MRI-Based Machine Learning for Differentiating Borderline From Malignant Epithelial Ovarian Tumors: A Multicenter Study.
borderline epithelial ovarian tumor
machine learning
magnetic resonance imaging
malignant epithelial ovarian tumor
preoperative prediction
Journal
Journal of magnetic resonance imaging : JMRI
ISSN: 1522-2586
Titre abrégé: J Magn Reson Imaging
Pays: United States
ID NLM: 9105850
Informations de publication
Date de publication:
09 2020
09 2020
Historique:
received:
20
11
2019
revised:
21
01
2020
accepted:
23
01
2020
pubmed:
12
2
2020
medline:
15
5
2021
entrez:
12
2
2020
Statut:
ppublish
Résumé
Preoperative differentiation of borderline from malignant epithelial ovarian tumors (BEOT from MEOT) can impact surgical management. MRI has improved this assessment but subjective interpretation by radiologists may lead to inconsistent results. To develop and validate an objective MRI-based machine-learning (ML) assessment model for differentiating BEOT from MEOT, and compare the performance against radiologists' interpretation. Retrospective study of eight clinical centers. In all, 501 women with histopathologically-confirmed BEOT (n = 165) or MEOT (n = 336) from 2010 to 2018 were enrolled. Three cohorts were constructed: a training cohort (n = 250), an internal validation cohort (n = 92), and an external validation cohort (n = 159). Preoperative MRI within 2 weeks of surgery. Single- and multiparameter (MP) machine-learning assessment models were built utilizing the following four MRI sequences: T Diagnostic performance of the models was assessed for both whole tumor (WT) and solid tumor (ST) components. Assessment of the performance of the model in discriminating BEOT vs. early-stage MEOT was made. Six radiologists of varying experience also interpreted the MR images. Mann-Whitney U-test: significance of the clinical characteristics; chi-square test: difference of label; DeLong test: difference of receiver operating characteristic (ROC). The MP-ST model performed better than the MP-WT model for both the internal validation cohort (area under the curve [AUC] = 0.932 vs. 0.917) and external validation cohort (AUC = 0.902 vs. 0.767). The model showed capability in discriminating BEOT vs. early-stage MEOT, with AUCs of 0.909 and 0.920, respectively. Radiologist performance was considerably poorer than both the internal (mean AUC = 0.792; range, 0.679-0.924) and external (mean AUC = 0.797; range, 0.744-0.867) validation cohorts. Performance of the MRI-based ML model was robust and superior to subjective assessment of radiologists. If our approach can be implemented in clinical practice, improved preoperative prediction could potentially lead to preserved ovarian function and fertility for some women. Level 4. Stage 2. J. Magn. Reson. Imaging 2020;52:897-904.
Sections du résumé
BACKGROUND
Preoperative differentiation of borderline from malignant epithelial ovarian tumors (BEOT from MEOT) can impact surgical management. MRI has improved this assessment but subjective interpretation by radiologists may lead to inconsistent results.
PURPOSE
To develop and validate an objective MRI-based machine-learning (ML) assessment model for differentiating BEOT from MEOT, and compare the performance against radiologists' interpretation.
STUDY TYPE
Retrospective study of eight clinical centers.
POPULATION
In all, 501 women with histopathologically-confirmed BEOT (n = 165) or MEOT (n = 336) from 2010 to 2018 were enrolled. Three cohorts were constructed: a training cohort (n = 250), an internal validation cohort (n = 92), and an external validation cohort (n = 159).
FIELD STRENGTH/SEQUENCE
Preoperative MRI within 2 weeks of surgery. Single- and multiparameter (MP) machine-learning assessment models were built utilizing the following four MRI sequences: T
ASSESSMENT
Diagnostic performance of the models was assessed for both whole tumor (WT) and solid tumor (ST) components. Assessment of the performance of the model in discriminating BEOT vs. early-stage MEOT was made. Six radiologists of varying experience also interpreted the MR images.
STATISTICAL TESTS
Mann-Whitney U-test: significance of the clinical characteristics; chi-square test: difference of label; DeLong test: difference of receiver operating characteristic (ROC).
