Top

Published in:

Open Access 01-12-2023 | Magnetic Resonance Imaging | Critical Review

Analysis of computer-aided diagnostics in the preoperative diagnosis of ovarian cancer: a systematic review

Authors: Anna H. Koch, Lara S. Jeelof, Caroline L. P. Muntinga, T. A. Gootzen, Nienke M. A. van de Kruis, Joost Nederend, Tim Boers, Fons van der Sommen, Jurgen M. J. Piek

Published in: Insights into Imaging | Issue 1/2023

Abstract

Objectives

Different noninvasive imaging methods to predict the chance of malignancy of ovarian tumors are available. However, their predictive value is limited due to subjectivity of the reviewer. Therefore, more objective prediction models are needed. Computer-aided diagnostics (CAD) could be such a model, since it lacks bias that comes with currently used models. In this study, we evaluated the available data on CAD in predicting the chance of malignancy of ovarian tumors.

Methods

We searched for all published studies investigating diagnostic accuracy of CAD based on ultrasound, CT and MRI in pre-surgical patients with an ovarian tumor compared to reference standards.

Results

In thirty-one included studies, extracted features from three different imaging techniques were used in different mathematical models. All studies assessed CAD based on machine learning on ultrasound, CT scan and MRI scan images. Per imaging method, subsequently ultrasound, CT and MRI, sensitivities ranged from 40.3 to 100%; 84.6–100% and 66.7–100% and specificities ranged from 76.3–100%; 69–100% and 77.8–100%. Results could not be pooled, due to broad heterogeneity. Although the majority of studies report high performances, they are at considerable risk of overfitting due to the absence of an independent test set.

Conclusion

Based on this literature review, different CAD for ultrasound, CT scans and MRI scans seem promising to aid physicians in assessing ovarian tumors through their objective and potentially cost-effective character. However, performance should be evaluated per imaging technique. Prospective and larger datasets with external validation are desired to make their results generalizable.

Available only for authorised users

Geomini PM, Kruitwagen RF, Bremer GL, Massuger L, Mol BW (2011) Should we centralise care for the patient suspected of having ovarian malignancy? Gynecol Oncol 122(1):95–99. https://doi.org/10.1016/j.ygyno.2011.03.005CrossRefPubMed

Jacobs I, Oram D, Fairbanks J, Turner J, Frost C, Grudzinskas JG (1990) A risk of malignancy index incorporating CA 125, ultrasound and menopausal status for the accurate preoperative diagnosis of ovarian cancer. Br J Obstet Gynaecol 97:922–929. https://doi.org/10.1111/j.1471-0528.1990.tb02448.xCrossRefPubMed

Van Calster B, Van Hoorde K, Valentin L et al (2014) Evaluating the risk of ovarian cancer before surgery using the ADNEX model to differentiate between benign, borderline, early and advanced stage invasive, and secondary metastatic tumours: prospective multicentre diagnostic study. BMJ 349:g5920. https://doi.org/10.1136/bmj.g5920CrossRefPubMedPubMedCentral

Van Calster B, Valentin L, Froyman W et al (2020) Validation of models to diagnose ovarian cancer in patients managed surgically or conservatively: multicentre cohort study. BMJ 370:m2614. https://doi.org/10.1136/bmj.m2614CrossRefPubMedPubMedCentral

Meys EMJ, Jeelof LS, Achten NMJ et al (2017) Estimating risk of malignancy in adnexal masses: external validation of the ADNEX model and comparison with other frequently used ultrasound methods. Ultrasound Obstet Gynecol 49(6):784–792. https://doi.org/10.1002/uog.17225CrossRefPubMedPubMedCentral

Basha MAA, Metwally MI, Gamil SA et al (2021) Comparison of O-RADS, GI-RADS, and IOTA simple rules regarding malignancy rate, validity, and reliability for diagnosis of adnexal masses. Eur Radiol 31(2):674–684. https://doi.org/10.1007/s00330-020-07143-7CrossRefPubMed

