1
|
Pasini G, Russo G, Mantarro C, Bini F, Richiusa S, Morgante L, Comelli A, Russo GI, Sabini MG, Cosentino S, Marinozzi F, Ippolito M, Stefano A. A Critical Analysis of the Robustness of Radiomics to Variations in Segmentation Methods in 18F-PSMA-1007 PET Images of Patients Affected by Prostate Cancer. Diagnostics (Basel) 2023; 13:3640. [PMID: 38132224 PMCID: PMC10743045 DOI: 10.3390/diagnostics13243640] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Revised: 11/29/2023] [Accepted: 12/08/2023] [Indexed: 12/23/2023] Open
Abstract
BACKGROUND Radiomics shows promising results in supporting the clinical decision process, and much effort has been put into its standardization, thus leading to the Imaging Biomarker Standardization Initiative (IBSI), that established how radiomics features should be computed. However, radiomics still lacks standardization and many factors, such as segmentation methods, limit study reproducibility and robustness. AIM We investigated the impact that three different segmentation methods (manual, thresholding and region growing) have on radiomics features extracted from 18F-PSMA-1007 Positron Emission Tomography (PET) images of 78 patients (43 Low Risk, 35 High Risk). Segmentation was repeated for each patient, thus leading to three datasets of segmentations. Then, feature extraction was performed for each dataset, and 1781 features (107 original, 930 Laplacian of Gaussian (LoG) features, 744 wavelet features) were extracted. Feature robustness and reproducibility were assessed through the intra class correlation coefficient (ICC) to measure agreement between the three segmentation methods. To assess the impact that the three methods had on machine learning models, feature selection was performed through a hybrid descriptive-inferential method, and selected features were given as input to three classifiers, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA), Random Forest (RF), AdaBoost and Neural Networks (NN), whose performance in discriminating between low-risk and high-risk patients have been validated through 30 times repeated five-fold cross validation. CONCLUSIONS Our study showed that segmentation methods influence radiomics features and that Shape features were the least reproducible (average ICC: 0.27), while GLCM features the most reproducible. Moreover, feature reproducibility changed depending on segmentation type, resulting in 51.18% of LoG features exhibiting excellent reproducibility (range average ICC: 0.68-0.87) and 47.85% of wavelet features exhibiting poor reproducibility that varied between wavelet sub-bands (range average ICC: 0.34-0.80) and resulted in the LLL band showing the highest average ICC (0.80). Finally, model performance showed that region growing led to the highest accuracy (74.49%), improved sensitivity (84.38%) and AUC (79.20%) in contrast with manual segmentation.
Collapse
Affiliation(s)
- Giovanni Pasini
- Department of Mechanical and Aerospace Engineering, Sapienza University of Rome, Eudossiana 18, 00184 Rome, Italy; (G.P.); (L.M.); (F.M.)
- Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, Italy; (G.R.); (S.R.); (A.C.); (A.S.)
| | - Giorgio Russo
- Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, Italy; (G.R.); (S.R.); (A.C.); (A.S.)
- National Laboratory of South, National Institute for Nuclear Physics (LNS-INFN), 95125 Catania, Italy
| | - Cristina Mantarro
- Nuclear Medicine Department, Cannizzaro Hospital, 95125 Catania, Italy; (C.M.); (S.C.); (M.I.)
| | - Fabiano Bini
- Department of Mechanical and Aerospace Engineering, Sapienza University of Rome, Eudossiana 18, 00184 Rome, Italy; (G.P.); (L.M.); (F.M.)
| | - Selene Richiusa
- Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, Italy; (G.R.); (S.R.); (A.C.); (A.S.)
| | - Lucrezia Morgante
- Department of Mechanical and Aerospace Engineering, Sapienza University of Rome, Eudossiana 18, 00184 Rome, Italy; (G.P.); (L.M.); (F.M.)
| | - Albert Comelli
- Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, Italy; (G.R.); (S.R.); (A.C.); (A.S.)
- Ri.MED Foundation, Via Bandiera 11, 90133 Palermo, Italy
| | - Giorgio Ivan Russo
- Department of Surgery, Urology Section, University of Catania, 95125 Catania, Italy;
| | | | - Sebastiano Cosentino
- Nuclear Medicine Department, Cannizzaro Hospital, 95125 Catania, Italy; (C.M.); (S.C.); (M.I.)
| | - Franco Marinozzi
- Department of Mechanical and Aerospace Engineering, Sapienza University of Rome, Eudossiana 18, 00184 Rome, Italy; (G.P.); (L.M.); (F.M.)
| | - Massimo Ippolito
- Nuclear Medicine Department, Cannizzaro Hospital, 95125 Catania, Italy; (C.M.); (S.C.); (M.I.)
| | - Alessandro Stefano
- Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, Italy; (G.R.); (S.R.); (A.C.); (A.S.)
