基于 MRI 平扫影像组学辅助卵巢常见良性上皮肿瘤鉴别诊断
摘要
巢良性浆液性（BST）与黏液性（BMT）囊腺瘤中的鉴别价值。方法 : 回顾性分析 2012 年 5 月至 2023 年 12 月义乌市中心
医院 175 例术后常规病理检查确诊为 BST 或 BMT, 并于术前行盆腔磁共振平扫检查。按７：３随机分成 121 例训练组和 54
例验证组，利用 T1WI 平扫影像提取影像组学特征并进行 LASSO 算法，构建影像组学标签、得到影像组学分数模型，采用
受试者工作曲线 (ROC) 和校正曲线对不同模型的预测性能进行评价。结果：在影像组学分析中，提取 396 个影像组学纹理
特征，降维提取 9 个最优影像组学参数创建影像组学标签。训练组中 T1WI 影像组学模型中鉴别良性浆液性与黏液性囊腺
瘤的平均 AUC、特异度、灵敏度分别为 0.768 （P<0.05）、74.6%、66.7%；在验证组中，AUC、特异度、灵敏度分别为 0.731
（P<0.05）、80.0%、75%。结论：基于术前 MRI 平扫检查建立的放射组学标签预测模型在卵巢良性浆液性肿瘤和黏液性肿
瘤分类中取得了良好的预测性能。
关键词
全文:
PDF参考
[1] Jaime P , Emanuela D , IñIgo E . Ovarian carcinomas:
at least five different diseases with distinct histological
features and molecular genetics.[J]. Human Pathology,
2018:S0046817718302302-.
[2] Marko J , Marko K I , Pachigolla S L , et al. Mucinous
Neoplasms of the Ovary: Radiologic-Pathologic Correlation[J].
Radiographics, 2019, 39(4):982-997.
[3] Lee KR, BSTully RE. Mucinous tumors of the
ovary: a clinicopathologic study of 196 borderline tumors (of
intestinal type) and carcinomas, including an evaluation of 11
cases with “pseudomyxoma peritonei.” Am J Surg Pathol
2000;24(11):1447–1464.
[4] BSThmeler KM, Tao X, Frumovitz M, et al. Prevalence
of lymph node metastasis in primary mucinous carcinoma of the
ovary. Obstet Gynecol 2010;116(2 Pt 1):269–273.
[5] 赵书会 , 强金伟 , 张国福 , 等 .MRI 鉴别卵巢良性与交
界性黏液性囊腺瘤的价值 [J]. 中华放射学杂志 ,2012(04):327-
331.
[6] Pan S , Ding Z , Zhang L , et al. A Nomogram Combined
Radiomic and Semantic Features as Imaging Biomarker for
Classification of Ovarian Cystadenomas[J]. Frontiers in Oncology,
2020, 10.
[7] Tocci P, Cianfrocca R, Castro VD, et al. β- arrestin1/
YAP/mutant p53 complexes orchestrate the endothelin A
receptor signaling in high-grade serous ovarian cancer[J]. Nature
Communications, 2019, 10 (1):23-29.
[8] Wang Y, Cao J, Liu W, et al. Protein tyrosine phosphatase
receptor type R (PTPRR) antagonizes the Wnt signaling pathway
in ovarian cancer by dephosphorylating and inactivating β -
catenin[J]. Journal of Biological Chemistry, 2019,294(48):18306-
18323.
[9] Marko J , Marko K I , Pachigolla S L , et al. Mucinous
Neoplasms of the Ovary: Radiologic-Pathologic Correlation[J].
Radiographics, 2019, 39(4):982-997.
[10] Takahashi N , Yoshino O , Hayashida E , et al.
Quantitative analysis of ovarian cysts and tumors by using T2 star
mapping[J]. Journal of Obstetrics and Gynaecology Research,
2019, 46(1).
[11]Ayumi O ,Yasunari F . Magnetic resonance imaging
findings of cystic ovarian tumors: major differential diagnoses in
five types frequently encountered in daily clinical practice. [J].
Japanese journal of radiology, 2022, 40 (12): 1213-1234.
[12] li SX, Liang RJ, Dan Z, et al. Radiomics derived from
dynamic contrast-enhanced MRI pharmacokinetic protocol
features: the value of precision diagnosis ovarian neoplasms. Eur
Radiol, 2020,31(1).
[13] Zhang H, Mao Y, Chen X, et al. Magnetic resonance
imaging radiomics in categorizing ovarian masses and predicting
clinical outcome: a preliminary study. Springer Berlin Heidelberg,
2019,29(7).
[14] Guangxing W, Yang S, Youting C, et al. Rapid
identification of human ovarian cancer in second harmonic
generation images using radiomics feature analyses and treebased pipeline optimization tool[J]. J Biophotonics, 2020,13(9)
[15]Minkook S ,Korea O R S K O U C T M O C H M S E C
I S C K O R S K O U C T M O C H M S E R O D H M C ,Joon Y
L , et al. Evaluating the added benefit of CT texture analysis on
conventional CT analysis to differentiate benign ovarian cysts. [J].
Diagnostic and interventional radiology (Ankara, Turkey), 2021,
27 (4): 460-468.
(1 摘要 Views, 22 PDF Downloads)
Refbacks
- 当前没有refback。