Share:
Share this content in WeChat
X
Clinical Article
Differentiation of borderline and malignant epithelial tumors based on MRI-T2WI radiomics nomogram
DING Cong  WEI Mingxiang  JIA jianye  ZHOU Wei  BAI Genji 

Cite this article as: Ding C, Wei MX, Jia JY, et al. Differentiation of borderline and malignant epithelial tumors based on MRI-T2WI radiomics nomogram[J]. Chin J Magn Reson Imaging, 2022, 13(7): 55-60. DOI:10.12015/issn.1674-8034.2022.07.010.


[Abstract] Objective To develop and validate a radiomics nomogram that was based on MRI-T2WI to distinguish between borderline epithelial ovarian tumors (BEOTs) and malignant epithelial ovarian tumors (MEOTs).Materials and Methods The clinical and imaging data of 192 patients with epithelial ovarian tumors confirmed by pathology from January 2016 to May 2021 were retrospectively analyzed in the Affiliated Huaian First People's Hospital of Nanjing Medical University, including EBOTs (n=72) and MEOTs (n=153) were enrolled. According to the ratio of 8∶2,all cases were randomly divided into the training group (n=153) and validation group (n=39). We used T2WI to manually delineated ROI and extract radiomics features. Mann-Whitney U test, correlation and LASSO regression were used to select features, and then constructed radiomics model by these features, used to calculate Radscore. Combining Radscore with clinic factors, we used multiple logistic regression to construct radiomics nomogram. ROC curve, calibration curve and decision curve analysis and correction were used to evaluate the clinical value of radiomics nomogram.Results We reserved 10 radiomics features after the feature was filtered. The AUC of the radiomics nomogram which combined HE4 with Radscore in the training group and validation group (training group: 0.947, validation group: 0.914) were higher than those of the single radiomics model (training group:0.925, validation group:0.819). ROC and DCA results showed that the radiomics nomogram had higher reliability.Conclusions The radiomics nomogram combined radiomics feature based on T2WI and clinical factors is able to distinguish between BEOTs and MEOTs intuitively and accurately and provide guidance for the next clinical decision.
[Keywords] ovarian tumors;radiomics;machine learning;nomogram;magnetic resonance imaging;T2-weighted imaging

DING Cong1   WEI Mingxiang2   JIA jianye1   ZHOU Wei1   BAI Genji1*  

1 Department of Imaging, the Affiliated Huaian No.1 People's Hospital of Nanjing Medical University,Huaian 223000, China

2 Department of Imaging, the Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou 215000, China

Bai GJ, E-mail: hybgj0451@163.com

Conflicts of interest   None.

Received  2022-03-08
Accepted  2022-07-08
DOI: 10.12015/issn.1674-8034.2022.07.010
Cite this article as: Ding C, Wei MX, Jia JY, et al. Differentiation of borderline and malignant epithelial tumors based on MRI-T2WI radiomics nomogram[J]. Chin J Magn Reson Imaging, 2022, 13(7): 55-60.DOI:10.12015/issn.1674-8034.2022.07.010

