Classification of Benign and Malignant Ovarian Masses Based on Quantitative Parameters of DCE-MRI

Authors

Anahita Fathi Kazerooni1, Mohammad Hadi Aarabi1, Elaheh Kia1, Hamidreza Saligheh Rad1,*

Abstract

Background:

Accurate characterization of benign and malignant ovarian cancers plays a critical role in decision making about the therapeutic strategy, treatment monitoring, and could highly affect the treatment outcome. In this context, dynamic contrast enhanced (DCE-) MRI has evolved into a helpful imaging technique in distinguishing complex adnexal masses by providing noninvasive and quantitative biomarkers of tumor progression. Reliable prediction of malignancy in complex adnexal masses depends on proper selection of quantitative DCE-MRI descriptive parameters and their cutoff points, which the latter is commonly carried out by threshold criteria.

Objectives:

In this work, we exploited an unsupervised, non-parametric clustering algorithm, which does not require any prior or expert knowledge about the thresholds to select the optimal predictor parameters, followed by introducing a classification decision-tree for accurate differentiation of malignant from benign ovarian tumors.

Patients and Methods:

Data Acquisition: Twenty-two patients diagnosed with solid or solid/cystic complex ovarian masses (12 benign and 10 malignant as identified with histological assessment) underwent DCE-MR imaging on a 3T MR scanner (Siemens MAGNETOM Tim TRIO) using a surface phased-array coil, TE/TR = 1.74/5 ms, flip angle = 60, image matrix = 156x192, FOV = 23x23 cm2, slice thickness = 5 mm, number of measurements = 52 at 6 s/volume, number of slices = 16. The acquisition was performed before and immediately after injection of 0.2mL/kg of Gadolinium (DOTAREM; Guerbet, Aulnay, France), followed by injection of 20 cc normal saline solution with 3 mL/min injection rate. Pre-processing: All images were corrected for motion artifacts, using an efficient non-rigid image registration approach in a groupwise setting. Data Quantification: The regions-of-interest (ROIs) were placed on the solid part of tumors and within the adjacent psoas (as an internal reference). Several semi-quantitative parameters were used for further analysis and clustering of the signal intensity curves: SImax = maximum signal intensity of tumor to that of psoas, TTP: Time-to-Peak, Wash-in-Rate (WIR) = (SImax-SI0)/TTP, IAUC60 = initial area under the time-intensity curve during the first 60 seconds in tumor to that of psoas. Clustering: Clustering was performed for each descriptive parameter, using unsupervised Hierarchical Clustering (HC) with Wards linkage method, before and after registration, to both determine the best descriptive parameters for diagnosing malignant from benign tumors and evaluate the effects of registration on the outcome of diagnosis.

Results:

The box-and-whisker plots for TTP, SImax, WIR, and IAUC60 for both benign and malignant tumors were shown. TTP and WIR parameters led to none and small overlaps between enhancement characteristics of benign and malignant tumors, respectively, suggesting their reliability in distinguishing cancer types. The sensitivity and specificity of each parameter in diagnosing malignancy in complex ovarian cancers are summarized. As it can be inferred, WIR parameter returns a sensitivity of 100% in distinguishing malignant tumors (both before and after registration), and TTP produces the best specificity in comparison with SImax and IAUC60 parameters. In several studies, the early enhancement (TTP) is confirmed to be an indication of malignancy, and WIR is shown to be correlated with the expression of vascular endothelial growth factor (VEGF). Also, it can be observed that registration can significantly improve the outcome of tumor characterization, in the sense that the parameters would become more reliable to characterize the cancer malignancy. In view of these results, WIR and TTP were combined to develop a decision tree for classification of malignant from benign tumors, which generated promising results on the data with 95% of accuracy before and 100% after registration.

Conclusions:

This result recommends that optimizing the decision approach could compensate for misalignment of data, which is essentially important when proper registration software is not available or feasible in a clinical diagnosis setting. In conclusion, we proposed a decision tree classifier developed through an unsupervised clustering approach, which is unbiased to the threshold values of the parameters and provides a more flexible framework for increasing the positive prediction rate for distinguishing malignant from benign complex ovarian tumors.