Timmerman D, Planchamp F, Bourne T et al (2021) ESGO/ISUOG/IOTA/ESGE Consensus Statement on pre-operative diagnosis of ovarian tumors. Int J Gynecol Cancer 31(7):961–982. https://doi.org/10.1136/ijgc-2021-002565CrossRefPubMedPubMedCentral

Meys E, Rutten I, Kruitwagen R, et al. Simple Rules, Not So Simple: The Use of International Ovarian Tumor Analysis (IOTA) Terminology and Simple Rules in Inexperienced Hands in a Prospective Multicenter Cohort Study. Ultraschall Med. 2017;38(6):633–641. "Simple Rules" - nicht so einfach: Anwendung der "International Ovarian Tumor Analysis" (IOTA)- Terminologie und der "Simple Rules" in unerfahrenen Handen in einer prospektiven multizentrischen Kohortenstudie. doi:https://doi.org/10.1055/s-0043-113819

Shimada K, Matsumoto K, Mimura T et al (2018) Ultrasound-based logistic regression model LR2 versus magnetic resonance imaging for discriminating between benign and malignant adnexal masses: a prospective study. Int J Clin Oncol 23(3):514–521. https://doi.org/10.1007/s10147-017-1222-yCrossRefPubMed

10.

Thomassin-Naggara I, Poncelet E, Jalaguier-Coudray A et al (2020) Ovarian-adnexal reporting data system magnetic resonance imaging (O-RADS MRI) score for risk stratification of sonographically indeterminate adnexal masses. JAMA Netw Open. 3(1):e1919896. https://doi.org/10.1001/jamanetworkopen.2019.19896CrossRefPubMedPubMedCentral

11.

Mukhtar S, Khan SA, Hussain M, Adil SO (2017) Role of multidetector computed tomography in evaluation of ovarian lesions in women clinically suspected of malignancy. Asian Pac J Cancer Prev 18(8):2059–2062. https://doi.org/10.22034/apjcp.2017.18.8.2059CrossRefPubMedPubMedCentral

12.

Walker SP, The ROC (2019) Curve redefined—optimizing sensitivity (and specificity) to the lived reality of cancer. N Engl J Med 380(17):1594–1595. https://doi.org/10.1056/NEJMp1814951CrossRefPubMed

13.

Lange RT, Lippa SM (2017) Sensitivity and specificity should never be interpreted in isolation without consideration of other clinical utility metrics. Clin Neuropsychol 31(6–7):1015–1028. https://doi.org/10.1080/13854046.2017.1335438CrossRefPubMed

14.

Biagiotti R, Desii C, Vanzi E, Gacci G (1999) Predicting ovarian malignancy: application of artificial neural networks to transvaginal and color Doppler flow US. Radiology 210(2):399–403. https://doi.org/10.1148/radiology.210.2.r99fe18399CrossRefPubMed

15.

Timmerman D, Verrelst H, Bourne TH et al (1999) Artificial neural network models for the preoperative discrimination between malignant and benign adnexal masses. Ultrasound Obstet Gynecol 13(1):17–25. https://doi.org/10.1046/j.1469-0705.1999.13010017.xCrossRefPubMed

16.

Zimmer Y, Tepper R, Akselrod S (1999) Computerized quantification of structures within ovarian cysts using ultrasound images. Ultrasound Med Biol 25(2):189–200. https://doi.org/10.1016/s0301-5629(98)00150-1CrossRefPubMed

17.

Chilamkurthy S, Ghosh R, Tanamala S et al (2018) Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet 392(10162):2388–2396. https://doi.org/10.1016/s0140-6736(18)31645-3CrossRefPubMed

18.

Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118. https://doi.org/10.1038/nature21056CrossRefPubMedPubMedCentral

19.

Ehteshami Bejnordi B, Veta M, Johannes van Diest P et al (2017) Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318(22):2199–2210. https://doi.org/10.1001/jama.2017.14585CrossRefPubMedPubMedCentral

20.