RESULTS
The MP-ST model performed better than the MP-WT model for both the internal validation cohort (area under the curve [AUC] = 0.932 vs. 0.917) and external validation cohort (AUC = 0.902 vs. 0.767). The model showed capability in discriminating BEOT vs. early-stage MEOT, with AUCs of 0.909 and 0.920, respectively. Radiologist performance was considerably poorer than both the internal (mean AUC = 0.792; range, 0.679-0.924) and external (mean AUC = 0.797; range, 0.744-0.867) validation cohorts.
DATA CONCLUSION
Performance of the MRI-based ML model was robust and superior to subjective assessment of radiologists. If our approach can be implemented in clinical practice, improved preoperative prediction could potentially lead to preserved ovarian function and fertility for some women.
LEVEL OF EVIDENCE
Level 4.
TECHNICAL EFFICACY
Stage 2. J. Magn. Reson. Imaging 2020;52:897-904.
Types de publication
Journal Article
Multicenter Study
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
897-904Informations de copyright
© 2020 International Society for Magnetic Resonance in Medicine.
Références
Hauptmann S, Friedrich K, Redline R, Avril S. Ovarian borderline tumors in the 2014 WHO classification: Evolving concepts and diagnostic criteria. Virchows Arch 2017;470:125-142.
Silverberg SG, Bell DA, Kurman RJ, et al. Borderline ovarian tumors: Key points and workshop summary. Hum Pathol 2004;35:910-917.
Sun L, Li N, Song Y, Wang G, Zhao Z, Wu L. Clinicopathologic features and risk factors for recurrence of mucinous borderline ovarian tumors: A retrospective study with follow-up of more than 10 years. Int J Gynecol Cancer 2018;28:1643-1649.
Guleria S, Jensen A, Kjaer SK. Risk of borderline ovarian tumors among women with benign ovarian tumors: A cohort study. Gynecol Oncol 2018;148:86-90.
Gershenson DM. Management of borderline ovarian tumours. Best Pract Res Clin Obstet Gynaecol 2017;41:49-59.
Morgan RJ Jr, Armstrong DK, Alvarez RD, et al. Ovarian cancer, version 1.2016, NCCN clinical practice guidelines in oncology. J Natl Compr Canc Netw 2016;14:1134.
Colombo N, Peiretti M, Parma G, et al. Newly diagnosed and relapsed epithelial ovarian carcinoma: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol 2010;21(Suppl 5):v23-v30.
Denewar FA, Takeuchi M, Urano M, et al. Multiparametric MRI for differentiation of borderline ovarian tumors from stage I malignant epithelial ovarian tumors using multivariate logistic regression analysis. Eur J Radiol 2017;91:116-123.
Borrelli GM, de Mattos LA, Andres M de P, Gonçalves MO, Kho RM, Abrão MS. Role of imaging tools for the diagnosis of borderline ovarian tumors: A systematic review and meta-analysis. J Minim Invasive Gynecol 2017;24:353-363.
Hashmi AA, Naz S, Edhi MM, et al. Accuracy of intraoperative frozen section for the evaluation of ovarian neoplasms: An institutional experience. World J Surg Oncol 2016;14:1-5.
Ratnavelu ND, Brown AP, Mallett S, et al. Intraoperative frozen section analysis for the diagnosis of early stage ovarian cancer in suspicious pelvic masses. Cochrane Database Syst Rev 2016;3:CD010360.
Yumiko Oishi T, Satoshi O, Toyomi S, et al. Ovarian serous surface papillary borderline tumors form sea anemone-like masses. J Magn Reson Imaging 2015;33:633-640.
Khiewvan B, Torigian DA, Emamzadehfard S, et al. An update on the role of PET/CT and PET/MRI in ovarian cancer. Eur J Nucl Med Mol Imaging 2017;44:1079-1091.
Valentin L, Ameye L, Savelli L, et al. Unilocular adnexal cysts with papillary projections but no other solid components: Is there a diagnostic method that can classify them reliably as benign or malignant before surgery? Ultrasound Obstet Gynecol 2013;41:570-581.