Highlights

How to Cite:Fathi Kazerooni A, Aarabi MH, Kia E, Saligheh Rad H. Classification of Benign and Malignant Ovarian Masses Based on Quantitative Parameters of DCE-MRI. I J Radiol. 2014;11(30th Iranian Congress of Radiology):e21391. doi: https://doi.org/10.5812/iranjradiol.21391

Full Text

Full text is available in PDF

Copyright

© 2014, Author(s). This open-access article is available under the Creative Commons Attribution 4.0 (CC BY 4.0) International License (https://creativecommons.org/licenses/by/4.0/), which allows for unrestricted use, distribution, and reproduction in any medium, provided that the original work is properly cited.

Similar Articles

28
Feb
2014

A Review Study on the efficacy of Quantitative DCE-MRI in Adnexal Lesion Diagnosis

Sahar Rezaei,
Hamidreza Saligheh Rad

Rezaei S, Saligheh Rad H. A Review Study on the efficacy of Quantitative DCE-MRI in Adnexal Lesion Diagnosis. I J Radiol. 2014;11(30th Iranian Congress of Radiology):e21335. doi: https://doi.org/10.5812/iranjradiol.21335

28
Feb
2014

Effectiveness of Semi-Quantitative Multiphase Dynamic Contrast-Enhanced MRI at 3 Tesla as a Predictor of Malignancy in Adnexal Masses

Leila Torbati,
Mahrooz Malek

Torbati L, Malek M. Effectiveness of Semi-Quantitative Multiphase Dynamic Contrast-Enhanced MRI at 3 Tesla as a Predictor of Malignancy in Adnexal Masses. I J Radiol. 2014;11(30th Iranian Congress of Radiology):e21333. doi: https://doi.org/10.5812/iranjradiol.21333

28
Feb
2014

Improved Quantification of Dynamic Contrast Enhanced MR Imaging (DCE-MRI) in Adnexal Masses by Elastic Registration Method

Elaheh Kia,
Anahita Fathi Kazerooni,
Alireza Ahmadian,
Hamidreza Saligheh Rad

Kia E, Fathi Kazerooni A, Ahmadian A, Saligheh Rad H. Improved Quantification of Dynamic Contrast Enhanced MR Imaging (DCE-MRI) in Adnexal Masses by Elastic Registration Method. I J Radiol. 2014;11(30th Iranian Congress of Radiology):e21290. doi: https://doi.org/10.5812/iranjradiol.21290

28
Feb
2014
A Review Study on the Efficacy of Quantitative DCE-MRI in Breast Lesion Diagnosis

A Review Study on the Efficacy of Quantitative DCE-MRI in Breast Lesion Diagnosis

Sahar Rezaei,
Hamidreza Saligheh Rad

Rezaei S, Saligheh Rad H. A Review Study on the Efficacy of Quantitative DCE-MRI in Breast Lesion Diagnosis. I J Radiol. 2014;11(30th Iranian Congress of Radiology):e21252. doi: https://doi.org/10.5812/iranjradiol.21252

23
Jan
2016
Significance of Additional Non-Mass Enhancement in Patients with Breast Cancer on Preoperative 3T Dynamic Contrast Enhanced MRI of the Breast

Significance of Additional Non-Mass Enhancement in Patients with Breast Cancer on Preoperative 3T Dynamic Contrast Enhanced MRI of the Breast

Yun Hee Cho,
Kyu Ran Cho,
Eun Kyung Park,
Bo Kyoung Seo,
Ok Hee Woo,
Sung Bum Cho
,et al.

Cho YH, Cho KR, Park EK, Seo BK, Woo OH, et al. Significance of Additional Non-Mass Enhancement in Patients with Breast Cancer on Preoperative 3T Dynamic Contrast Enhanced MRI of the Breast. I J Radiol. 2016;13(1):e30909. doi: https://doi.org/10.5812/iranjradiol.30909

More by these authors

Anahita Fathi KazerooniPubMedScholar
Mohammad Hadi AarabiPubMedScholar
Elaheh KiaPubMedScholar
Hamidreza Saligheh RadPubMedScholar
Share
Cited by
Metrics