Top

Published in:

Open Access 01-02-2015 | Magnetic Resonance

Logistic regression model for diagnosis of transition zone prostate cancer on multi-parametric MRI

Authors: Nikolaos Dikaios, Jokha Alkalbani, Harbir Singh Sidhu, Taiki Fujiwara, Mohamed Abd-Alazeez, Alex Kirkham, Clare Allen, Hashim Ahmed, Mark Emberton, Alex Freeman, Steve Halligan, Stuart Taylor, David Atkinson, Shonit Punwani

Published in: European Radiology | Issue 2/2015

Abstract

Objectives

We aimed to develop logistic regression (LR) models for classifying prostate cancer within the transition zone on multi-parametric magnetic resonance imaging (mp-MRI).

Methods

One hundred and fifty-five patients (training cohort, 70 patients; temporal validation cohort, 85 patients) underwent mp-MRI and transperineal-template-prostate-mapping (TPM) biopsy. Positive cores were classified by cancer definitions: (1) any-cancer; (2) definition-1 [≥Gleason 4 + 3 or ≥ 6 mm cancer core length (CCL)] [high risk significant]; and (3) definition-2 (≥Gleason 3 + 4 or ≥ 4 mm CCL) cancer [intermediate–high risk significant]. For each, logistic-regression mp-MRI models were derived from the training cohort and validated internally and with the temporal cohort. Sensitivity/specificity and the area under the receiver operating characteristic (ROC-AUC) curve were calculated. LR model performance was compared to radiologists’ performance.

Results

Twenty-eight of 70 patients from the training cohort, and 25/85 patients from the temporal validation cohort had significant cancer on TPM. The ROC-AUC of the LR model for classification of cancer was 0.73/0.67 at internal/temporal validation. The radiologist A/B ROC-AUC was 0.65/0.74 (temporal cohort). For patients scored by radiologists as Prostate Imaging Reporting and Data System (Pi-RADS) score 3, sensitivity/specificity of radiologist A ‘best guess’ and LR model was 0.14/0.54 and 0.71/0.61, respectively; and radiologist B ‘best guess’ and LR model was 0.40/0.34 and 0.50/0.76, respectively.

Conclusions

LR models can improve classification of Pi-RADS score 3 lesions similar to experienced radiologists.

Key Points

• MRI helps find prostate cancer in the anterior of the gland

• Logistic regression models based on mp-MRI can classify prostate cancer

• Computers can help confirm cancer in areas doctors are uncertain about

Dickinson L, Ahmed HU, Allen C et al (2011) Magnetic resonance imaging for the detection, localisation, and characterisation of prostate cancer: recommendations from a European consensus meeting. Eur Urol 59:477–494PubMedCrossRef

Emberton M (2013) Has magnetic resonance-guided biopsy of the prostate become the standard of care? Eur Urol 64:720–721PubMedCrossRef

Langer DL, van der Kwast TH, Evans AJ, Trachtenberg J, Wilson BC, Haider MA (2009) Prostate cancer detection with multi-parametric MRI: logistic regression analysis of quantitative T2, diffusion-weighted imaging, and dynamic contrast-enhanced MRI. J Magn Reson Imaging 30:327–334PubMedCrossRef

Zakian KL, Eberhardt S, Hricak H et al (2003) Transition zone prostate cancer: metabolic characteristics at 1H MR spectroscopic imaging–initial results. Radiology 229:241–247PubMedCrossRef

Chesnais AL, Niaf E, Bratan F et al (2013) Differentiation of transitional zone prostate cancer from benign hyperplasia nodules: evaluation of discriminant criteria at multiparametric MRI. Clin Radiol 68:e323–e330PubMedCrossRef

Robinson C, Halligan S, Iinuma G et al (2011) CT colonography: computer-assisted detection of colorectal cancer. Br J Radiol 84:435–440PubMedCentralPubMedCrossRef

Sprindzuk MV, Kovalev VA, Snezhko EV, Kharuzhyk SA (2010) Lung cancer differential diagnosis based on the computer assisted radiology: The state of the art. Pol J Radiol 75:67–80PubMedCentralPubMed

Yuan Y, Giger ML, Li H, Bhooshan N, Sennett CA (2010) Multimodality computer-aided breast cancer diagnosis with FFDM and DCE-MRI. Acad Radiol 17:1158–1167PubMedCrossRef

Engelbrecht MR, Huisman HJ, Laheij RJ et al (2003) Discrimination of prostate cancer from normal peripheral zone and central gland tissue by using dynamic contrast-enhanced MR imaging. Radiology 229:248–254PubMedCrossRef

10.

