Abstract
Purpose
To compare CT texture features of benign and malignant ovarian lesions and to build a machine learning model to detect malignancy in incidental ovarian lesions.
Methods
In this IRB-approved, HIPAA-compliant, retrospective study, 427 consecutive patients with incidental ovarian lesions detected on contrast-enhanced CT (348, 81.5% benign and 79, 18.5% malignant) were included. The following CT texture features were analyzed using commercially available software (TexRAD, Feedback Plc, Cambridge, UK): total pixel, mean, standard deviation (SD), entropy, mean value of positive pixels (MPP), skewness, kurtosis and entropy. Three machine learning models were created by combining texture features and patients’ age, and performance of these models was assessed using tenfold cross-validation. Receiver operating characteristics (ROC) were constructed to assess sensitivity and specificity. The cutoff value was picked using a cost-weighted method.
Results
Total pixels, mean, SD, entropy, MPP, and skewness were significantly different between benign and malignant groups (p < 0.05). With a selected 10 as a cost factor to optimize cutoff value selection, sensitivity 92%, specificity 60% in the random forest (RF) model, sensitivity 91%, specificity 69% in SVM model, and sensitivity 92%, specificity 61% in the logistic regression, respectively.
Conclusion
CT texture analysis could provide objective imaging analysis of incidental ovarian lesions and ML models using CT texture features and age demonstrated high sensitivity and moderate specificity for detection of malignant lesions.
Similar content being viewed by others
Data availability
Yes.
Code availability
Yes.
Abbreviations
- ML:
-
Machine learning
- LR:
-
Logistic regression
- SVM:
-
Support vector machine
- RF:
-
Random forest
- MPP:
-
Mean value of positive pixels
References
Spencer JA, Gore RM. The adnexal incidentaloma: a practical approach to management. Cancer imaging : the official publication of the International Cancer Imaging Society 2011;11:48-51. https://doi.org/10.1102/1470-7330.2011.0008
Jung SE, Lee JM, Rha SE, Byun JY, Jung JI, Hahn ST. CT and MR imaging of ovarian tumors with emphasis on differential diagnosis. Radiographics : a review publication of the Radiological Society of North America, Inc 2002;22(6):1305-1325. https://doi.org/10.1148/rg.226025033
Boos J, Brook OR, Fang J, Brook A, Levine D. Ovarian Cancer: Prevalence in Incidental Simple Adnexal Cysts Initially Identified in CT Examinations of the Abdomen and Pelvis. Radiology 2018;286(1):196-204. https://doi.org/10.1148/radiol.2017162139
Slanetz PJ, Hahn PF, Hall DA, Mueller PR. The frequency and significance of adnexal lesions incidentally revealed by CT. AJR American journal of roentgenology 1997;168(3):647-650. https://doi.org/10.2214/ajr.168.3.9057508
Patel MD, Ascher SM, Paspulati RM, Shanbhogue AK, Siegelman ES, Stein MW, Berland LL. Managing incidental findings on abdominal and pelvic CT and MRI, part 1: white paper of the ACR Incidental Findings Committee II on adnexal findings. Journal of the American College of Radiology : JACR 2013;10(9):675-681. https://doi.org/10.1016/j.jacr.2013.05.023
Forstner R, Thomassin-Naggara I, Cunha TM, Kinkel K, Masselli G, Kubik-Huch R, Spencer JA, Rockall A. ESUR recommendations for MR imaging of the sonographically indeterminate adnexal mass: an update. European radiology 2017;27(6):2248-2257. https://doi.org/10.1007/s00330-016-4600-3
Shinagare AB, Alper E, Wang A, Ip IK, Khorasani R. Impact of a Multifaceted Information Technology-Enabled Intervention on the Adoption of ACR White Paper Follow-Up Recommendations for Incidental Adnexal Lesions Detected on CT. AJR American journal of roentgenology 2019:1-7. https://doi.org/10.2214/ajr.18.20468