Moro F, Poma CB, Zannoni GF, Urbinati AV, Testa AC. Imaging in gynecological disease: Clinical and ultrasound features of invasive and non-invasive malignant serous ovarian tumors: Serous ovarian tumors and ultrasound. Ultrasound Obstet Gynecol 2017;50:788-799.
Shetty MK. Adnexal masses: Role of supplemental imaging with magnetic resonance imaging. Semin Ultrasound CT MRI 2015;36:369-384.
Zhao SH, Qiang JW, Zhang GF, et al. Diffusion-weighted MR imaging for differentiating borderline from malignant epithelial tumours of the ovary: Pathological correlation. Eur Radiol 2014;24:2292-2299.
Li HM, Zhao SH, Qiang JW, et al. Diffusion kurtosis imaging for differentiating borderline from malignant epithelial ovarian tumors: A correlation with Ki-67 expression: DKI for differentiating BEOT from MEOT. J Magn Reson Imaging 2017;46:1499-1506.
Ma FH, Li YA, Liu J, Li HM, Zhang GF, Qiang JW. Role of proton MR spectroscopy in the differentiation of borderline from malignant epithelial ovarian tumors: A preliminary study. J Magn Reson Imaging 2019;49:1684-1693.
Hricak H, Chen M, Coakley FV, et al. Complex adnexal masses: Detection and characterization with MR imaging-Multivariate analysis. Radiology 2000;214:39-46.
Wang J, Wu C-J, Bao M-L, Zhang J, Wang X-N, Zhang Y-D. Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer. Eur Radiol 2017;27:4082-4090.
Meng X, Xia W, Xie P, et al. Preoperative radiomic signature based on multiparametric magnetic resonance imaging for noninvasive evaluation of biological characteristics in rectal cancer. Eur Radiol 2019;29:3200-3209.
van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res 2017;77:e104-e107.
Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 2005;27:1226-1238.
Huang Y, Liang C, He L, et al. Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 2016;34:2157-2164.
Haenssle HA, Fink C, Schneiderbauer R, et al. Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol Off J Eur Soc Med Oncol 2018;29:1836-1842.
DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics 1988;44:837-845.
Bonekamp D, Kohl S, Wiesenfarth M, et al. Radiomic machine learning for characterization of prostate lesions with MRI: Comparison to ADC values. Radiology 2018;289:128-137.
Li H, Zhu Y, Burnside ES, et al. MR imaging radiomics signatures for predicting the risk of breast cancer recurrence as given by research versions of MammaPrint, Oncotype DX, and PAM50 gene assays. Radiology 2016;281:382-391.
Song J, Shi J, Dong D, et al. A new approach to predict progression-free survival in stage IV EGFR-mutant NSCLC patients with EGFR-TKI therapy. Clin Cancer Res 2018;24:3583-3592.
Jayson GC, Kohn EC, Kitchener HC, Ledermann JA. Ovarian cancer. Lancet 2014;384:1376-1388.
Satoh T, Yoshikawa H. Fertility-sparing surgery for early stage epithelial ovarian cancer. Jpn J Clin Oncol 2016;46:703-710.
Morice P. Borderline tumours of the ovary and fertility. Eur J Cancer 2006;42:149-158.
Palomba S, Zupi E, Russo T, et al. Comparison of two fertility-sparing approaches for bilateral borderline ovarian tumours: A randomized controlled study. Hum Reprod 2007;22:578-585.
Pi S, Cao R, Qiang JW, Guo YH. Utility of DWI with quantitative ADC values in ovarian tumors: A meta-analysis of diagnostic test performance. Acta Radiol 2018;59:1386-1394.
Michielsen K, Dresen R, Vanslembrouck R, et al. Diagnostic value of whole body diffusion-weighted MRI compared to computed tomography for pre-operative assessment of patients suspected for ovarian cancer. Eur J Cancer 2017;83:88-98.
Li YA, Qiang JW, Ma FH, Li HM, Zhao SH. MRI features and score for differentiating borderline from malignant epithelial ovarian tumors. Eur J Radiol 2018;98:136-142.