1
|
Grahovac M, Spielvogel CP, Krajnc D, Ecsedi B, Traub-Weidinger T, Rasul S, Kluge K, Zhao M, Li X, Hacker M, Haug A, Papp L. Machine learning predictive performance evaluation of conventional and fuzzy radiomics in clinical cancer imaging cohorts. Eur J Nucl Med Mol Imaging 2023; 50:1607-1620. [PMID: 36738311 PMCID: PMC10119059 DOI: 10.1007/s00259-023-06127-1] [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: 10/03/2022] [Accepted: 01/25/2023] [Indexed: 02/05/2023]
Abstract
BACKGROUND Hybrid imaging became an instrumental part of medical imaging, particularly cancer imaging processes in clinical routine. To date, several radiomic and machine learning studies investigated the feasibility of in vivo tumor characterization with variable outcomes. This study aims to investigate the effect of recently proposed fuzzy radiomics and compare its predictive performance to conventional radiomics in cancer imaging cohorts. In addition, lesion vs. lesion+surrounding fuzzy and conventional radiomic analysis was conducted. METHODS Previously published 11C Methionine (MET) positron emission tomography (PET) glioma, 18F-FDG PET/computed tomography (CT) lung, and 68GA-PSMA-11 PET/magneto-resonance imaging (MRI) prostate cancer retrospective cohorts were included in the analysis to predict their respective clinical endpoints. Four delineation methods including manually defined reference binary (Ref-B), its smoothed, fuzzified version (Ref-F), as well as extended binary (Ext-B) and its fuzzified version (Ext-F) were incorporated to extract imaging biomarker standardization initiative (IBSI)-conform radiomic features from each cohort. Machine learning for the four delineation approaches was performed utilizing a Monte Carlo cross-validation scheme to estimate the predictive performance of the four delineation methods. RESULTS Reference fuzzy (Ref-F) delineation outperformed its binary delineation (Ref-B) counterpart in all cohorts within a volume range of 938-354987 mm3 with relative cross-validation area under the receiver operator characteristics curve (AUC) of +4.7-10.4. Compared to Ref-B, the highest AUC performance difference was observed by the Ref-F delineation in the glioma cohort (Ref-F: 0.74 vs. Ref-B: 0.70) and in the prostate cohort by Ref-F and Ext-F (Ref-F: 0.84, Ext-F: 0.86 vs. Ref-B: 0.80). In addition, fuzzy radiomics decreased feature redundancy by approx. 20%. CONCLUSIONS Fuzzy radiomics has the potential to increase predictive performance particularly in small lesion sizes compared to conventional binary radiomics in PET. We hypothesize that this effect is due to the ability of fuzzy radiomics to model partial volume effects and delineation uncertainties at small lesion boundaries. In addition, we consider that the lower redundancy of fuzzy radiomic features supports the identification of imaging biomarkers in future studies. Future studies shall consider systematically analyzing lesions and their surroundings with fuzzy and binary radiomics.
Collapse
Affiliation(s)
- M Grahovac
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
| | - C P Spielvogel
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
- Christian Doppler Laboratory for Applied Metabolomics, Medical University of Vienna, Vienna, Austria
| | - D Krajnc
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20, AT-1090, Vienna, Austria
| | - B Ecsedi
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20, AT-1090, Vienna, Austria
| | - T Traub-Weidinger
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
| | - S Rasul
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
| | - K Kluge
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
| | - M Zhao
- Department of Nuclear Medicine, Peking University Third Hospital, Beijing, People's Republic of China
| | - X Li
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
| | - M Hacker
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
| | - A Haug
- Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria
- Christian Doppler Laboratory for Applied Metabolomics, Medical University of Vienna, Vienna, Austria
| | - Laszlo Papp
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20, AT-1090, Vienna, Austria.
| |
Collapse
|
2
|
Papp L, Spielvogel CP, Grubmüller B, Grahovac M, Krajnc D, Ecsedi B, Sareshgi RAM, Mohamad D, Hamboeck M, Rausch I, Mitterhauser M, Wadsak W, Haug AR, Kenner L, Mazal P, Susani M, Hartenbach S, Baltzer P, Helbich TH, Kramer G, Shariat SF, Beyer T, Hartenbach M, Hacker M. Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [ 68Ga]Ga-PSMA-11 PET/MRI. Eur J Nucl Med Mol Imaging 2021; 48:1795-1805. [PMID: 33341915 PMCID: PMC8113201 DOI: 10.1007/s00259-020-05140-y] [Citation(s) in RCA: 60] [Impact Index Per Article: 20.0] [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: 10/09/2020] [Accepted: 11/29/2020] [Indexed: 12/13/2022]
Abstract
PURPOSE Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning. METHODS Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses. RESULTS The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively. CONCLUSION Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.
Collapse
Affiliation(s)
- L Papp
- QIMP Team, Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - C P Spielvogel
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
- Christian Doppler Laboratory for Applied Metabolomics, Vienna, Austria
| | - B Grubmüller
- Department of Urology, Medical University of Vienna, Vienna, Austria
| | - M Grahovac
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - D Krajnc
- QIMP Team, Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - B Ecsedi
- QIMP Team, Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - R A M Sareshgi
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - D Mohamad
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - M Hamboeck
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - I Rausch
- QIMP Team, Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - M Mitterhauser
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
- Ludwig Boltzmann Institute Applied Diagnostics, Vienna, Austria
| | - W Wadsak
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - A R Haug
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
- Christian Doppler Laboratory for Applied Metabolomics, Vienna, Austria
| | - L Kenner
- Christian Doppler Laboratory for Applied Metabolomics, Vienna, Austria
- Clinical Institute of Pathology, Medical University of Vienna, Vienna, Austria
| | - P Mazal
- Clinical Institute of Pathology, Medical University of Vienna, Vienna, Austria
| | - M Susani
- Clinical Institute of Pathology, Medical University of Vienna, Vienna, Austria
| | | | - P Baltzer
- Department of Biomedical Imaging and Image-guided Therapy, Division of Common General and Pediatric Radiology, Medical University of Vienna, Vienna, Austria
| | - T H Helbich
- Department of Biomedical Imaging and Image-guided Therapy, Division of Common General and Pediatric Radiology, Medical University of Vienna, Vienna, Austria
| | - G Kramer
- Department of Urology, Medical University of Vienna, Vienna, Austria
| | - S F Shariat
- Department of Urology, Medical University of Vienna, Vienna, Austria
| | - T Beyer
- QIMP Team, Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - M Hartenbach
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - M Hacker
- Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria.
| |
Collapse
|