Skip to main content
SpringerLink
Log in

Funktionelle Bildgebung: Translation von Radiomics und künstlicher Intelligenz in die klinische Praxis

Functional imaging: translation of radiomics and artificial intelligence into clinical practice

  • Leitthema
  • Published:
Die Onkologie Aims and scope

Zusammenfassung

Hintergrund

Radiomics und künstliche Intelligenz (KI) sind eines der wichtigsten Themen der radiologischen Forschung der letzten Jahre. Die Translation von der Forschung in die Praxis ist bisher aber nur sporadisch erfolgt.

Ziel der Arbeit

Der bisherige und zukünftig zu erwartende klinische Nutzen von Radiomics und KI in der Onkologie wird im vorliegenden Beitrag kritisch betrachtet.

Material und Methoden

Es handelt sich um eine Literaturrecherche.

Ergebnisse

KI-Systeme sind für die radiologisch-onkologische Praxis bereits erhältlich und werden zunehmend bei der Befundung eingesetzt. Systeme, die den Zuweiser:innen Informationen für Prognosen, Therapieansprechen oder Progress liefern, sind allerdings noch nicht zugelassen und werden auch auf absehbare Zeit nicht verfügbar werden.

Schlussfolgerung

Zur Verbesserung der radiologischen Befundqualität zeigen Radiomics und KI bereits praktischen Wert. Um auch zuverlässige Systeme zu entwickeln, die quantitative – für die Behandlung der Patienten nutzbare – Aussagen machen können, mangelt es noch an größeren Validierungsstudien und finanziellen Anreizen für Hersteller.

Abstract

Background

Radiomics and artificial intelligence (AI) are among the most important topics in radiologic research of recent years. However, translation from research to practice has so far only occurred sporadically.

Objective

The current and future clinical benefits of radiomics and AI in oncology are critically examined in the present article.

Materials and methods

A literature search was performed.

Results

AI systems are already available for radiologic oncology practice and are increasingly used in diagnostics. However, systems that provide referrers with information for prognosis, treatment response, or progression are not yet approved and will not become available in the foreseeable future.

Conclusion

Radiomics and AI already show practical value for improving radiologic diagnostic quality. However, to develop reliable systems that can provide quantitative statements useful for patient treatment, there is still a lack of larger validation studies and financial incentives for manufacturers.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Abb. 1
Abb. 2

Literatur

  1. Amann J, Blasimme A, Vayena E et al (2020) Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inform Decis Mak 20:310. https://doi.org/10.1186/s12911-020-01332-6

    Article  PubMed  PubMed Central  Google Scholar 

  2. Becker CD, Kotter E, Fournier L et al (2022) Current practical experience with artificial intelligence in clinical radiology: a survey of the European society of radiology. Insights Imaging 13:107. https://doi.org/10.1186/s13244-022-01247-y

    Article  Google Scholar 

  3. Bera K, Braman N, Gupta A et al (2022) Predicting cancer outcomes with radiomics and artificial intelligence in radiology. Nat Rev Clin Oncol 19:132–146. https://doi.org/10.1038/s41571-021-00560-7

    Article  CAS  PubMed  Google Scholar 

  4. Bogowicz M, Riesterer O, Stark LS et al (2017) Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma. Acta Oncol 56:1531–1536. https://doi.org/10.1080/0284186X.2017.1346382

    Article  CAS  PubMed  Google Scholar 

  5. Bonekamp D, Kohl S, Wiesenfarth M et al (2018) Radiomic machine learning for characterization of prostate lesions with MRI: comparison to ADC values. Radiology 289:128–137. https://doi.org/10.1148/radiol.2018173064

    Article  PubMed  Google Scholar 

  6. Buvat I, Orlhac F (2019) The dark side of radiomics: on the paramount importance of publishing negative results. J Nucl Med 60:1543–1544. https://doi.org/10.2967/jnumed.119.235325

    Article  PubMed  Google Scholar 

  7. Carvalho S, Leijenaar RTH, Troost EGC et al (2018) 18F-fluorodeoxyglucose positron-emission tomography (FDG-PET)-Radiomics of metastatic lymph nodes and primary tumor in non-small cell lung cancer (NSCLC)—a prospective externally validated study. PLoS One 13:e192859. https://doi.org/10.1371/journal.pone.0192859

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Centre hospitalier de l’Université de Montréal (CHUM) (2022) PSMA-PET: deep radiomic biomarkers of progression and response prediction in prostate cancer (clinicaltrials.gov)

    Google Scholar 

  9. Chang G‑C (2022) Validation and optimization of multidimensional modelling for never smoking lung cancer risk prediction by multicenter prospective study (clinicaltrials.gov)

    Google Scholar 

  10. Eriksson M, Destounis S, Czene K et al (2022) A risk model for digital breast tomosynthesis to predict breast cancer and guide clinical care. Sci Transl Med 14:eabn3971. https://doi.org/10.1126/scitranslmed.abn3971

    Article  PubMed  Google Scholar 

  11. Fournier L, Costaridou L, Bidaut L et al (2021) Incorporating radiomics into clinical trials: expert consensus endorsed by the European society of radiology on considerations for data-driven compared to biologically driven quantitative biomarkers. Eur Radiol 31:6001–6012. https://doi.org/10.1007/s00330-020-07598-8

    Article  PubMed  PubMed Central  Google Scholar 

  12. Funingana I‑G, Piyatissa P, Reinius M et al (2022) Radiomic and volumetric measurements as clinical trial endpoints—a comprehensive review. Cancers 14:5076. https://doi.org/10.3390/cancers14205076

