Grading of prostate cancer is usually done using Transrectal Ultrasound (TRUS) biopsy followed by microscopic examination of histological images by the pathologist. TRUS is a painful procedure which leads to infections of severe nature. In the recent past, Magnetic Resonance Imaging (MRI) has emerged as a modality which can be used for the diagnosis of prostate cancer without subjecting patients to biopsies. A novel method for grading of prostate cancer based on MRI utilizing Convolutional Neural Networks (CNN) and LADTree classifier is explored in this paper. T2 weighted (T2W), high B-value Diffusion Weighted (BVALDW) and Apparent Diffusion Coefficient (ADC) MRI images obtained from the training dataset of PROSTATEx-2 2017 challenge are used for this study. A quadratic weighted Cohen’s kappa score of 0.3772 is attained in predicting different grade groups of cancer and a positive predictive value of 81.58% in predicting high-grade cancer. The method also attained an unweighted kappa score of 0.3993, and weighted Area Under Receiver Operating Characteristic Curve (AUC), accuracy and F-score of 0.74, 58.04 and 0.56, respectively. The above-mentioned results are better than that obtained by the winning method of PROSTATEx-2 2017 challenge.
SiegelR.L., MillerK.D., JemalA., Cancer statistics, 2018, CA: A Cancer Journal for Clinicians68(1) (2018), 7–30.
2.
SmithR.A., AndrewsK., BrooksD., DeSantisC.E., FedewaS.A., Lortet-TieulentJ., Manassaram-BaptisteD., BrawleyO.W., WenderR.C., Cancer screening in the United States, 2016: A review of current American Cancer Society guidelines and current issues in cancer screening, CA: A Cancer Journal for Clinicians66(2) (2016), 95–114.
3.
NguyenT.H., SridharanS., MaciasV., Kajdacsy-BallaA., MelamedJ., DoM.N., PopescuG., Automatic Gleason grading of prostate cancer using quantitative phase imaging and machine learning, Journal of Biomedical Optics22(3) (2017), 036015–103601512.
4.
RajinikanthA., ManoharanM., SolowayC.T., CivantosF.J., SolowayM.S., Trends in Gleason score: Concordance between biopsy and prostatectomy over 15 years, Urology72(1) (2008), 177–182.
5.
LoebS., VellekoopA., AhmedH.U., CattoJ., EmbertonM., NamR., RosarioD.J., ScattoniV., LotanY., Systematic review of complications of prostate biopsy, European Urology64(6) (2013), 876–892.
6.
AlbitarM., MaW., LundL., ShahbabaB., UchioE., FeddersenS., MoylanD., WojnoK., ShoreN., Prostatectomybased validation of combined urine and plasma test for predicting high grade prostate cancer, The Prostate78(4) (2018), 294–299.
7.
OtoA., YangC., KayhanA., TretiakovaM., AnticT., Schmid-TannwaldC., EggenerS., KarczmarG.S., StadlerW.M., Diffusion-weighted and dynamic contrastenhanced MRI of prostate cancer: Correlation of quantitative MR parameters with Gleason score and tumor angiogenesis, American Journal of Roentgenology197(6) (2011), 1382–1390.
8.
DownesM.R., GibsonE., SykesJ., HaiderM., van der KwastT.H. and WardA., Determination of the association between T2-weighted MRI and Gleason sub-pattern: A proof of principle study, Academic Radiology23(11) (2016), 1412–1421.
9.
PengY., JiangY., YangC., BrownJ.B., AnticT., SethiI., Schmid-TannwaldC., GigerM.L., EggenerS.E., OtoA., Quantitative analysis of multiparametric prostate MR images: Differentiation between prostate cancer and normal tissue and correlation with Gleason score-a computer-aided diagnosis development study, Radiology267(3) (2013), 787–796.
10.
TamadaT., PrabhuV., LiJ., BabbJ.S., TanejaS.S., RosenkrantzA.B., Prostate cancer: Diffusion-weighted MR imaging for detection and assessment of aggressiveness-comparison between conventional and kurtosis models, Radiology284(1) (2017), 100–108.
11.