Lakhani P, Sundaram B (2017) Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284(2):574–582. https://doi.org/10.1148/radiol.2017162326CrossRefPubMed

21.

Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14(12):749–762. https://doi.org/10.1038/nrclinonc.2017.141CrossRefPubMed

22.

Mysona DP, Kapp DS, Rohatgi A et al (2021) Applying artificial intelligence to gynecologic oncology: a review. Obstet Gynecol Surv 76(5):292–301. https://doi.org/10.1097/ogx.0000000000000902CrossRefPubMed

23.

Veritas Health Innovation M, Australia. Covidence systematic review software. website. Covidence systematic review software, Veritas Health Innovation. Updated 2022. Accessed 09–05–2022, https://www.covidence.org/

24.

Zamora J, Abraira V, Muriel A, Khan K, Coomarasamy A (2006) Meta-DiSc: a software for meta-analysis of test accuracy data. BMC Med Res Methodol 6:31. https://doi.org/10.1186/1471-2288-6-31CrossRefPubMedPubMedCentral

25.

Higgins JP, Thompson SG, Deeks JJ, Altman DG (2003) Measuring inconsistency in meta-analyses. BMJ 327(7414):557–560. https://doi.org/10.1136/bmj.327.7414.557CrossRefPubMedPubMedCentral

26.

Moses LE, Shapiro D, Littenberg B (1993) Combining independent studies of a diagnostic test into a summary ROC curve: data-analytic approaches and some additional considerations. Stat Med 12(14):1293–1316. https://doi.org/10.1002/sim.4780121403CrossRefPubMed

27.

Wolff RF, Moons KGM, Riley RD et al (2019) PROBAST: a tool to assess the risk of bias and applicability of prediction model studies. Ann Intern Med 170(1):51–58. https://doi.org/10.7326/m18-1376CrossRefPubMed

28.

Moons KGM, Wolff RF, Riley RD et al (2019) PROBAST: a tool to assess risk of bias and applicability of prediction model studies: explanation and elaboration. Ann Intern Med 170(1):W1–W33. https://doi.org/10.7326/M18-1377CrossRefPubMed

29.

Whiting PF, Rutjes AW, Westwood ME et al (2011) QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med 155(8):529–536. https://doi.org/10.7326/0003-4819-155-8-201110180-00009CrossRefPubMed

30.

Hayden JA, van der Windt DA, Cartwright JL, Cote P, Bombardier C (2013) Assessing bias in studies of prognostic factors. Ann Intern Med 158(4):280–286. https://doi.org/10.7326/0003-4819-158-4-201302190-00009CrossRefPubMed

31.

Moher D, Liberati A, Tetzlaff J, Altman DG (2009) Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. BMJ. 339:b2535. https://doi.org/10.1136/bmj.b2535CrossRefPubMedPubMedCentral

32.

Page MJ, McKenzie JE, Bossuyt PM et al (2021) The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 372:n71. https://doi.org/10.1136/bmj.n71CrossRefPubMedPubMedCentral

33.

Gao Y, Zeng S, Xu X et al (2022) Deep learning-enabled pelvic ultrasound images for accurate diagnosis of ovarian cancer in China: a retrospective, multicentre, diagnostic study. Lancet Digit Health 4(3):e179–e187. https://doi.org/10.1016/s2589-7500(21)00278-8CrossRefPubMed

34.

Chiappa V, Bogani G, Interlenghi M et al (2021) The Adoption of Radiomics and machine learning improves the diagnostic processes of women with Ovarian MAsses (the AROMA pilot study). J Ultrasound 24(4):429–437. https://doi.org/10.1007/s40477-020-00503-5CrossRefPubMed

35.

Chiappa V, Interlenghi M, Bogani G et al (2021) A decision support system based on radiomics and machine learning to predict the risk of malignancy of ovarian masses from transvaginal ultrasonography and serum CA-125. Eur Radiol Exp. 5(1):28. https://doi.org/10.1186/s41747-021-00226-0CrossRefPubMedPubMedCentral

36.