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Kessler LG, Barnhart HX, Buckler AJ et al (2015) The emerging science of quantitative imaging biomarkers terminology and definitions for scientific studies and regulatory submissions. Stat Methods Med Res 24:9–26. https://doi.org/10.1177/0962280214537333

    Article  PubMed  Google Scholar 

  14. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. https://doi.org/10.1145/3065386

    Article  Google Scholar 

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

    Article  PubMed  Google Scholar 

  16. Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446

    Article  PubMed  PubMed Central  Google Scholar 

  17. Langlotz CP (2019) Will artificial intelligence replace radiologists? Radiol Artif Intell 1:e190058. https://doi.org/10.1148/ryai.2019190058

    Article  PubMed  PubMed Central  Google Scholar 

  18. van Leeuwen KG, Schalekamp S, Rutten MJCM et al (2021) Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. Eur Radiol 31:3797–3804. https://doi.org/10.1007/s00330-021-07892-z

    Article  PubMed  PubMed Central  Google Scholar 

  19. Liu Y, Zhang Y, Cheng R et al (2019) Radiomics analysis of apparent diffusion coefficient in cervical cancer: a preliminary study on histological grade evaluation. J Magn Reson Imaging 49:280–290. https://doi.org/10.1002/jmri.26192

    Article  PubMed  Google Scholar 

  20. Lohmann P, Franceschi E, Vollmuth P et al (2022) Radiomics in neuro-oncological clinical trials. Lancet Digit Health 4:e841–e849. https://doi.org/10.1016/S2589-7500(22)00144-3

    Article  CAS  PubMed  Google Scholar 

  21. Maier-Hein L, Eisenmann M, Reinke A et al (2018) Why rankings of biomedical image analysis competitions should be interpreted with care. Nat Commun 9:5217. https://doi.org/10.1038/s41467-018-07619-7

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Netzer N, Weißer C, Schelb P et al (2021) Fully automatic deep learning in Bi-institutional prostate magnetic resonance imaging: effects of cohort size and heterogeneity. Invest Radiol 56:799–808. https://doi.org/10.1097/RLI.0000000000000791

    Article  CAS  PubMed  Google Scholar 

  23. Ospedale Policlinico San Martino (2022) Development of a horizontal data integration classifier for noninvasive early diagnosis of breast cancer (clinicaltrials.gov)

    Google Scholar 

  24. Park JE, Kim D, Kim HS et al (2020) Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement. Eur Radiol 30:523–536. https://doi.org/10.1007/s00330-019-06360-z

    Article  PubMed  Google Scholar 

  25. Publications Office of the European Union (2017on) Regulation (EU) 2017/745 of the European parliament and of the council of 5 April 2017 on medical devices. http://data.europa.eu/eli/reg/2017/745/oj. Zugegriffen: 10. März 2023 (amending Directive 2001/83/EC, Regulation (EC) No 178/2002 and Regulation (EC) No 1223/2009 and repealing Council Directives 90/385/EEC and 93/42/EEC (Text with EEA relevance. ))

  26. Saase V, Wenz H, Ganslandt T et al (2020) Simple statistical methods for unsupervised brain anomaly detection on MRI are competitive to deep learning methods https://doi.org/10.48550/arXiv.2011.12735

    Book  Google Scholar 

  27. Sollini M, Antunovic L, Chiti A, Kirienko M (2019) Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics. Eur J Nucl Med Mol Imaging 46:2656–2672. https://doi.org/10.1007/s00259-019-04372-x

    Article  PubMed  PubMed Central  Google Scholar 

  28. Vicini S, Bortolotto C, Rengo M et al (2022) A narrative review on current imaging applications of artificial intelligence and radiomics in oncology: focus on the three most common cancers. Radiol Med 127:819–836. https://doi.org/10.1007/s11547-022-01512-6

    Article  PubMed  Google Scholar 

  29. Wennmann M, Bauer F, Klein A et al (2022) In vivo repeatability and multiscanner reproducibility of MRI radiomics features in patients with monoclonal plasma cell disorders: a prospective Bi-institutional study. Invest Radiol. https://doi.org/10.1097/RLI.0000000000000927

    Article  PubMed  Google Scholar 

  30. Zhang X, Zhang Y, Zhang G et al (2022) Prospective clinical research of radiomics and deep learning in oncology: a translational review. Crit Rev Oncol Hematol 179:103823. https://doi.org/10.1016/j.critrevonc.2022.103823

    Article  PubMed  Google Scholar 

  31. Zwanenburg A, Vallières M, Abdalah MA et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338. https://doi.org/10.1148/radiol.2020191145

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Abteilung Radiologie, DKFZ Heidelberg, Heidelberg, Deutschland

    Victor Saase & David Bonekamp

  2. Heidelberg, Deutschland

    Victor Saase

Authors
  1. Victor Saase
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David Bonekamp
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Victor Saase.

Ethics declarations

Interessenkonflikt

V. Saase und D. Bonekamp geben an, dass kein Interessenkonflikt besteht.

Für diesen Beitrag wurden von den Autor/-innen keine Studien an Menschen oder Tieren durchgeführt. Für die aufgeführten Studien gelten die jeweils dort angegebenen ethischen Richtlinien.

Additional information

figure qr

QR-Code scannen & Beitrag online lesen

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Saase, V., Bonekamp, D. Funktionelle Bildgebung: Translation von Radiomics und künstlicher Intelligenz in die klinische Praxis. Onkologie 29, 1052–1059 (2023). https://doi.org/10.1007/s00761-023-01391-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00761-023-01391-0

Schlüsselwörter

Keywords

Search

Navigation