Zusammenfassung
Klinisches/methodisches Problem
Angesichts der diagnostischen Komplexität und der großen Untersuchungszahlen ergibt sich die Herausforderung für die moderne Radiologie, klinisch signifikante Prostatakarzinome (PCa) mit hoher Sensitivität und Spezifität zu identifizieren sowie eine Überdiagnostik und Übertherapie von klinisch nicht signifikanten Karzinomen zu vermeiden.
Radiologische Standardverfahren
In den internationalen Leitlinien etabliert sich zunehmend die multiparametrische Magnetresonanztomographie (mpMRT) als Standarduntersuchung in der Diagnostik des PCa.
Methodische Innovationen
Die MRT-Beurteilung nach den PI-RADS-Kriterien durch Radiologen weist eine begrenzte Reproduzierbarkeit auf, sodass die rasanten Entwicklungen der automatisierten Bildanalyse mittels Radiomics oder künstlicher Intelligenz (KI; Machine Learning, Deep Learning) auf eine weitere Verbesserung der Patientenversorgung hoffen lassen.
Leistungsfähigkeit
Die Anwendung von KI konzentriert sich auf die automatisierte Detektion und Klassifikation von PCa-Läsionen und versucht, die Aggressivität anhand des Gleason-Scores zu stratifizieren. Neueste Studien präsentieren gute bis sehr gute Ergebnisse für die Befundung der mpMRT mittels Radiomics oder KI. Eine breite klinische Anwendung bleibt jedoch aktuell noch aus.
Bewertung und Empfehlung für die Praxis
Das wachsende Bewusstsein der Forschungsgesellschaft für eine strukturierte Datenakquise, die Entwicklung robuster AI-Systeme sowie die zunehmende Akzeptanz gegenüber KI-Algorithmen als diagnostisches Hilfsmittel sind Voraussetzungen für die klinische Anwendbarkeit dieser Technologien. Wenn die KI diese Hürden überwindet, kann ihr eine Schlüsselrolle in der quantitativen, reproduzierbaren Befundung der Prostata-MRT bei ständig ansteigenden Untersuchungsvolumina zukommen.
Abstract
Clinical/methodical issue
In view of the diagnostic complexity and the large number of examinations, modern radiology is challenged to identify clinically significant prostate cancer (PCa) with high sensitivity and specificity. Meanwhile overdiagnosis and overtreatment of clinically nonsignificant carcinomas need to be avoided.
Standard radiological methods
Increasingly, international guidelines recommend multiparametric magnetic resonance imaging (mpMRI) as first-line investigation in patients with suspected PCa.
Methodical innovations
Image interpretation according to the PI-RADS criteria is limited by interobserver variability. Thus, rapid developments in the field of automated image analysis tools, including radiomics and artificial intelligence (AI; machine learning, deep learning), give hope for further improvement in patient care.
Performance
AI focuses on the automated detection and classification of PCa, but it also attempts to stratify tumor aggressiveness according to the Gleason score. Recent studies present good to very good results in radiomics or AI-supported mpMRI diagnosis. Nevertheless, these systems are not widely used in clinical practice.
Achievements and practical recommendations
In order to apply these innovative technologies, a growing awareness for the need of structured data acquisition, development of robust systems and an increased acceptance of AI as diagnostic support are needed. If AI overcomes these obstacles, it may play a key role in the quantitative and reproducible image-based diagnosis of ever-increasing prostate MRI examination volumes.
Literatur
Grönberg H (2003) Prostate cancer epidemiology. Lancet 361:859–864
Wolters T et al (2011) A critical analysis of the tumor volume threshold for clinically insignificant prostate cancer using a data set of a randomized screening trial. J Urol 185:121–125
Bi WL et al (2019) Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin 69:127–157
Costa DN, Pedrosa I, Donato F Jr, Roehrborn CG, Rofsky NM (2015) MR imaging-transrectal US fusion for targeted prostate biopsies: implications for diagnosis and clinical management. Radiographics 35:696–708
Cuocolo R et al (2019) Machine learning applications in prostate cancer magnetic resonance imaging. Eur Radiol Exp 3:35
Liu L, Tian Z, Zhang Z, Fei B (2016) Computer-aided detection of prostate cancer with MRI: technology and applications. Acad Radiol 23:1024–1046
Loeb S et al (2014) Overdiagnosis and overtreatment of prostate cancer. Eur Urol 65:1046–1055
Turkbey B et al (2019) Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2. Eur Urol 76:340–351
Rosenkrantz AB et al (2016) Interobserver reproducibility of the PI-RADS version 2 lexicon: a multicenter study of six experienced prostate radiologists. Radiology 280:793–804
Venderink W et al (2018) Results of targeted biopsy in men with magnetic resonance imaging lesions classified equivocal, likely or highly likely to be clinically significant prostate cancer. Eur Urol 73:353–360
Patel N, Henry A, Scarsbrook A (2018) The value of MR textural analysis in prostate cancer. Clin Radiol 74:876–885
Schwier M et al (2019) Repeatability of multiparametric prostate MRI radiomics features. Sci Rep 9:9441
Toivonen J et al (2019) Radiomics and machine learning of multisequence multiparametric prostate MRI: Towards improved non-invasive prostate cancer characterization. PLoS ONE 14:e217702