Christiansen F, Epstein EL, Smedberg E, Akerlund M, Smith K, Epstein E (2021) Ultrasound image analysis using deep neural networks for discriminating between benign and malignant ovarian tumors: comparison with expert subjective assessment. Ultrasound Obstet Gynecol 57(1):155–163. https://doi.org/10.1002/uog.23530CrossRefPubMedPubMedCentral

37.

Qi L, Chen D, Li C et al (2021) Diagnosis of ovarian neoplasms using nomogram in combination with ultrasound image-based radiomics signature and clinical factors. Front Genet 12:753948. https://doi.org/10.3389/fgene.2021.753948CrossRefPubMedPubMedCentral

38.

Wang H, Liu C, Zhao Z et al (2021) Application of deep convolutional neural networks for discriminating benign, borderline, and malignant serous ovarian tumors from ultrasound images. Front Oncol. https://doi.org/10.3389/fonc.2021.770683CrossRefPubMedPubMedCentral

39.

Martinez-Mas J, Bueno-Crespo A, Khazendar S et al (2019) Evaluation of machine learning methods with Fourier Transform features for classifying ovarian tumors based on ultrasound images. PLoS One 14(7):e0219388. https://doi.org/10.1371/journal.pone.0219388CrossRefPubMedPubMedCentral

40.

Zhang L, Huang J, Liu L (2019) Improved deep learning network based in combination with cost-sensitive learning for early detection of ovarian cancer in color ultrasound detecting system. J Med Syst. 43(8):251. https://doi.org/10.1007/s10916-019-1356-8CrossRefPubMed

41.

Acharya UR, Akter A, Chowriappa P et al (2018) Use of nonlinear features for automated characterization of suspicious ovarian tumors using ultrasound images in fuzzy forest framework. Int J Fuzzy Syst 20(4):1385–1402. https://doi.org/10.1007/s40815-018-0456-9CrossRef

42.

Acharya UR, Mookiah MR, Vinitha Sree S et al (2014) Evolutionary algorithm-based classifier parameter tuning for automatic ovarian cancer tissue characterization and classification. Ultraschall Med 35(3):237–245. https://doi.org/10.1055/s-0032-1330336CrossRefPubMed

43.

Acharya UR, Sree SV, Krishnan MM et al (2012) Ovarian tumor characterization using 3D ultrasound. Technol Cancer Res Treat 11(6):543–552. https://doi.org/10.7785/tcrt.2012.500272CrossRefPubMed

44.

Acharya UR, Sree SV, Kulshreshtha S et al (2014) GyneScan: an improved online paradigm for screening of ovarian cancer via tissue characterization. Technol Cancer Res Treat 13(6):529–539. https://doi.org/10.7785/tcrtexpress.2013.600273CrossRefPubMed

45.

Acharya UR, Sree SV, Saba L, Molinari F, Guerriero S, Suri JS (2013) Ovarian tumor characterization and classification using ultrasound-a new online paradigm. J Digit Imaging 26(3):544–553. https://doi.org/10.1007/s10278-012-9553-8CrossRefPubMed

46.

Aramendia-Vidaurreta V, Cabeza R, Villanueva A, Navallas J, Alcazar JL (2016) Ultrasound image discrimination between benign and malignant adnexal masses based on a neural network approach. Ultrasound Med Biol 42(3):742–752. https://doi.org/10.1016/j.ultrasmedbio.2015.11.014CrossRefPubMed

47.

Khazendar S, Sayasneh A, Al-Assam H et al (2015) Automated characterisation of ultrasound images of ovarian tumours: the diagnostic accuracy of a support vector machine and image processing with a local binary pattern operator. Facts Views Vis Obgyn 7(1):7–15PubMedPubMedCentral

48.

Faschingbauer F, Beckmann MW, Weyert Goecke T et al (2013) Automatic texture-based analysis in ultrasound imaging of ovarian masses. Ultraschall Med 34(2):145–150. https://doi.org/10.1055/s-0031-1299331CrossRefPubMed

49.