Andreotti RF, Timmerman D, Strachowski LM, Froyman W, Benacerraf BR, Bennett GL, Bourne T, Brown DL, Coleman BG, Frates MC, Goldstein SR, Hamper UM, Horrow MM, Hernanz-Schulman M, Reinhold C, Rose SL, Whitcomb BP, Wolfman WL, Glanc P. O-RADS US Risk Stratification and Management System: A Consensus Guideline from the ACR Ovarian-Adnexal Reporting and Data System Committee. Radiology 2019:191150. https://doi.org/10.1148/radiol.2019191150
Levine D, Patel MD, Suh-Burgmann EJ, Andreotti RF, Benacerraf BR, Benson CB, Brewster WR, Coleman BG, Doubilet PM, Goldstein SR, Hamper UM, Hecht JL, Horrow MM, Hur HC, Marnach ML, Pavlik E, Platt LD, Puscheck E, Smith-Bindman R, Brown DL. Simple Adnexal Cysts: SRU Consensus Conference Update on Follow-up and Reporting. Radiology 2019;293(2):359-371. https://doi.org/10.1148/radiol.2019191354
Lubner MG, Smith AD, Sandrasegaran K, Sahani DV, Pickhardt PJ. CT Texture Analysis: Definitions, Applications, Biologic Correlates, and Challenges. Radiographics : a review publication of the Radiological Society of North America, Inc 2017;37(5):1483-1503. https://doi.org/10.1148/rg.2017170056
Thomas R, Qin L, Alessandrino F, Sahu SP, Guerra PJ, Krajewski KM, Shinagare A. A review of the principles of texture analysis and its role in imaging of genitourinary neoplasms. Abdominal radiology (New York) 2018. https://doi.org/10.1007/s00261-018-1832-5
Chee CG, Kim YH, Lee KH, Lee YJ, Park JH, Lee HS, Ahn S, Kim B. CT texture analysis in patients with locally advanced rectal cancer treated with neoadjuvant chemoradiotherapy: A potential imaging biomarker for treatment response and prognosis. PloS one 2017;12(8):e0182883. https://doi.org/10.1371/journal.pone.0182883
Fan TW, Malhi H, Varghese B, Cen S, Hwang D, Aron M, Rajarubendra N, Desai M, Duddalwar V. Computed tomography-based texture analysis of bladder cancer: differentiating urothelial carcinoma from micropapillary carcinoma. Abdominal radiology (New York) 2019;44(1):201-208. https://doi.org/10.1007/s00261-018-1694-x
Lubner MG, Stabo N, Abel EJ, Del Rio AM, Pickhardt PJ. CT Textural Analysis of Large Primary Renal Cell Carcinomas: Pretreatment Tumor Heterogeneity Correlates With Histologic Findings and Clinical Outcomes. AJR American journal of roentgenology 2016;207(1):96-105. https://doi.org/10.2214/ajr.15.15451
Sandrasegaran K, Lin Y, Asare-Sawiri M, Taiyini T, Tann M. CT texture analysis of pancreatic cancer. European radiology 2019;29(3):1067-1073. https://doi.org/10.1007/s00330-018-5662-1
Vargas HA, Veeraraghavan H, Micco M, Nougaret S, Lakhman Y, Meier AA, Sosa R, Soslow RA, Levine DA, Weigelt B, Aghajanian C, Hricak H, Deasy J, Snyder A, Sala E. A novel representation of inter-site tumour heterogeneity from pre-treatment computed tomography textures classifies ovarian cancers by clinical outcome. European radiology 2017;27(9):3991-4001. https://doi.org/10.1007/s00330-017-4779-y
Meier A, Veeraraghavan H, Nougaret S, Lakhman Y, Sosa R, Soslow RA, Sutton EJ, Hricak H, Sala E, Vargas HA. Association between CT-texture-derived tumor heterogeneity, outcomes, and BRCA mutation status in patients with high-grade serous ovarian cancer. Abdominal radiology (New York) 2019;44(6):2040-2047. https://doi.org/10.1007/s00261-018-1840-5
Beer L, Sahin H, Bateman NW, Blazic I, Vargas HA, Veeraraghavan H, Kirby J, Fevrier-Sullivan B, Freymann JB, Jaffe CC, Brenton J, Miccó M, Nougaret S, Darcy KM, Maxwell GL, Conrads TP, Huang E, Sala E. Integration of proteomics with CT-based qualitative and radiomic features in high-grade serous ovarian cancer patients: an exploratory analysis. European radiology 2020. https://doi.org/10.1007/s00330-020-06755-3
