Application progress of CT radiomics in gastrointestinal stromal tumor
MA Ben,, ZHAO Cheng, SHU Yijun, DONG Ping,
Department of General Surgery, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine; Shanghai Key Laboratory of Biliary Tract Disease Research, Shanghai 200092, China
Gastrointestinal stromal tumor (GIST) is the most common mesenchymal tumor in the gastrointestinal tract, with complex biological characteristics and varying risks, and the treatment methods and prognosis of patients with different risks are quite different; therefore, early diagnosis and risk assessment are crucial for its precision treatment. In recent years, CT radiomics, as an emerging imaging technology, can transform traditional CT image features into a large number of data, thereby reflecting the inherent heterogeneity of GIST and even correlating with its gene expression features. This paper reviews the research progress of CT radiomics in the diagnosis and prediction of GIST with the help of machine learning. The current CT radiomics can not only be used for the differential diagnosis of GIST and other gastric diseases, but also for the risk evaluation of GIST. Furthermore, pathological analysis and gene diagnosis can be performed based on CT images, and then the first-line treatment effect and long-term prognosis can be predicted. At present, various prediction models constructed by combination of CT radiomics and clinical information have been well verified in the specific practice of different clinical problems, showing broad application prospects. However, in the specific clinical application process, different methods of sample data collection and processing, differences in the selection of machine learning algorithms, and the selection of 2D or 3D images all affect the specific effectiveness of CT radiomics. Hence, unified and standardized application rules for radiomics has to be established.
MA Ben, ZHAO Cheng, SHU Yijun, DONG Ping. Application progress of CT radiomics in gastrointestinal stromal tumor. Journal of Shanghai Jiao Tong University (Medical Science)[J], 2023, 43(7): 923-930 doi:10.3969/j.issn.1674-8115.2023.07.015
目前针对不同的临床问题,可以通过构建影像组学模型进行处理。其中使用CT图像构建影像组学临床模型的基本步骤[14-15](图1)包括:① 经过纳入标准与排除标准确定研究人群并获得CT图像。② 于CT图像中分离出感兴趣区域(region of interest,ROI),或者进一步加工为三维的感兴趣体积(volume of interest,VOI)。③ 将获取的ROI或VOI的图像导入影像组学软件,根据所探究内容提取出影像组学参数(包括影像的密度、形状、纹理等)。④ 运用机器学习筛选出具备统计学意义的影像组学参数。⑤ 运用所选取的影像组学参数构建临床模型。
Note: The basic flow of CT radiomics mode consists of ① acquiring CT images, ② selecting ROI/VOI, ③ extracting features such as shape, density change, and texture distribution, ④ machine learning process using different classifiers such as Logistic regression, support vector machine, and random forest, and⑤ making different models such as radiomics model, radiomics and clinical data models, and radiomics nomogram.
伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后。目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27]。《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群。在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂。已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用。
MA Ben drafted the original manuscript. ZHAO Cheng and SHU Yijun participated in the reviewing and editing. DONG Ping conceived the idea and participated in the reviewing and editing. All the authors have read the last version of paper and consented for submission.
利益冲突声明
所有作者声明不存在利益冲突。
All authors disclose no relevant conflict of interests.
LEE I S, PARK Y S, LEE J H, et al. Pathologic discordance of differentiation between endoscopic biopsy and postoperative specimen in mucosal gastric adenocarcinomas[J]. Ann Surg Oncol, 2013, 20(13): 4231-4237.
DEMETRI G D, VON MEHREN M, BLANKE C D, et al. Efficacy and safety of imatinib mesylate in advanced gastrointestinal stromal tumors[J]. N Engl J Med, 2002, 347(7): 472-480.
MIETTINEN M, SOBIN L H, LASOTA J. Gastrointestinal stromal tumors of the stomach: a clinicopathologic, immunohistochemical, and molecular genetic study of 1 765 cases with long-term follow-up[J]. Am J Surg Pathol, 2005, 29(1): 52-68.
ZHANG L J, KANG L Q, LI G C, et al. Computed tomography-based radiomics model for discriminating the risk stratification of gastrointestinal stromal tumors[J]. Radiol Med, 2020, 125(5): 465-473.
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446.
CHEN T, LIU S Q, LI Y, et al. Developed and validated a prognostic nomogram for recurrence-free survival after complete surgical resection of local primary gastrointestinal stromal tumors based on deep learning[J]. EBioMedicine, 2019, 39: 272-279.
SUN Z Q, HU S D, LI J, et al. Radiomics study for differentiating gastric cancer from gastric stromal tumor based on contrast-enhanced CT images[J]. J Xray Sci Technol, 2019, 27(6): 1021-1031.