EpsteinJ.I., Prostate cancer grading: A decade after the modified system, Modern Pathology31(S1) (2018), 47.
12.
EpsteinJ.I., EgevadL., AminM.B., DelahuntB., SrigleyJ.R., HumphreyP.A., CommitteeG., et al., The International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma: Definition of grading patterns and proposal for a new grading system, The American Journal of Surgical Pathology40(2) (2016), 244–252.
13.
IrshadS., BansalM., Castillo-MartinM., ZhengT., AytesA., WenskeS., Le MagnenC., GuarnieriP., SumazinP., BensonM.C., et al., A molecular signature predictive of indolent prostate cancer, Science Translational Medicine5(202) (2013), 202–122120212212.
14.
LeM.H., ChenJ., WangL., WangZ., LiuW., ChengK.-T.T., YangX., Automated diagnosis of prostate cancer in multiparametric MRI based on multimodal convolutional neural networks, Physics in Medicine & Biology62(16) (2017), 6497.
15.
FehrD., VeeraraghavanH., WibmerA., GondoT., MatsumotoK., VargasH.A., SalaE., HricakH., DeasyJ.O., Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images, Proceedings of the National Academy of Sciences112(46) (2015), 6265–6273.
16.
WangZ., LiuC., ChengD., WangaL., YangX., ChengbK.-T.T., Automated detection of clinically significant prostate cancer in mp-MRI images based on an end-to-end deep neural network, IEEE Transactions on Medical Imaging37(5) (2018), 1127–1139.
17.
NketiahG., ElschotM., KimE., TeruelJ.R., ScheenenT.W., BathenT.F., SelnæsK.M., T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: Preliminary results, European Radiology27(7) (2017), 3050–3059.
18.
NezzoM., Di TraniM., CaporaleA., MianoR., MaurielloA., BoveP., CapuaniS. and ManentiG., Mean diffusivity discriminates between prostate cancer with grade group 1&2 and grade groups equal to or greater than 3, European Journal of Radiology85(10) (2016), 1794–1801.
19.
AbrahamB., NairM.S., Computer-aided diagnosis of clinically significant prostate cancer from MRI images using sparse autoencoder and random forest classifier, Biocybernetics and Biomedical Engineering38(3) (2018), 733–744.
20.
AbrahamB., NairM.S., Computer-aided classification of prostate cancer grade groups from MRI images using texture features and stacked sparse autoencoder, Computerized Medical Imaging and Graphics69 (2018), 60–68.
21.
LitjensG., DebatsO., BarentszJ., KarssemeijerN., HuismanH., Computer-aided detection of prostate cancer in MRI, IEEE Transactions on Medical Imaging33(5) (2014), 1083–1092.
22.
ClarkK., VendtB., SmithK., FreymannJ., KirbyJ., KoppelP., MooreS., PhillipsS., MaffittD., PringleM., et al., The Cancer Imaging Archive (TCIA): Maintaining and operating a public information repository, Journal of Digital Imaging26(6) (2013), 1045–1057.
PuechP., Sufana-IancuA., RenardB., LemaitreL., Prostate MRI: Can we do without DCE sequences in 2013?Diagnostic and Interventional Imaging94(12) (2013), 1299–1311.
25.
V. M, Radiomics/TextureToolbox, Radiomics/TextureToolbox, Github, 2015, accessed on 08.05.2018.
26.
LeCunY., BengioY., HintonG., Deep learning, Nature521(7553) (2015), 436–444.
27.
LeCunY., BoserB.E., DenkerJ.S., HendersonD., HowardR.E., HubbardW.E., JackelL.D., Handwritten digit recognition with a back-propagation network, in: Advances in Neural Information Processing Systems, 1990, pp. 396–404.
28.
KrizhevskyA., SutskeverI., HintonG.E., Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.
29.
AzimiS.M., BritzD., EngstlerM., FritzM., MücklichF., Advanced steel microstructural classification by deep learning methods, Scientific Reports8(1) (2018), 2128.
30.
DundarM., KouQ., ZhangB., HeY., RajwaB., Simplicity of kmeans versus deepness of deep learning: A case of unsupervised feature learning with limited data, in: Machine Learning and Applications (ICMLA), 2015 IEEE 14th International Conference on, IEEE, 2015, pp. 883–888.