Vaes E, Manchanda R, Autier P et al (2012) Differential diagnosis of adnexal masses: sequential use of the risk of malignancy index and HistoScanning, a novel computer-aided diagnostic tool. Ultrasound Obstet Gynecol 39(1):91–98. https://doi.org/10.1002/uog.9079CrossRefPubMed

50.

Vaes E, Manchanda R, Nir R et al (2011) Mathematical models to discriminate between benign and malignant adnexal masses: potential diagnostic improvement using ovarian HistoScanning. Int J Gynecol Cancer 21(1):35–43. https://doi.org/10.1097/IGC.0b013e3182000528CrossRefPubMed

51.

Lu C, Van Gestel T, Suykens JA, Van Huffel S, Vergote I, Timmerman D (2003) Preoperative prediction of malignancy of ovarian tumors using least squares support vector machines. Artif Intell Med 28(3):281–306. https://doi.org/10.1016/s0933-3657(03)00051-4CrossRefPubMed

52.

Lucidarme O, Akakpo JP, Granberg S et al (2010) A new computer-aided diagnostic tool for non-invasive characterisation of malignant ovarian masses: results of a multicentre validation study. Eur Radiol 20(8):1822–1830. https://doi.org/10.1007/s00330-010-1750-6CrossRefPubMed

53.

Zimmer Y, Tepper R, Akselrod S (2003) An automatic approach for morphological analysis and malignancy evaluation of ovarian masses using B-scans. Ultrasound Med Biol 29(11):1561–1570. https://doi.org/10.1016/j.ultrasmedbio.2003.08.013CrossRefPubMed

54.

Li S, Liu J, Xiong Y et al (2022) Application values of 2D and 3D radiomics models based on CT plain scan in differentiating benign from malignant ovarian tumors. Biomed Res Int 2022:5952296. https://doi.org/10.1155/2022/5952296CrossRefPubMedPubMedCentral

55.

Park H, Qin L, Guerra P, Bay CP, Shinagare AB (2021) Decoding incidental ovarian lesions: use of texture analysis and machine learning for characterization and detection of malignancy. Abdom Radiol (NY) 46(6):2376–2383. https://doi.org/10.1007/s00261-020-02668-3CrossRefPubMed

56.

Li S, Liu J, Xiong Y et al (2021) A radiomics approach for automated diagnosis of ovarian neoplasm malignancy in computed tomography. Sci Rep 11(1):8730. https://doi.org/10.1038/s41598-021-87775-xCrossRefPubMedPubMedCentral

57.

Liu X, Wang T, Zhang G et al (2022) Two-dimensional and three-dimensional T2 weighted imaging-based radiomic signatures for the preoperative discrimination of ovarian borderline tumors and malignant tumors. J Ovarian Res 15(1):22. https://doi.org/10.1186/s13048-022-00943-zCrossRefPubMedPubMedCentral

58.

Song XL, Ren JL, Zhao D, Wang L, Ren H, Niu J (2021) Radiomics derived from dynamic contrast-enhanced MRI pharmacokinetic protocol features: the value of precision diagnosis ovarian neoplasms. Eur Radiol 31(1):368–378. https://doi.org/10.1007/s00330-020-07112-0CrossRefPubMed

59.

Jian J, Li Y, Xia W et al (2021) MRI-based multiple instance convolutional neural network for increased accuracy in the differentiation of borderline and malignant epithelial ovarian tumors. J Magn Reson Imaging. https://doi.org/10.1002/jmri.28008CrossRefPubMed

60.

Zhang H, Mao Y, Chen X et al (2019) Magnetic resonance imaging radiomics in categorizing ovarian masses and predicting clinical outcome: a preliminary study. Eur Radiol 29(7):3358–3371. https://doi.org/10.1007/s00330-019-06124-9CrossRefPubMed

61.