Acharya UR, Molinari F, Sree SV, Swapna G, Saba L, Guerriero S, Suri JS. Ovarian tissue characterization in ultrasound: a review. Technology in cancer research & treatment 2015;14(3):251-261. https://doi.org/10.1177/1533034614547445
Acharya UR, Sree SV, Saba L, Molinari F, Guerriero S, Suri JS. Ovarian tumor characterization and classification using ultrasound-a new online paradigm. Journal of digital imaging 2013;26(3):544-553. https://doi.org/10.1007/s10278-012-9553-8
Nougaret S, Tardieu M, Vargas HA, Reinhold C, Vande Perre S, Bonanno N, Sala E, Thomassin-Naggara I. Ovarian cancer: An update on imaging in the era of radiomics. Diagnostic and interventional imaging 2018. https://doi.org/10.1016/j.diii.2018.11.007
Levine D, Brown DL, Andreotti RF, Benacerraf B, Benson CB, Brewster WR, Coleman B, DePriest P, Doubilet PM, Goldstein SR, Hamper UM, Hecht JL, Horrow M, Hur HC, Marnach M, Patel MD, Platt LD, Puscheck E, Smith-Bindman R. Management of asymptomatic ovarian and other adnexal cysts imaged at US Society of Radiologists in Ultrasound consensus conference statement. Ultrasound quarterly 2010;26(3):121-131. https://doi.org/10.1097/RUQ.0b013e3181f09099
McLemore MR, Miaskowski C, Aouizerat BE, Chen LM, Dodd MJ. Epidemiological and genetic factors associated with ovarian cancer. Cancer nursing 2009;32(4):281-288; quiz 289-290. https://doi.org/10.1097/NCC.0b013e31819d30d6
Youden WJ. Index for rating diagnostic tests. Cancer 1950;3(1):32-35. https://doi.org/10.1002/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3
Perkins NJ, Schisterman EF. The inconsistency of "optimal" cutpoints obtained using two criteria based on the receiver operating characteristic curve. American journal of epidemiology 2006;163(7):670-675. https://doi.org/10.1093/aje/kwj063
Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC, Muller M. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC bioinformatics 2011;12:77. https://doi.org/10.1186/1471-2105-12-77
Kuhn M, Contributions from Jed Wing SW, Andre Williams, Chris Keefer, Allan Engelhardt, Tony Cooper, Zachary Mayer, Brenton Kenkel, the R Core Team, Michael Benesty, Reynald Lescarbeau, Andrew Ziem, Luca Scrucca, Yuan Tang, Can Candan, and Tyler Hunt. Package ‘caret’: Classification and Regression Training. 2019.
Davnall F, Yip CS, Ljungqvist G, Selmi M, Ng F, Sanghera B, Ganeshan B, Miles KA, Cook GJ, Goh V. Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? Insights into imaging 2012;3(6):573-589. https://doi.org/10.1007/s13244-012-0196-6
Hanania AN, Bantis LE, Feng Z, Wang H, Tamm EP, Katz MH, Maitra A, Koay EJ. Quantitative imaging to evaluate malignant potential of IPMNs. Oncotarget 2016;7(52):85776-85784. https://doi.org/10.18632/oncotarget.11769
Ng F, Kozarski R, Ganeshan B, Goh V. Assessment of tumor heterogeneity by CT texture analysis: can the largest cross-sectional area be used as an alternative to whole tumor analysis? European journal of radiology 2013;82(2):342-348. https://doi.org/10.1016/j.ejrad.2012.10.023
Funding
The authors state that this work has not received any funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Ethical approval
Institutional Review Board approval was obtained, and informed consent was waived.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Park, H., Qin, L., Guerra, P. et al. Decoding incidental ovarian lesions: use of texture analysis and machine learning for characterization and detection of malignancy. Abdom Radiol 46, 2376–2383 (2021). https://doi.org/10.1007/s00261-020-02668-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00261-020-02668-3