[1]
Tu N, Zhong Y, Wang X, et al. Treatment response prediction of nasopharyngeal carcinoma based on histogram analysis of diffusional kurtosis imaging[J]. AJNR Am J Neuroradiol, 2019, 40(2): 326-333. DOI: 10.3174/ajnr.A5925.
[2]
Siegel RL, Miller KD, Goding Sauer A, et al. Colorectal cancer statistics, 2020[J]. CA Cancer J Clin, 2020, 70(3): 145-164. DOI: 10.3322/caac.21601.
[3]
Staebler A, Mayr D. The 2016 update of the S3 guideline for malignant tumours of the ovary: role of pathology in diagnosis, therapy and clinical management of epithelial tumours[J]. Pathologe, 2017, 38(4): 331-344. DOI: 10.1007/s00292-017-0310-0.
[4]
Fang CY, Zhao LQ, Chen X, et al. The impact of clinicopathologic and surgical factors on relapse and pregnancy in young patients (≤40 years old) with borderline ovarian tumors[J]. BMC Cancer, 2018, 18(1): 1147. DOI: 10.1186/s12885-018-4932-2.
[5]
Fischerova D, Zikan M, Dundr P, et al. Diagnosis, treatment, and follow-up of borderline ovarian tumors[J]. Oncologist, 2012, 17(12): 1515-1533. DOI: 10.1634/theoncologist.2012-0139.
[6]
Acs G. Serous and mucinous borderline (low malignant potential) tumors of the ovary[J]. Am J Clin Pathol, 2005, 123(Suppl): S13-S57. DOI: 10.1309/J6PXXK1HQJAEBVPM.
[7]
Wang W, Zhang SQ, Wang YD, et al. Expert consensus on the diagnosis and treatment of borderline ovarian tumors[J]. Chin J Pract Gynecol Obstet, 2019, 35(9): 1000-1007. DOI: 10.19538/j.fk2019090113.
[8]
Hauptmann S, Friedrich K, Redline R, et al. Ovarian borderline tumors in the 2014 WHO classification: evolving concepts and diagnostic criteria[J]. Virchows Arch, 2017, 470(2): 125-142. DOI: 10.1007/s00428-016-2040-8.
[9]
Huang Z, Li L, Li CC, et al. Diagnostic accuracy of frozen section analysis of borderline ovarian tumors: a meta-analysis with emphasis on misdiagnosis factors[J]. J Cancer, 2018, 9(16): 2817-2824. DOI: 10.7150/jca.25883.
[10]
Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
[11]
Zhang H, Mao YF, Chen XJ, et al. Magnetic resonance imaging radiomics in categorizing ovarian masses and predicting clinical outcome: a preliminary study[J]. Eur Radiol, 2019, 29(7): 3358-3371. DOI: 10.1007/s00330-019-06124-9.
[12]
Li YA, Qiang JW, Ma FH, et al. MRI features and score for differentiating borderline from malignant epithelial ovarian tumors[J]. Eur J Radiol, 2018, 98: 136-142. DOI: 10.1016/j.ejrad.2017.11.014.
[13]
Javadi S, Ganeshan DM, Qayyum A, et al. Ovarian cancer, the revised FIGO staging system, and the role of imaging[J]. AJR Am J Roentgenol, 2016, 206(6): 1351-1360. DOI: 10.2214/AJR.15.15199.
[14]
Baeßler B, Weiss K, Pinto dos Santos D. Robustness and reproducibility of radiomics in magnetic resonance imaging: a phantom study[J]. Invest Radiol, 2019, 54(4): 221-228. DOI: 10.1097/RLI.0000000000000530.
[15]
Yu XP, Wang L, Yu HY, et al. MDCT-based radiomics features for the differentiation of serous borderline ovarian tumors and serous malignant ovarian tumors[J]. Cancer Manag Res, 2021, 13: 329-336. DOI: 10.2147/CMAR.S284220.
[16]
Nougaret S, Tardieu M, Vargas HA, et al. Ovarian cancer: an update on imaging in the era of radiomics[J]. Diagn Interv Imaging, 2019, 100(10): 647-655. DOI: 10.1016/j.diii.2018.11.007.
[17]
Bektas CT, Kocak B, Yardimci AH, et al. Clear cell renal cell carcinoma: machine learning-based quantitative computed tomography texture analysis for prediction of fuhrman nuclear grade[J]. Eur Radiol, 2019, 29(3): 1153-1163. DOI: 10.1007/s00330-018-5698-2.
[18]
Horvat N, Bates DDB, Petkovska I. Novel imaging techniques of rectal cancer: what do radiomics and radiogenomics have to offer? A literature review[J]. Abdom Radiol (NY), 2019, 44(11): 3764-3774. DOI: 10.1007/s00261-019-02042-y.
[19]