ZHENG J, XIA Y, XU A Q, et al. Combined model based on enhanced CT texture features in liver metastasis prediction of high-risk gastrointestinal stromal tumors[J]. Abdom Radiol (NY), 2022, 47(1): 85-93.
STARMANS M P A, TIMBERGEN M J M, VOS M, et al. Differential diagnosis and molecular stratification of gastrointestinal stromal tumors on CT images using a radiomics approach[J]. J Digit Imaging, 2022, 35(2): 127-136.
LI D J, WU H, LIU R, et al. Early evaluation of radiotherapy effect of esophageal cancer based on diagnostic CT imaging histology[J]. Chinese Journal of Radiation Oncology, 2019, 28(10): 731-734.
LI H X, LI Z H, LI K, et al. Efficacy of CT radiomics in predicting neoadjuvant therapy of locally advanced rectal cancer[J]. Chinese Journal of Medical Imaging, 2020, 28(1): 44-50.
ZHOU Y, HE L, HUANG Y Q, et al. CT-based radiomics signature: a potential biomarker for preoperative prediction of early recurrence in hepatocellular carcinoma[J]. Abdom Radiol, 2017, 42(6): 1695-1704.
GAO X J, MA T T, CUI J L, et al. A radiomics-based model for prediction of lymph node metastasis in gastric cancer[J]. Eur J Radiol, 2020, 129: 109069.
BA-SSALAMAH A, MUIN D, SCHERNTHANER R, et al. Texture-based classification of different gastric tumors at contrast-enhanced CT[J]. Eur J Radiol, 2013, 82(10): e537-e543.
BASHIR U, SIDDIQUE M M, MCLEAN E, et al. Imaging heterogeneity in lung cancer: techniques, applications, and challenges[J]. AJR Am J Roentgenol, 2016, 207(3): 534-543.
YE H, XIN H, ZHENG Q, et al. Prognostic role of the primary tumour site in patients with operable small intestine and gastrointestinal stromal tumours: a large population-based analysis[J]. Oncotarget, 2017, 9(8): 8147-8154.
Expert Committee on Gastrointestinal Stromal Tumor, Chinese Society of Clinical Oncology. Chinese consensus on diagnosis and treatment of gastrointestinal stromal tumor (2017 edition)[J]. Journal of Multidisciplinary Cancer Management (Electronic Version), 2018, 4(1): 31-43.
CHOI I Y, YEOM S K, CHA J, et al. Feasibility of using computed tomography texture analysis parameters as imaging biomarkers for predicting risk grade of gastrointestinal stromal tumors: comparison with visual inspection[J]. Abdom Radiol (NY), 2019, 44(7): 2346-2356.
SONG Y C, LI J, WANG H X, et al. Radiomics nomogram based on contrast-enhanced CT to predict the malignant potential of gastrointestinal stromal tumor: a two-center study[J]. Acad Radiol, 2022, 29(6): 806-816.
DEMETRI G D, VON MEHREN M, ANTONESCU C R, et al. NCCN Task Force report: update on the management of patients with gastrointestinal stromal tumors[J]. J Natl Compr Canc Netw, 2010, 8(Suppl 2): S1-S44.
RUTKOWSKI P, PRZYBYŁ J, ZDZIENICKI M. Extended adjuvant therapy with imatinib in patients with gastrointestinal stromal tumors[J]. Mol Diagn Ther, 2013, 17(1): 9-19.
ECKARDT A J, ADLER A, GOMES E M, et al. Endosonographic large-bore biopsy of gastric subepithelial tumors: a prospective multicenter study[J]. Eur J Gastroenterol Hepatol, 2012, 24(10): 1135-1144.
ZHAO Y L, FENG M B, WANG M H, et al. CT radiomics for the preoperative prediction of Ki67 index in gastrointestinal stromal tumors: a multi-center study[J]. Front Oncol, 2021, 11: 689136.
WANG C, LI H L, JIAERKEN Y, et al. Building CT radiomics-based models for preoperatively predicting malignant potential and mitotic count of gastrointestinal stromal tumors[J]. Transl Oncol, 2019, 12(9): 1229-1236.
BASILIO-DE-OLIVEIRA R P, PANNAIN V L N. Prognostic angiogenic markers (endoglin, VEGF, CD31) and tumor cell proliferation (Ki67) for gastrointestinal stromal tumors[J]. World J Gastroenterol, 2015, 21(22): 6924-6930.