- National Laboratory of South, National Institute for Nuclear Physics (LNS-INFN), 95125 Catania, Italy
| |
Collapse
|
2
|
Kirchner MA, Holzgreve A, Brendel M, Orth M, Ruf VC, Steiger K, Pötter D, Gold L, Unterrainer M, Mittlmeier LM, Barci E, Kälin RE, Glass R, Lindner S, Kaiser L, Maas J, von Baumgarten L, Ilhan H, Belka C, Notni J, Bartenstein P, Lauber K, Albert NL. PSMA PET Imaging in Glioblastoma: A Preclinical Evaluation and Theranostic Outlook. Front Oncol 2021; 11:774017. [PMID: 34869017 PMCID: PMC8635528 DOI: 10.3389/fonc.2021.774017] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2021] [Accepted: 10/20/2021] [Indexed: 12/11/2022] Open
Abstract
Background Prostate specific membrane antigen (PSMA) PET imaging has recently gained attention in glioblastoma (GBM) patients as a potential theranostic target for PSMA radioligand therapy. However, PSMA PET has not yet been established in a murine GBM model. Our goal was to investigate the potential of PSMA PET imaging in the syngeneic GL261 GBM model and to give an outlook regarding the potential of PMSA radioligand therapy in this model. Methods We performed an 18F-PSMA-1007 PET study in the orthotopic GL261 model (n=14 GBM, n=7 sham-operated mice) with imaging at day 4, 8, 11, 15, 18 and 22 post implantation. Time-activity-curves (TAC) were extracted from dynamic PET scans (0-120 min p. i.) in a subset of mice (n=4 GBM, n=3 sham-operated mice) to identify the optimal time frame for image analysis, and standardized-uptake-values (SUV) as well as tumor-to-background ratios (TBR) using contralateral normal brain as background were calculated in all mice. Additionally, computed tomography (CT), ex vivo and in vitro18F-PSMA-1007 autoradiographies (ARG) were performed. Results TAC analysis of GBM mice revealed a plateau of TBR values after 40 min p. i. Therefore, a 30 min time frame between 40-70 min p. i. was chosen for PET quantification. At day 15 and later, GBM mice showed a discernible PSMA PET signal on the inoculation site, with highest TBRmean in GBM mice at day 18 (7.3 ± 1.3 vs. 1.6 ± 0.3 in shams; p=0.024). Ex vivo ARG confirmed high tracer signal in GBM compared to healthy background (TBRmean 26.9 ± 10.5 vs. 1.6 ± 0.7 in shams at day 18/22 post implantation; p=0.002). However, absolute uptake values in the GL261 tumor remained low (e.g., SUVmean 0.21 ± 0.04 g/ml at day 18) resulting in low ratios compared to dose-relevant organs (e.g., mean tumor-to-kidney ratio 1.5E-2 ± 0.5E-2). Conclusions Although 18F-PSMA-1007 PET imaging of GL261 tumor-bearing mice is feasible and resulted in high TBRs, absolute tumoral uptake values remained low and hint to limited applicability of the GL261 model for PSMA-directed therapy studies. Further investigations are warranted to identify suitable models for preclinical evaluation of PSMA-targeted theranostic approaches in GBM.