Liu MZ, Ge YQ, Li MR, et al. Prediction of BRCA gene mutation status in epithelial ovarian cancer by radiomics models based on 2D and 3D CT images[J]. BMC Med Imaging, 2021, 21(1): 180. DOI: 10.1186/s12880-021-00711-3.
[20]
Pan SS, Ding ZX, Zhang LX, et al. A nomogram combined radiomic and semantic features as imaging biomarker for classification of ovarian cystadenomas[J]. Front Oncol, 2020, 10: 895. DOI: 10.3389/fonc.2020.00895.
[21]
Li SY. Preliminary study on the value of the 2D and 3D radiomics model based on plain CT in differentiating benign from malignant ovarian lesions[D]. Nanchang: Nanchang University, 2021.
[22]
Borrelli GM, de Mattos LA, Andres MP, et al. Role of imaging tools for the diagnosis of borderline ovarian tumors: a systematic review and meta-analysis[J]. J Minim Invasive Gynecol, 2017, 24(3): 353-363. DOI: 10.1016/j.jmig.2016.12.012.
[23]
Yu XY, Wu H, Niu GM, et al. Multiparameter MRI radiomics predicts preoperative peritoneal metastasis in patients with epithelial ovarian cancer[J]. Chin J Magn Reson Imaging, 2021, 12(8): 44-48.
[24]
Song XL, Ren JL, Yao TY, et al. Radiomics based on multisequence magnetic resonance imaging for the preoperative prediction of peritoneal metastasis in ovarian cancer[J]. Eur Radiol, 2021, 31(11): 8438-8446. DOI: 10.1007/s00330-021-08004-7.
[25]
Li HM, Gong J, Li RM, et al. Development of MRI-based radiomics model to predict the risk of recurrence in patients with advanced high-grade serous ovarian carcinoma[J]. AJR Am J Roentgenol, 2021, 217(3): 664-675. DOI: 10.2214/AJR.20.23195.
[26]
Ye RP, Weng SP, Li YM, et al. Texture analysis of three-dimensional MRI images may differentiate borderline and malignant epithelial ovarian tumors[J]. Korean J Radiol, 2021, 22(1): 106-117. DOI: 10.3348/kjr.2020.0121.
[27]
Li YA, Jian JM, Pickhardt PJ, et al. MRI-based machine learning for differentiating borderline from malignant epithelial ovarian tumors: a multicenter study[J]. J Magn Reson Imaging, 2020, 52(3): 897-904. DOI: 10.1002/jmri.27084.
[28]
Jian JM. Research on machine learning methods for medical image and its application in precise diagnosis of ovarian cancer[D]. Hefei: University of Science and Technology of China, 2021.
[29]
Qi LS, Chen DD, Li CX, et al. Diagnosis of ovarian neoplasms using nomogram in combination with ultrasound image-based radiomics signature and clinical factors[J/OL]. Front Genet, 2021 [2022-03-08]. https://www.frontiersin.org/articles/10.3389/fgene.2021.753948/full. DOI: 10.3389/fgene.2021.753948..
[30]
Luo YT. Application value of multimodal magnetic resonance imaging combined with serum CA125 and HE4 in differentiating benign and malignant ovarian tumors[D]. Jining: Jining Medical University, 2021.
[31]
Scaletta G, Plotti F, Luvero D, et al. The role of novel biomarker HE4 in the diagnosis, prognosis and follow-up of ovarian cancer: a systematic review[J]. Expert Rev Anticancer Ther, 2017, 17(9): 827-839. DOI: 10.1080/14737140.2017.1360138.
[32]
Leandersson P, Åkesson A, Hedenfalk I, et al. A multiplex biomarker assay improves the diagnostic performance of HE4 and CA125 in ovarian tumor patients[J/OL]. PLoS One, 2020 [2022-03-08]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0240418. DOI: 10.1371/journal.pone.0240418.
[33]
Zheng X, Chen SL, Li LF, et al. Evaluation of HE4 and TTR for diagnosis of ovarian cancer: comparison with CA-125[J]. J Gynecol Obstet Hum Reprod, 2018, 47(6): 227-230. DOI: 10.1016/j.jogoh.2018.03.010.

PREV Clinical application of whole-volume apparent diffusion coefficient histogram parameters of histological grading rectal adenocarcinoma
NEXT Preoperative predicting lymphov-ascular space invasion in endometrial carcinoma by nomogram based on mpMRI radiomics
  



Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn