Download PDF
Der Nuklearmediziner 2019; 42(02): 144-147
DOI: 10.1055/a-0916-6143
Big data
© Georg Thieme Verlag KG Stuttgart · New York

Künstliche Intelligenz zur Detektion, Quantifizierung und Charakterisierung des metastasierten Prostatakarzinoms in der PSMA-PET/CT – Wo stehen wir?

Artificial intelligence for the detection, quantification and characterization of metastatic prostate cancer in PSMA PET/CT- where are we now?
Ali Afshar-Oromieh
Klinik für Nuklearmedizin, Universitätsklinik Bern, Inselspital, University of Bern, Bern, Schweiz
,
Axel Rominger
Klinik für Nuklearmedizin, Universitätsklinik Bern, Inselspital, University of Bern, Bern, Schweiz
,
Kuangyu Shi
Klinik für Nuklearmedizin, Universitätsklinik Bern, Inselspital, University of Bern, Bern, Schweiz
› Author Affiliations
Further Information

Publication History

Publication Date:
22 July 2019 (online)

Also available at
    Permissions and Reprints

Zusammenfassung

Das Prostatakarzinom (PCa) ist der weltweit häufigste maligne Tumor bei Männern. Seit ihrer klinischen Einführung in 2011 hat sich sowohl die PET/CT als auch die Radioligandentherapie mit PSMA-Liganden zur Diagnostik bzw. Therapie des PCa weltweit rasch ausgebreitet. Obwohl die PSMA-PET/CT als ein signifikanter Durchbruch in der Diagnostik des PCa gilt, stellt die Evaluation und Kontrolle aller Tumorherde inklusive ihrer Volumina und Charakteristika bei fortgeschrittener, multimetastatischer PCa nach wie vor eine große Herausforderung dar. Diese gilt es zu bewältigen, um beispielsweise eine Optimierung der Endoradiotherapie mit PSMA-Liganden zu erreichen. In diesem Kontext könnte die künstliche Intelligenz, die in den letzten Jahren signifikante Fortschritte erzielt hat, in der nahen Zukunft eine wichtige Rolle spielen. Die Artificial Intelligence (AI) hat bereits demonstriert, dass sie den menschlichen Fähigkeiten zur Datenverarbeitung überlegen sein kann und bietet damit großes Potential zur Verbesserung der Detektion, Quantifizierung und Charakterisierung von PCa-Herden in der PSMA-PET/CT. Die hier vorliegende Schrift befasst sich mit den aktuellen Entwicklungen der künstlichen Intelligenz für den Einsatz in der PSMA-PET/CT und den sich daraus bietenden Möglichkeiten.

Abstract

Prostate cancer (PCa) is the most frequent tumor entity in men worldwide. Since their clinical introduction in 2011, PSMA-PET/CT and radionuclide therapy with PSMA-ligands have rapidly spread worldwide and are regarded as significant step forwards in the diagnosis and therapy of PCa. However, it is still an unmet challenge to evaluate and control all tumor lesions including their volume and characteristics in the complex context of advanced multimetastatic disease in PSMA-PET/CT. Such a control plays an important role, e.g. for the optimization of PSMA-ligandtherapy. In this context, artificial intelligence (AI) could play an important role in the near future. The rapid development of AI in the past few years has demonstrated its superiority in extending the human power of data processing and provides great potential to improve the detection, quantification and characterization of metastatic prostate cancer lesions in PSMA-PET/CT. This paper reviews the current progress of the development of artificial intelligence methods for PSMA-PET/CT and discusses the potential of clinical application.

Schlüsselwörter

PSMA - PET/CT - Prostatakarzinom - PSMA-Therapie - künstliche Intelligenz - Artificial Intelligence - Deep Learning

Keywords

PSMA - PET/CT - Prostate Cancer - PSMA-therapy - Artificial Intelligence - Deep Learning
 

  • Literatur

  • 1 Freedland SJ. et al. Time trends in biochemical recurrence after radical prostatectomy: results of the SEARCH database. Urology 2003; 61: 736-741
    CrossrefPubMedGoogle Scholar
  • 2 Khuntia D. et al. Recurrence-free survival rates after external-beam radiotherapy for patients with clinical T1-T3 prostate carcinoma in the prostate-specific antigen era: what should we expect?. Cancer 2004; 100: 1283-1292
    CrossrefPubMedGoogle Scholar
  • 3 Afshar-Oromieh A. et al. [68Ga]Gallium-labelled PSMA ligand as superior PET tracer for the diagnosis of prostate cancer: comparison with 18F-FECH. Eur J Nucl Med Mol Imaging 2012; 39: 1085-1086
    CrossrefPubMedGoogle Scholar
  • 4 Afshar-Oromieh A. et al. PET imaging with a [68Ga]gallium-labelled PSMA ligand for the diagnosis of prostate cancer: biodistribution in humans and first evaluation of tumour lesions. Eur J Nucl Med Mol Imaging 2013; 40: 486-495
    CrossrefPubMedGoogle Scholar
  • 5 Afshar-Oromieh A. et al. The diagnostic value of PET/CT imaging with the (68)Ga-labelled PSMA ligand HBED-CC in the diagnosis of recurrent prostate cancer. Eur J Nucl Med Mol Imaging 2015; 42: 197-209
    CrossrefPubMedGoogle Scholar
  • 6 Afshar-Oromieh A. et al. Diagnostic performance of (68)Ga-PSMA-11 (HBED-CC) PET/CT in patients with recurrent prostate cancer: evaluation in 1007 patients. Eur J Nucl Med Mol Imaging 2017; 44: 1258-1268
    CrossrefPubMedGoogle Scholar
  • 7 Eiber M. et al. Evaluation of Hybrid (6)(8)Ga-PSMA Ligand PET/CT in 248 Patients with Biochemical Recurrence After Radical Prostatectomy. J Nucl Med 2015; 56: 668-674
    CrossrefPubMedGoogle Scholar
  • 8 Caroli P. et al. (68)Ga-PSMA PET/CT in patients with recurrent prostate cancer after radical treatment: prospective results in 314 patients. Eur J Nucl Med Mol Imaging 2018; 45: 2035-2044
    CrossrefPubMedGoogle Scholar
  • 9 Fendler WP. et al. Assessment of 68Ga-PSMA-11 PET Accuracy in Localizing Recurrent Prostate Cancer: A Prospective Single-Arm Clinical Trial. JAMA Oncol 2019; DOI: 10.1001/jamaoncol.2019.0096.
    CrossrefPubMedGoogle Scholar
  • 10 Bander NH. Technology insight: monoclonal antibody imaging of prostate cancer. Nat Clin Pract Urol 2006; 3: 216-225
    CrossrefPubMedGoogle Scholar
  • 11 EANM. Treatment Planning For Molecular Radiotherapy: Potential And Prospects.
    PubMedGoogle Scholar
  • 12 Bieth M. et al. Exploring New Multimodal Quantitative Imaging Indices for the Assessment of Osseous Tumor Burden in Prostate Cancer Using (68)Ga-PSMA PET/CT. J Nucl Med 2017; 58: 1632-1637
    CrossrefPubMedGoogle Scholar
  • 13 Maurer T. et al. Prostate-specific membrane antigen-radioguided surgery for metastatic lymph nodes in prostate cancer. Eur Urol 2015; 68: 530-534
    CrossrefPubMedGoogle Scholar
  • 14 Fuerst B. et al. First Robotic SPECT for Minimally Invasive Sentinel Lymph Node Mapping. IEEE Trans Med Imaging 2016; 35: 830-838
    CrossrefPubMedGoogle Scholar
  • 15 Zamboglou C. et al. Radiomic features from PSMA PET for non-invasive intraprostatic tumor discrimination and characterization in patients with intermediate- and high-risk prostate cancer – a comparison study with histology reference. Theranostics 2019; 9: 2595-2605
    CrossrefPubMedGoogle Scholar
  • 16 Bieth M. et al. Exploring New Multimodal Quantitative Imaging Indices for the Assessment of Osseous Tumor Burden in Prostate Cancer Using 68Ga-PSMA PET/CT. Journal of Nuclear Medicine 2017; 58: 1632-1637
    CrossrefPubMedGoogle Scholar
  • 17 Xu L. et al. Automated Whole-Body Bone Lesion Detection for Multiple Myeloma on 68Ga-Pentixafor PET/CT Imaging Using Deep Learning Methods. Contrast Media Mol Imaging 2018; 2018: 11
    PubMedGoogle Scholar
  • 18 Shi K. et al. Multi-Task Deep Learning for the Detection of Lesions on 68Ga-PSMA PET/CT Imaging. EANM Annual Congress; 2018
    PubMedGoogle Scholar
  • 19 Shi K. et al. Artificial Neural Network for Prediction of Post-therapy Dosimetry for 177Lu-PSMA I&T Therapy. DGN; 2019
    PubMedGoogle Scholar