的价值 [J]. 中国CT和MRI杂志 , 2021 , 19 ( 12 ): 147 - 149 ; 153 .
Wang L , Wu BL , Wang XL , et al . The value of enhanced CT-based radiomics in predicting preoperative pathological grading of gastric cancer [J]. Chin J CT and MRI , 2021 , 19 ( 12 ): 147 - 149 ; 153 .
陈智成 , 朱可心 , 刘屹 . CT影像组学在胃癌的研究进展 [J]. 临床放射学杂志 , 2021 , 40 ( 11 ): 2215 - 2219 .
Chen ZC , Zhu KX , Liu Y . Research progresses of CT-based radiomics in gastric cancer [J]. J Clin Radiol , 2021 , 40 ( 11 ): 2215 - 2219 .
陕飞 , 李子禹 , 张连海 , 等 . 国际抗癌联盟及美国肿瘤联合会胃癌TNM分期系统(第8版)简介及解读 [J]. 中国实用外科杂志 , 2017 , 37 ( 1 ): 15 - 17 .
Shan F , Li ZY , Zhang LH , et al . The union for international cancer control (UICC) and the american joint committee on cancer (AJCC) gastric cancer TNM staging system (8th edition) explanation and elaboration [J]. Chin J Pract Surg , 2017 , 37 ( 1 ): 15 - 17 .
朱雄增 , 李小秋 . 解读2008年恶性淋巴瘤WHO分类 [J]. 临床与实验病理学杂志 , 2010 , 26 ( 1 ): 10 - 13 .
Zhu XZ , Li XQ . Interpretation of the 2008 WHO classification of malignant lymphoma [J]. J Clin Exp Pathol , 2010 , 26 ( 1 ): 10 - 13 .
Kim TU , Kim S , Lee JW , et al . MDCT features in the differentiation of T4a gastric cancer from less-advanced gastric cancer: significance of the hyperattenuating serosa sign [J]. Br J Radiol , 2013 , 86 ( 1029 ): 20130290 .
Sun R J , Tang L , Chen Y , et al . Feasibility of differentiating T3 from T4a gastric cancer in different Lauren classification by determining serosa invasion: Diagnostic performance of high enhanced serosa sign [J]. Chin J Cancer Res , 2018 , 30 ( 2 ): 263 - 271 .
唐磊 . 胃癌影像学分期与评效--多学科诊疗的需求与对策 [J]. 中华胃肠外科杂志 , 2015 ( 3 ): 208 - 212 .
Tang L . Staging and response evaluation of gastric cancer: requirements and resolutions by multidisciplinary treatment [J]. Chin J Gastrointest Surg , 2015 ( 3 ): 208 - 212 .
李雪丹 , 崔玲玲 , 崔立贺 , 等 . 胃癌浆膜面的不同CT表现及其诊断意义 [J]. 中国医学影像技术 , 2012 , 28 ( 7 ): 1350 - 1353 .
Li XD , Cui LL , Cui LH , et al . CT findings of serosa and their diagnostic significances of gastric cancer [J]. Chin J Med Imaging Technol , 2012 , 28 ( 7 ): 1350 - 1353 .
黎昕 , 黄柏锋 , 蓝博文 , 等 . 浸润型胃淋巴瘤和浸润型胃癌的多层螺旋CT表现 [J]. 中国医学影像学杂志 , 2012 , 20 ( 3 ): 195 - 198 .
Li X , Huang BF , Lan BW , et al . The manifestations of infiltrative gastric lymphoma and infiltrative gastric carcinoma with multi-slice helical CT [J]. Chin J Med Imaging , 2012 , 20 ( 3 ): 195 - 198 .
黄列彬 , 龙晚生 , 薛慧敏 , 等 . CT灌注成像在构建胃癌术前淋巴结转移预测模型中的价值 [J]. 影像诊断与介入放射学 , 2020 , 29 ( 3 ): 171 - 176 .
Huang LB , Long WS , Xue HM , et al . Value of CT perfusion imaging in preoperative prediction of lymph node metastasis of gastric cancer [J]. Diagn Imaging & Interv Radiol , 2020 , 29 ( 3 ): 171 - 176 .
钟添荣 , 梁翠媚 , 梁倩雯 , 等 . 胃淋巴瘤的MSCT影像特征与病理分型的关系 [J]. 广东医学 , 2015 , 36 ( 23 ): 3668 - 3670 .
Zhong TR , Liang CM , Liang QW , et al . The relationship between MSCT features and pathological classification of gastric lymphoma [J]. Guangdong Med J , 2015 , 36 ( 23 ): 3668 - 3670 .
刘宇亭 , 夏瑞明 . 34例胃癌及胃淋巴瘤的CT表现及病理对照分析 [J]. 医学影像学杂志 , 2017 , 27 ( 4 ): 693 - 695 .
Liu YT , Xia RM . The CT manifestations and pathological comparison analysis in 34 cases of gastric cancer and gastric lymphoma [J]. J Med Imaging , 2017 , 27 ( 4 ): 693 - 695 .
陈智慧 , 陈任政 , 司徒敏婷 , 等 . 64排螺旋CT在进展期胃癌与胃淋巴瘤的诊断及鉴别诊断的应用价值 [J]. 实用放射学杂志 , 2020 , 36 ( 5 ): 756 - 758, 803 .
Chen ZH , Chen RZ , Si TMT , et al . The value of 64-slice spiral CT in the diagnosis and differential diagnosis of advanced gastric cancer and gastric lymphoma [J]. J Pract Radiol , 2020 , 36 ( 5 ): 756 - 758, 803 .
Shen C , Liu Z , Guan M , et al . 2D and 3D CT radiomics features prognostic performance comparison in non-small cell lung cancer [J]. Translational Oncology , 2017 , 10 ( 6 ): 886 - 894 .
0
浏览量
198
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