Algohary A et al (2018) Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: preliminary findings. J Magn Reson Imaging 48:818–828
Vignati A et al (2015) Texture features on T2-weighted magnetic resonance imaging: new potential biomarkers for prostate cancer aggressiveness. Phys Med Biol 60:2685
Ginsburg SB et al (2017) Radiomic features for prostate cancer detection on MRI differ between the transition and peripheral zones: preliminary findings from a multi-institutional study. J Magn Reson Imaging 46:184–193
Wang J et al (2017) Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer. Eur Radiol 27:4082–4090
Varghese B et al (2019) Objective risk stratification of prostate cancer using machine learning and radiomics applied to multiparametric magnetic resonance images. Sci Rep 9:1570
Bonekamp D et al (2018) Radiomic machine learning for characterization of prostate lesions with MRI: comparison to ADC values. Radiology 289:128–137
Litjens G, Debats O, Barentsz J, Karssemeijer N, Huisman H (2014) Computer-aided detection of prostate cancer in MRI. IEEE Trans Med Imaging 33:1083–1092
Kwak JT et al (2015) Automated prostate cancer detection using T2-weighted and high-b-value diffusion-weighted magnetic resonance imaging. Med Phys 42:2368–2378
Peng Y et al (2013) 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. Radiology 267:787–796
Greer MD et al (2018) Computer-aided diagnosis prior to conventional interpretation of prostate mpMRI: an international multi-reader study. Eur Radiol 28:4407–4417
Hamm CA et al (2019) Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI. Eur Radiol 29:3338–3347
Esteva A et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115–118. https://doi.org/10.1038/nature21056
Ishioka J et al (2018) Computer-aided diagnosis of prostate cancer on magnetic resonance imaging using a convolutional neural network algorithm. BJU Int 122:411–417
Wang X et al (2017) Searching for prostate cancer by fully automated magnetic resonance imaging classification: deep learning versus non-deep learning. Sci Rep 7:15415
Schelb P et al (2019) Classification of cancer at prostate MRI: deep learning versus clinical PI-RADS assessment. Radiology. https://doi.org/10.1148/radiol.2019190938
Stamey TA, McNeal JE, Yemoto CM, Sigal BM, Johnstone IM (1999) Biological determinants of cancer progression in men with prostate cancer. JAMA 281:1395–1400
Aldoj N, Lukas S, Dewey M, Penzkofer T (2019) Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network. Eur Radiol. https://doi.org/10.1007/s00330-019-06417-z
Antonelli M et al (2019) Machine learning classifiers can predict Gleason pattern 4 prostate cancer with greater accuracy than experienced radiologists. Eur Radiol 29:4754–4764. https://doi.org/10.1007/s00330-019-06244-2
Min X et al (2019) Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: Cross-validation of a machine learning method. Eur J Radiol 115:16–21
Karimi D et al (2019) Accurate and robust deep learning-based segmentation of the prostate clinical target volume in ultrasound images. Med Image Anal 57:186–196. https://doi.org/10.1016/j.media.2019.07.005
Nguyen D et al (2019) A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning. Sci Rep 9:1076
Wang B et al (2019) Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation. Med Phys 46:1707–1718
Lee SL et al (2019) Changes in ADC and T2-weighted MRI-derived radiomic features in patients treated with focal salvage HDR prostate brachytherapy for local recurrence after previous external-beam radiotherapy. Brachytherapy 18(5):567. https://doi.org/10.1016/j.brachy.2019.04.006
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Interessenkonflikt
C.A. Hamm und N.L. Beetz geben an, dass kein Interessenkonflikt besteht. L.J. Savic erhielt Research Grants der Leopoldina, der Rolf W. Günther Stiftung für radiologische Wissenschaften, des Berlin Institute of Health (Clinician Scientist Program) und der Society of Interventional Oncology. T. Penzkofer erhielt Research Grants des Berlin Institute of Health (Clinician Scientist Program) und nimmt an Forschungsvorhaben mit den folgenden Firmen (ohne persönliche Zuwendungen) teil: AGO, Aprea AB, ARCAGY-GINECO, Astellas Pharma Global Inc (APGD), Astra Zeneca, Clovis Oncology, Inc., Dohme Corp, Holaira, Incyte Corporation, Karyopharm, Lion Biotechnologies, Inc., MedImmune, Merck Sharp, Millennium Pharmaceuticals, Inc., Morphotec Inc., NovoCure Ltd., PharmaMar S.A. and PharmaMar USA, Inc, Roche, Siemens Healthineers und TESARO Inc.
Für diesen Beitrag wurden von den Autoren keine Studien an Menschen oder Tieren durchgeführt. Für die aufgeführten Studien gelten die jeweils dort angegebenen ethischen Richtlinien.
Rights and permissions
About this article
Cite this article
Hamm, C.A., Beetz, N.L., Savic, L.J. et al. Künstliche Intelligenz und Radiomics in der MRT-basierten Prostatadiagnostik. Radiologe 60, 48–55 (2020). https://doi.org/10.1007/s00117-019-00613-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00117-019-00613-0
Schlüsselwörter
- Prostatakarzinom
- Quantitative Bildgebung
- Machine Learning
- Deep Learning
- Multiparametrische Magnetresonanztomographie