Preoperative Tumor Texture Analysis on MRI for High-Risk Disease Prediction in Endometrial Cancer: A Hypothesis-Generating Study

被引:8
作者
Micco, Maura [1 ]
Gui, Benedetta [1 ]
Russo, Luca [1 ,2 ]
Boldrini, Luca [2 ]
Lenkowicz, Jacopo
Cicogna, Stefania [3 ]
Cosentino, Francesco [4 ]
Restaino, Gennaro [5 ]
Avesani, Giacomo
Panico, Camilla
Moro, Francesca [6 ]
Ciccarone, Francesca [6 ]
Macchia, Gabriella [7 ]
Valentini, Vincenzo [2 ,8 ]
Scambia, Giovanni [6 ,9 ]
Manfredi, Riccardo [1 ,8 ]
Fanfani, Francesco [6 ,9 ]
机构
[1] Fdn Policlin Univ A Gemelli, IRCCS, Area Diagnost Immagini, Dipartimento Diagnost Immagini Radioterapia Oncol, I-00168 Rome, Italy
[2] Fdn Policlin Univ A Gemelli, IRCCS, UOC Radioterapia Oncol, Dipartimento Diagnost Immagini Radioterapia Oncol, I-00168 Rome, Italy
[3] IRCCS Burlo Garofolo, Inst Maternal & Child Hlth, Dept Obstet & Gynaecol, I-34137 Trieste, Italy
[4] Gemelli Molise Spa, Gynecol Oncol, I-86100 Campobasso, Italy
[5] Gemelli Molise Spa, Dept Radiol, I-86100 Campobasso, Italy
[6] Bambino Sanita Pubbl Fdn Policlin Univ A Gemelli, Dipartimento Sci Salute Donna, IRCCS, I-00168 Rome, Italy
[7] Gemelli Molise Hosp, Radiotherapy Unit, I-86100 Campobasso, Italy
[8] Univ Cattolica Sacro Cuore, Sede Roma, I-00168 Rome, Italy
[9] Univ Cattolica Sacro Cuore, Ist Clin Ostetr Ginecolog, I-00168 Rome, Italy
来源
JOURNAL OF PERSONALIZED MEDICINE | 2022年 / 12卷 / 11期
关键词
radiomics; endometrial cancer; magnetic resonance imaging; CARCINOMA; MODEL; STRATIFICATION; RADIOMICS; DIAGNOSIS; INVASION;
D O I
10.3390/jpm12111854
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Objective: To develop and validate magnetic resonance (MR) imaging-based radiomics models for high-risk endometrial cancer (EC) prediction preoperatively, to be able to estimate deep myometrial invasion (DMI) and lymphovascular space invasion (LVSI), and to discriminate between low-risk and other categories of risk as proposed by ESGO/ESTRO/ESP (European Society of Gynaecological Oncology-European Society for Radiotherapy & Oncology and European Society of Pathology) guidelines. Methods: This retrospective study included 96 women with EC who underwent 1.5-T MR imaging before surgical staging between April 2009 and May 2019 in two referral centers divided into training (T = 73) and validation cohorts (V = 23). Radiomics features were extracted using the MODDICOM library with manual delineation of whole-tumor volume on MR images (axial T2-weighted). Diagnostic performances of radiomic models were evaluated by area under the receiver operating characteristic (ROC) curve in training (AUCT) and validation (AUCV) cohorts by using a subset of the most relevant texture features tested individually in univariate analysis using Wilcoxon-Mann-Whitney. Results: A total of 228 radiomics features were extracted and ultimately limited to 38 for DMI, 29 for LVSI, and 15 for risk-classes prediction for logistic radiomic modeling. Whole-tumor radiomic models yielded an AUCT/AUCV of 0.85/0.68 in DMI estimation, 0.92/0.81 in LVSI prediction, and 0.84/0.76 for differentiating low-risk vs other risk classes (intermediate/high-intermediate/high). Conclusion: MRI-based radiomics has great potential in developing advanced prognostication in EC.
引用
收藏
页数:15
相关论文
共 37 条
  • [1] Cancer of the corpus uteri
    Amant, Frederic
    Mirza, Mansoor Raza
    Koskas, Martin
    Creutzberg, Carien L.
    [J]. INTERNATIONAL JOURNAL OF GYNECOLOGY & OBSTETRICS, 2018, 143 : 37 - 50
  • [2] Prediction of tumor grade and lymphovascular space invasion in endometrial adenocarcinoma with MR imaging-based radiomic analysis
    Bereby-Kahane, M.
    Dautry, R.
    Matzner-Lober, E.
    Cornelis, F.
    Sebbag-Sfez, D.
    Place, V
    Mezzadri, M.
    Soyer, P.
    Dohan, A.