31.
ChristodoulidisS., AnthimopoulosM., EbnerL., ChristeA., MougiakakouS., Multisource transfer learning with convolutional neural networks for lung pattern analysis, IEEE Journal of Biomedical and Health Informatics21(1) (2017), 76–84.
32.
YosinskiJ., CluneJ., BengioY., LipsonH., How transferable are features in deep neural networks? in: Advances in Neural Information Processing Systems, 2014, pp. 3320–3328.
33.
DonahueJ., JiaY., VinyalsO., HoffmanJ., ZhangN., TzengE., DarrellT., Decaf: A deep convolutional activation feature for generic visual recognition, in: International Conference on Machine Learning, 2014, pp. 647–655.
34.
AbidinA.Z., DengB., DSouzaA.M., NagarajanM.B., CoanP., WismüllerA., Deep transfer learning for characterizing chondrocyte patterns in phase contrast X-Ray computed tomography images of the human patellar cartilage, Computers in Biology and Medicine95 (2018), 24–33.
35.
NguyenK., FookesC., RossA., SridharanS., Iris recognition with off-the-shelf CNN features: A deep learning perspective, IEEE Access6 (2017), 18848–18855.
36.
van GinnekenB., SetioA.A., JacobsC. and CiompiF., Offthe-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans, in: Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium on, IEEE, 2015, pp. 286–289.
37.
SzegedyC., VanhouckeV., IoffeS., ShlensJ., WojnaZ., Rethinking the inception architecture for computer vision, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2818–2826.
38.
WengS.W, XuX., LiJ. and WongS.T., Combining deep learning and coherent anti-Stokes Raman scattering imaging for automated differential diagnosis of lung cancer, Journal of Biomedical Optics22(10) (2017), 106017.
39.
ChangJ., YuJ., HanT., ChangH.-J., ParkE., A method for classifying medical images using transfer learning: A pilot study on histopathology of breast cancer, in: e-Health Networking, Applications and Services (Healthcom), 2017 IEEE 19th International Conference on, IEEE, 2017, pp. 1–4.
40.
HolmesG., PfahringerB., KirkbyR., FrankE., HallM., Multiclass alternating decision trees, in: European Conference on Machine Learning, Springer, 2002, pp. 161–172.
41.
KalatskayaI., TrinhQ.M., SpearsM., McPhersonJ.D., BartlettJ.M., SteinL., ISOWN: Accurate somatic mutation identification in the absence of normal tissue controls, Genome Medicine9(1) (2017), 59–15918.
42.
RobsonJ., WatanabeC., Automated feature extraction from breast masses using multiscale fractal dimension, in: Computer Vision (WVC), 2017 Workshop, IEEE, 2017, pp. 25–30.
43.
FolorunshoO., Comparative study of different data mining techniques performance in knowledge discovery from medical database, International Journal of Advanced Research in Computer Science and Software Engineering3(3) (2013), 11–15.
44.
BouillotF., PonceletP., RocheM., Classification of small datasets: Why using class-based weighting measures? in: International Symposium on Methodologies for Intelligent Systems, Springer, 2014, pp. 345–354.
45.
FriedmanJ., HastieT., TibshiraniR., et al., Additive logistic regression: A statistical view of boosting (with discussion and a rejoinder by the authors), The annals of statistics28(2) (2000), 337–407.
46.
Ben-DavidA., Comparison of classification accuracy using Cohen’s Weighted Kappa, Expert Systems with Applications34(2) (2008), 825–832.
47.
FatourechiM., WardR.K., MasonS.G., HugginsJ., SchlöglA., BirchG.E., Comparison of evaluation metrics in classification applications with imbalanced datasets, in: Machine Learning and Applications, 2008 ICMLA’08 Seventh International Conference on, IEEE, 2008, pp. 777–782.
48.
WatsonP., PetrieA., Method agreement analysis: A review of correct methodology, Theriogenology73(9) (2010), 1167–1179.
49.
LandisJ.R., KochG.G., The measurement of observer agreement for categorical data, Biometrics33(1) (1977), 159–174.