Li Y, Jian J, Pickhardt PJ et al (2020) MRI-based machine learning for differentiating borderline from malignant epithelial ovarian tumors: a multicenter study. J Magn Reson Imaging 52(3):897–904. https://doi.org/10.1002/jmri.27084CrossRefPubMed

62.

Jian J, Xia W, Zhang R et al (2021) Multiple instance convolutional neural network with modality-based attention and contextual multi-instance learning pooling layer for effective differentiation between borderline and malignant epithelial ovarian tumors. Artif Intell Med 121:102194. https://doi.org/10.1016/j.artmed.2021.102194CrossRefPubMed

63.

Ștefan P-A, Lupean R-A, Mihu CM et al (2021) Ultrasonography in the diagnosis of adnexal lesions: the role of texture analysis. Diagnostics 11(5):812CrossRefPubMedPubMedCentral

64.

van der Sommen F, de Groof J, Struyvenberg M et al (2020) Machine learning in GI endoscopy: practical guidance in how to interpret a novel field. Gut 69(11):2035–2045. https://doi.org/10.1136/gutjnl-2019-320466CrossRefPubMed

65.

Chacon E, Dasi J, Caballero C, Alcazar JL (2019) Risk of ovarian malignancy algorithm versus risk malignancy index-I for preoperative assessment of adnexal masses: a systematic review and meta-analysis. Gynecol Obstet Invest 84(6):591–598. https://doi.org/10.1159/000501681CrossRefPubMed

66.

Mulder EE, Gelderblom ME, Schoot D, Vergeldt TF, Nijssen DL, Piek JM (2020) External validation of risk of malignancy index compared to IOTA simple rules. Acta Radiol. 62:673–678. https://doi.org/10.1177/0284185120933990CrossRefPubMed

67.

Sadowski EA, Maturen KE, Rockall A et al (2021) Ovary: MRI characterisation and O-RADS MRI. Br J Radiol 94(1125):20210157. https://doi.org/10.1259/bjr.20210157CrossRefPubMedPubMedCentral

68.

Song H, Bak S, Kim I et al (2021) An application of machine learning that uses the magnetic resonance imaging metric, mean apparent diffusion coefficient, to differentiate between the histological types of ovarian cancer. J Clin Med 11(1):229. https://doi.org/10.3390/jcm11010229CrossRefPubMedPubMedCentral

69.

Forstner R (2020) Early detection of ovarian cancer. Eur Radiol 30(10):5370–5373. https://doi.org/10.1007/s00330-020-06937-zCrossRefPubMedPubMedCentral

Title: Analysis of computer-aided diagnostics in the preoperative diagnosis of ovarian cancer: a systematic review
Authors: Anna H. Koch
Lara S. Jeelof
Caroline L. P. Muntinga
T. A. Gootzen
Nienke M. A. van de Kruis
Joost Nederend
Tim Boers
Fons van der Sommen
Jurgen M. J. Piek
Publication date: 01-12-2023
Publisher: Springer Vienna
Keywords: Magnetic Resonance Imaging
Ultrasound
Magnetic Resonance Imaging
Ultrasound
Published in: Insights into Imaging / Issue 1/2023
Electronic ISSN: 1869-4101
DOI: https://doi.org/10.1186/s13244-022-01345-x

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Analysis of computer-aided diagnostics in the preoperative diagnosis of ovarian cancer: a systematic review

Abstract

Objectives

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2023

Magnetic resonance imaging for treatment response evaluation and prognostication of hepatocellular carcinoma after thermal ablation

QuADRANT: a study on uptake and implementation of clinical audit of medical radiological procedures in Europe—expert recommendations for improvement, endorsed by the ESR

Prognostic utility of body composition parameters based on computed tomography analysis of advanced non-small cell lung cancer treated with immune checkpoint inhibitors

An active learning approach to train a deep learning algorithm for tumor segmentation from brain MR images

Clinical audit in European radiology: current status and recommendations for improvement endorsed by the European Society of Radiology (ESR)

Whole-body low-dose CT can be of value in prostate cancer decision-making: a retrospective study on 601 patients