    [J]. DIAGNOSTIC AND INTERVENTIONAL IMAGING, 2020, 101 (06) : 401 - 411
  • [3] MRI-Based Radiomic Model for Preoperative Risk stratification in Stage I Endometrial Cancer
    Chen, Jingya
    Gu, Hailei
    Fan, Weimin
    Wang, Yaohui
    Chen, Shuai
    Chen, Xiao
    Wang, Zhongqiu
    [J]. JOURNAL OF CANCER, 2021, 12 (03): : 726 - 734
  • [4] XGBoost: A Scalable Tree Boosting System
    Chen, Tianqi
    Guestrin, Carlos
    [J]. KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, : 785 - 794
  • [5] Collins GS, 2015, ANN INTERN MED, V162, P55, DOI [10.7326/M14-0697, 10.1136/bmj.g7594, 10.1016/j.jclinepi.2014.11.010, 10.1038/bjc.2014.639, 10.1002/bjs.9736, 10.1016/j.eururo.2014.11.025, 10.1186/s12916-014-0241-z, 10.7326/M14-0698]
  • [6] ESMO-ESGO-ESTRO Consensus Conference on Endometrial Cancer: diagnosis, treatment and follow-up
    Colombo, N.
    Creutzberg, C.
    Amant, F.
    Bosse, T.
    Gonzalez-Martin, A.
    Ledermann, J.
    Marth, C.
    Nout, R.
    Querleu, D.
    Mirza, M. R.
    Sessa, C.
    [J]. ANNALS OF ONCOLOGY, 2016, 27 (01) : 16 - 41
  • [7] ESGO/ESTRO/ESP guidelines for the management of patients with endometrial carcinoma
    Concin, Nicole
    Matias-Guiu, Xavier
    Vergote, Ignace
    Cibula, David
    Mirza, Mansoor Raza
    Marnitz, Simone
    Ledermann, Jonathan
    Bosse, Tjalling
    Chargari, Cyrus
    Fagotti, Anna
    Fotopoulou, Christina
    Gonzalez Martin, Antonio
    Lax, Sigurd
    Lorusso, Domenica
    Marth, Christian
    Morice, Philippe
    Nout, Remi A.
    O'Donnell, Dearbhaile
    Querleu, Denis
    Raspollini, Maria Rosaria
    Sehouli, Jalid
    Sturdza, Alina
    Taylor, Alexandra
    Westermann, Anneke
    Wimberger, Pauline
    Colombo, Nicoletta
    Planchamp, Francois
    Creutzberg, Carien L.
    [J]. INTERNATIONAL JOURNAL OF GYNECOLOGICAL CANCER, 2021, 31 (01) : 12 - 39
  • [8] Dinapoli N, 2015, IEEE ENG MED BIO, P771, DOI 10.1109/EMBC.2015.7318476
  • [9] Whole-Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer
    Fasmer, Kristine E.
    Hodneland, Erlend
    Dybvik, Julie A.
    Wagner-Larsen, Kari
    Trovik, Jone
    Salvesen, Oyvind
    Krakstad, Camilla
    Haldorsen, Ingfrid H. S.
    [J]. JOURNAL OF MAGNETIC RESONANCE IMAGING, 2021, 53 (03) : 928 - 937
  • [10] Integrated genomic characterization of endometrial carcinoma
    Getz, Gad
    Gabriel, Stacey B.
    Cibulskis, Kristian
    Lander, Eric
    Sivachenko, Andrey
    Sougnez, Carrie
    Lawrence, Mike
    Kandoth, Cyriac
    Dooling, David
    Fulton, Robert
    Fulton, Lucinda
    Kalicki-Veizer, Joelle
    McLellan, Michael D.
    O'Laughlin, Michelle
    Schmidt, Heather
    Wilson, Richard K.
    Ye, Kai
    Ding, Li
    Mardis, Elaine R.
    Ally, Adrian
    Balasundaram, Miruna
    Birol, Inanc
    Butterfield, Yaron S. N.
    Carlsen, Rebecca
    Carter, Candace
    Chu, Andy
    Chuah, Eric
    Chun, Hye-Jung E.
    Dhalla, Noreen
    Guin, Ranabir
    Hirst, Carrie
    Holt, Robert A.
    Jones, Steven J. M.
    Lee, Darlene
    Li, Haiyan I.
    Marra, Marco A.
    Mayo, Michael
    Moore, Richard A.
    Mungall, Andrew J.
    Plettner, Patrick
    Schein, Jacqueline E.
    Sipahimalani, Payal
    Tam, Angela
    Varhol, Richard J.
    Robertson, A. Gordon
    Pashtan, Itai
    Saksena, Gordon
    Onofrio, Robert C.
    Schumacher, Steven E.
    Tabak, Barbara
    [J]. NATURE, 2013, 497 (7447) : 67 - 73