ZHANG Q W, GAO Y J, ZHANG R Y, et al. Personalized CT-based radiomics nomogram preoperative predicting Ki-67 expression in gastrointestinal stromal tumors: a multicenter development and validation cohort[J]. Clin Transl Med, 2020, 9(1): 12.
KURATA Y, HAYANO K, OHIRA G, et al. Fractal analysis of contrast-enhanced CT images for preoperative prediction of malignant potential of gastrointestinal stromal tumor[J]. Abdom Radiol, 2018, 43(10): 2659-2664.
ZHU C B, LIAO G Q, ZHAO D M. Prognostic value of Ki-67 index in gastrointestinal stromal tumor[J]. Journal of Clinical and Pathological Research, 2018, 38(8): 1632-1639.
XU F, MA X H, WANG Y C, et al. CT texture analysis can be a potential tool to differentiate gastrointestinal stromal tumors without KIT exon 11 mutation[J]. Eur J Radiol, 2018, 107: 90-97.
LIU X J, YIN Y, WANG X Z, et al. Gastrointestinal stromal tumors: associations between contrast-enhanced CT images and KIT exon 11 gene mutation[J]. Ann Transl Med, 2021, 9(19): 1496.
PALATRESI D, FEDELI F, DANTI G, et al. Correlation of CT radiomic features for GISTs with pathological classification and molecular subtypes: preliminary and monocentric experience[J]. Radiol Med, 2022, 127(2): 117-128.
CHEN T, NING Z Y, XU L L, et al. Radiomics nomogram for predicting the malignant potential of gastrointestinal stromal tumours preoperatively[J]. Eur Radiol, 2019, 29(3): 1074-1082.
CHU H R, PANG P P, HE J, et al. Value of radiomics model based on enhanced computed tomography in risk grade prediction of gastrointestinal stromal tumors[J]. Sci Rep, 2021, 11(1): 12009.
WANG M H, FENG Z, ZHOU L X, et al. Computed-tomography-based radiomics model for predicting the malignant potential of gastrointestinal stromal tumors preoperatively: a multi-classifier and multicenter study[J]. Front Oncol, 2021, 11: 582847.
REN C Y, WANG S P, ZHANG S J. Development and validation of a nomogram based on CT images and 3D texture analysis for preoperative prediction of the malignant potential in gastrointestinal stromal tumors[J]. Cancer Imaging, 2020, 20(1): 5.
ZHANG Q W, ZHOU X X, ZHANG R Y, et al. Comparison of malignancy-prediction efficiency between contrast and non-contract CT-based radiomics features in gastrointestinal stromal tumors: a multicenter study[J]. Clin Transl Med, 2020, 10(3): e291.
COLLEWET G, STRZELECKI M, MARIETTE F. Influence of MRI acquisition protocols and image intensity normalization methods on texture classification[J]. Magn Reson Imaging, 2004, 22(1): 81-91.
LUBNER M G, STABO N, LUBNER S J, et al. CT textural analysis of hepatic metastatic colorectal cancer: pre-treatment tumor heterogeneity correlates with pathology and clinical outcomes[J]. Abdom Imaging, 2015, 40(7): 2331-2337.
HUANG Y Q, LIANG C H, HE L, et al. Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer[J]. J Clin Oncol, 2016, 34(18): 2157-2164.
... 伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后.目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27].《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群.在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂.已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用. ...
伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后.目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27].《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群.在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂.已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用. ...
... 伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后.目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27].《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群.在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂.已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用. ...
1
... 伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后.目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27].《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群.在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂.已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用. ...
1
... 伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后.目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27].《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群.在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂.已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用. ...
2
... 伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后.目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27].《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群.在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂.已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用. ...
... 伊马替尼是受体酪氨酸激酶的小分子抑制剂,它的发现极大地改变了中高危GIST患者的预后.目前关于GIST危险度的评估除美国国立综合癌症网络(National Comprehensive Cancer Network,NCCN)的标准外[25],还有美国国立卫生研究院(National Institutes of Health,NIH)修订的标准[3]、武装部队病理学研究所(Armed Forces Institute of Pathology,AFIP)制定的标准[26],以及世界卫生组织(WHO)标准(2013版)[27].《中国胃肠间质瘤诊断治疗共识》(2017年版)[28]推荐依据NIH标准(2008版)评估具有中等或高复发风险的患者作为辅助治疗的适应人群.在这些现行的危险度分级标准中,GIST的危险度取决于肿瘤的位置、大小、有丝分裂计数及是否存在肿瘤破裂.已有很多研究基于现有的GIST危险度分级标准构建CT影像组学模型,研究两者之间是否具有等效甚至替代作用. ...