Collapse
Affiliation(s)
- Maximilian A Kirchner
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Adrien Holzgreve
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Matthias Brendel
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Michael Orth
- Department of Radiation Oncology, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Viktoria C Ruf
- Center for Neuropathology and Prion Research, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Katja Steiger
- Institute of Pathology, Technische Universität München (TUM) School of Medicine, Technical University of Munich, Munich, Germany
| | - Dennis Pötter
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Lukas Gold
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Marcus Unterrainer
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany.,Department of Radiology, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Lena M Mittlmeier
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Enio Barci
- Neurosurgical Research, Department of Neurosurgery, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Roland E Kälin
- Neurosurgical Research, Department of Neurosurgery, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Rainer Glass
- Neurosurgical Research, Department of Neurosurgery, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany.,German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Simon Lindner
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Lena Kaiser
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Jessica Maas
- Department of Radiation Oncology, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Louisa von Baumgarten
- Department of Neurosurgery, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Harun Ilhan
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany
| | - Claus Belka
- Department of Radiation Oncology, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany.,German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Johannes Notni
- Institute of Pathology, Technische Universität München (TUM) School of Medicine, Technical University of Munich, Munich, Germany
| | - Peter Bartenstein
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany.,German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Kirsten Lauber
- Department of Radiation Oncology, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany.,German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Nathalie L Albert
- Department of Nuclear Medicine, University Hospital, Ludwig-Maximilians-Universität (LMU) Munich, Munich, Germany.,German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), Heidelberg, Germany
| |
Collapse
|
3
|
Mittlmeier LM, Unterrainer M, Rodler S, Todica A, Albert NL, Burgard C, Cyran CC, Kunz WG, Ricke J, Bartenstein P, Stief CG, Ilhan H, Staehler M. 18F-PSMA-1007 PET/CT for response assessment in patients with metastatic renal cell carcinoma undergoing tyrosine kinase or checkpoint inhibitor therapy: preliminary results. Eur J Nucl Med Mol Imaging 2020; 48:2031-2037. [PMID: 33369689 PMCID: PMC8113284 DOI: 10.1007/s00259-020-05165-3] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2020] [Accepted: 12/13/2020] [Indexed: 11/26/2022]
Abstract
Introduction Tyrosine kinase (TKI) and checkpoint inhibitors (CI) prolonged overall survival in metastatic renal cell carcinoma (mRCC). Early prediction of treatment response is highly desirable for the individualization of patient management and improvement of therapeutic outcome; however, serum biochemistry is unable to predict therapeutic efficacy. Therefore, we compared 18F-PSMA-1007 PET imaging for response assessment in mRCC patients undergoing TKI or CI therapy compared to CT-based response assessment as the current imaging reference standard. Methods 18F-PSMA-1007 PET/CT was performed in mRCC patients prior to initiation of systemic treatment and 8 weeks after therapy initiation. Treatment response was evaluated separately on 18F-PSMA-PET and CT. Changes on PSMA-PET (SUVmean) were assessed on a per patient basis using a modified PERCIST scoring system. Complete response (CRPET) was defined as absence of any uptake in all target lesions on posttreatment PET. Partial response (PRPET) was defined as decrease in summed SUVmean of > 30%. The appearance of new, PET-positive lesions or an increase in summed SUVmean of > 30% was defined as progressive disease (PDPET). A change in summed SUVmean of ± 30% defined stable disease (SDPET). RECIST 1.1 criteria were used for response assessment on CT. Results of radiographic response assessment on PSMA-PET and CT were compared. Results Overall, 11 mRCC patients undergoing systemic treatment were included. At baseline PSMA-PET1, all mRCC patients showed at least one PSMA-avid lesion. On follow-up PET2, 3 patients showed CRPET, 3 PRPET, 4 SDPET, and 1 PDPET. According to RECIST 1.1, 1 patient showed PRCT, 9 SDCT, and 1 PDCT. Overall, concordant classifications were found in only 2 cases (2 SDCT + PET). Patients with CRPET on PET were classified as 3 SDCT on CT using RECIST 1.1. By contrast, the patient classified as PRCT on CT showed PSMA uptake without major changes during therapy (SDPET). However, among 9 patients with SDCT on CT, 3 were classified as CRPET, 3 as PRPET, 1 as PDPET, and only 2 as SDPET on PSMA-PET. Conclusion On PSMA-PET, heterogeneous courses were observed during systemic treatment in mRCC patients with highly diverging results compared to RECIST 1.1. In the light of missing biomarkers for early response assessment, PSMA-PET might allow more precise response assessment to systemic treatment, especially in patients classified as SD on CT.
Collapse
Affiliation(s)
- L M Mittlmeier
- Department of Urology, University Hospital, LMU Munich, Munich, Germany
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - M Unterrainer
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - S Rodler
- Department of Urology, University Hospital, LMU Munich, Munich, Germany
| | - A Todica
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - N L Albert
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - C Burgard
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - C C Cyran
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - W G Kunz
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - J Ricke
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - P Bartenstein
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - C G Stief
- Department of Urology, University Hospital, LMU Munich, Munich, Germany
| | - H Ilhan
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - M Staehler
- Department of Urology, University Hospital, LMU Munich, Munich, Germany.
- Head Interdisciplinary Center on Renal Tumors, Department of Urology, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany.
| |
Collapse
|