Nogueira L, Wang L, Fine SW et al (2010) Focal treatment or observation of prostate cancer: pretreatment accuracy of transrectal ultrasound biopsy and T2-weighted MRI. Urology 75:472–477PubMedCentralPubMedCrossRef

11.

Sung YS, Kwon HJ, Park BW, Cho G, Lee CK, Cho KS, Kim JK (2011) Prostate cancer detection on dynamic contrast-enhanced MRI: computer-aided diagnosis versus single perfusion parameter maps. Am J Roentgenol 197:1122–1129CrossRef

12.

Niaf E, Rouvière O, Mège-Lechevallier F, Bratan F, Lartizien C (2012) Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI. Phys Med Biol 57:3833–3851PubMedCrossRef

13.

Dikaios NAM, Emberton M, Fujiwara T, Atkinson D, Punwani S (2013) Derivation and comparison of site specific peripheral and transition zone quantitative DCE MRI logistic regression models for prostate cancer detection: does cancer location matter? International Society of Magnetic Resonance in Medicine, Salt Lake City

14.

Puech P, Betrouni N, Makni N, Dewalle AS, Villers A, Lemaitre L (2009) Computer-assisted diagnosis of prostate cancer using DCE-MRI data: design, implementation and preliminary results. Int J Comput Assist Radiol Surg 4:1–10PubMedCrossRef

15.

Hambrock T, Vos PC, Hulsbergen-van de Kaa CA, Barentsz JO, Huisman HJ (2013) Prostate cancer: computer-aided diagnosis with multiparametric 3-T MR imaging–effect on observer performance. Radiology 266:521–530PubMedCrossRef

16.

Onik G, Barzell W (2008) Transperineal 3D mapping biopsy of the prostate: an essential tool in selecting patients for focal prostate cancer therapy. Urol Oncol 26:506–510PubMedCrossRef

17.

Taira AV, Merrick GS, Galbreath RW et al (2010) Performance of transperineal template-guided mapping biopsy in detecting prostate cancer in the initial and repeat biopsy setting. Prostate Cancer Prostatic Dis 13:71–77PubMedCentralPubMedCrossRef

18.

Barzell WE, Melamed MR (2007) Appropriate patient selection in the focal treatment of prostate cancer: the role of transperineal 3-dimensional pathologic mapping of the prostate—a 4-year experience. Urology 70:27–35PubMedCrossRef

19.

Ahmed HU, Hu Y, Carter T et al (2011) Characterizing clinically significant prostate cancer using template prostate mapping biopsy. J Urol 186:458–464PubMedCrossRef

20.

Barentsz JO, Richenberg J, Clements R et al (2012) ESUR prostate MR guidelines 2012. Eur Radiol 22:746–757PubMedCentralPubMedCrossRef

21.

Zelhof B, Lowry M, Rodrigues G, Kraus S, Turnbull L (2009) Description of magnetic resonance imaging-derived enhancement variables in pathologically confirmed prostate cancer and normal peripheral zone regions. BJU Int 104:621–627PubMedCrossRef

22.

Tofts PS (1197) Modeling tracer kinetics in dynamic Gd-DTPA MR imaging. J Magn Reson Imaging 7:91–101CrossRef

23.

SM (1995) Applied logistic regression analysisSage University Paper Series on Quantitative Applications in the Social Sciences. SAGE pp 7-106

24.

Tabachnick BG, Fidell LS (1996) Using Multivariate Statistics. HarperCollins, NY

25.

Fukunaga KHD (1989) Leave-one-out procedures for nonparametric error estimates. IEEE Trans Pattern Anal Mach Intell 11:421–423CrossRef

26.

Choi YJ, Kim JK, Kim N, Kim KW, Choi EK, Cho KS (2007) Functional MR imaging of prostate cancer. Radiographics 27:63–75, discussion 75-67PubMedCrossRef

27.

Shah V, Turkbey B, Mani H et al (2012) Decision support system for localizing prostate cancer based on multiparametric magnetic resonance imaging. Med Phys 39:4093–4103PubMedCentralPubMedCrossRef

28.

Akin O, Sala E, Moskowitz CS et al (2006) Transition zone prostate cancers: features, detection, localization, and staging at endorectal MR imaging. Radiology 239:784–792PubMedCrossRef

29.

Hoeks CM, Hambrock T, Yakar D et al (2013) Transition zone prostate cancer: detection and localization with 3-T multiparametric MR imaging. Radiology 266:207–217PubMedCrossRef

30.

Ahmed HU, Emberton M, Kepner G, Kepner J (2012) A biomedical engineering approach to mitigate the errors of prostate biopsy. Nature Reviews. Urology 9:227–23131PubMed

31.

Hoeks CM, Barentsz JO, Hambrock T et al (2011) Prostate cancer: multiparametric MR imaging for detection, localization, and staging. Radiology 261:46–66PubMedCrossRef

32.

Xu S, Kruecker J, Turkbey B et al (2008) Real-time MRI-TRUS fusion for guidance of targeted prostate biopsies. Comput Aided Surg 13:255–264PubMedCentralPubMedCrossRef

33.

Bonekamp D, Jacobs MA, El-Khouli R, Stoianovici D, Macura KJ (2011) Advancements in MR imaging of the prostate: from diagnosis to interventions. Radiographics 31:677–703PubMedCentralPubMedCrossRef

34.

Kirkham AP, Haslam P, Keanie JY, McCafferty I, Padhani AR, Punwani S, Richenberg J, Rottenberg G, Sohaib A, Thompson P, Turnbull LW, Kurban L, Sahdev A, Clements R, Carey BM, Allen C (2013) Prostate MRI: who, when, and how? Report from a UK consensus meeting. Clin Radiol 68:1016–1023PubMedCrossRef

35.

Kirkham AP, Emberton M, Allen C (2006) How good is MRI at detecting and characterising cancer within the prostate? Eur Urol 50:1163–1174PubMedCrossRef

36.

Bratan F, Niaf E, Melodelima C, Chesnais AL, Souchon R, Mège-Lechevallier F, Colombel M, Rouvière O (2013) Influence of imaging and histological factors on prostate cancer detection and localisation on multiparametric MRI: a prospective study. Eur Radiol 23:2019–2029PubMedCrossRef

37.

Lee SH, Park KK, Choi KH, Lim BJ, Kim JH, Lee SW, Chung BH (2010) Is endorectal coil necessary for the staging of clinically localized prostate cancer? Comparison of non-endorectal versus endorectal MR imaging. World J Urol 28:667–672PubMedCrossRef

38.

Arumainayagam N, Kumaar S, Ahmed HU et al (2010) Accuracy of multiparametric magnetic resonance imaging in detecting recurrent prostate cancer after radiotherapy. BJU Int 106:991–997PubMedCrossRef

39.

Mueller-Lisse U, Scheidler J, Klein G, Reiser M (2005) Reproducibility of image interpretation in MRI of the prostate: application of the sextant framework by two different radiologists. Eur Radiol 15:1826–1833PubMedCrossRef

40.

Villers A, Puech P, Mouton D, Leroy X, Ballereau C, Lemaitre L (2006) Dynamic contrast enhanced, pelvic phased array magnetic resonance imaging of localized prostate cancer for predicting tumor volume: correlation with radical prostatectomy findings. J Urol 176:2432–2437PubMedCrossRef

Title: Logistic regression model for diagnosis of transition zone prostate cancer on multi-parametric MRI
Authors: Nikolaos Dikaios
Jokha Alkalbani
Harbir Singh Sidhu
Taiki Fujiwara
Mohamed Abd-Alazeez
Alex Kirkham
Clare Allen
Hashim Ahmed
Mark Emberton
Alex Freeman
Steve Halligan
Stuart Taylor
David Atkinson
Shonit Punwani
Publication date: 01-02-2015
Publisher: Springer Berlin Heidelberg
Published in: European Radiology / Issue 2/2015
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-014-3386-4

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Logistic regression model for diagnosis of transition zone prostate cancer on multi-parametric MRI

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Please log in to get access to this content

Other articles of this Issue 2/2015

MR volumetric assessment of endolymphatic hydrops

Image-guided microwave thermoablation of hepatic tumours using novel robotic guidance: an early experience

Cross-sectional area measurements versus volumetric assessment of the quadriceps femoris muscle in patients with anterior cruciate ligament reconstructions

Assessment of diabetic peripheral neuropathy in streptozotocin-induced diabetic rats with magnetic resonance imaging

Imaging of bridging vein thrombosis in infants with abusive head trauma: the “Tadpole Sign”.

Clinical indications for computed tomographic colonography: European Society of Gastrointestinal Endoscopy (ESGE) and European Society of Gastrointestinal and Abdominal Radiology (ESGAR) Guideline