Automated multiparametric localization of prostate cancer based on B-mode, shear-wave elastography, and contrast-enhanced ultrasound radiomics
Standard
Automated multiparametric localization of prostate cancer based on B-mode, shear-wave elastography, and contrast-enhanced ultrasound radiomics. / Wildeboer, Rogier R; Mannaerts, Christophe K; van Sloun, Ruud J G; Budäus, Lars; Tilki, Derya; Wijkstra, Hessel; Salomon, Georg; Mischi, Massimo.
In: EUR RADIOL, Vol. 30, No. 2, 02.2020, p. 806-815.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Automated multiparametric localization of prostate cancer based on B-mode, shear-wave elastography, and contrast-enhanced ultrasound radiomics
AU - Wildeboer, Rogier R
AU - Mannaerts, Christophe K
AU - van Sloun, Ruud J G
AU - Budäus, Lars
AU - Tilki, Derya
AU - Wijkstra, Hessel
AU - Salomon, Georg
AU - Mischi, Massimo
PY - 2020/2
Y1 - 2020/2
N2 - OBJECTIVES: The aim of this study was to assess the potential of machine learning based on B-mode, shear-wave elastography (SWE), and dynamic contrast-enhanced ultrasound (DCE-US) radiomics for the localization of prostate cancer (PCa) lesions using transrectal ultrasound.METHODS: This study was approved by the institutional review board and comprised 50 men with biopsy-confirmed PCa that were referred for radical prostatectomy. Prior to surgery, patients received transrectal ultrasound (TRUS), SWE, and DCE-US for three imaging planes. The images were automatically segmented and registered. First, model-based features related to contrast perfusion and dispersion were extracted from the DCE-US videos. Subsequently, radiomics were retrieved from all modalities. Machine learning was applied through a random forest classification algorithm, using the co-registered histopathology from the radical prostatectomy specimens as a reference to draw benign and malignant regions of interest. To avoid overfitting, the performance of the multiparametric classifier was assessed through leave-one-patient-out cross-validation.RESULTS: The multiparametric classifier reached a region-wise area under the receiver operating characteristics curve (ROC-AUC) of 0.75 and 0.90 for PCa and Gleason > 3 + 4 significant PCa, respectively, thereby outperforming the best-performing single parameter (i.e., contrast velocity) yielding ROC-AUCs of 0.69 and 0.76, respectively. Machine learning revealed that combinations between perfusion-, dispersion-, and elasticity-related features were favored.CONCLUSIONS: In this paper, technical feasibility of multiparametric machine learning to improve upon single US modalities for the localization of PCa has been demonstrated. Extended datasets for training and testing may establish the clinical value of automatic multiparametric US classification in the early diagnosis of PCa.KEY POINTS: • Combination of B-mode ultrasound, shear-wave elastography, and contrast ultrasound radiomics through machine learning is technically feasible. • Multiparametric ultrasound demonstrated a higher prostate cancer localization ability than single ultrasound modalities. • Computer-aided multiparametric ultrasound could help clinicians in biopsy targeting.
AB - OBJECTIVES: The aim of this study was to assess the potential of machine learning based on B-mode, shear-wave elastography (SWE), and dynamic contrast-enhanced ultrasound (DCE-US) radiomics for the localization of prostate cancer (PCa) lesions using transrectal ultrasound.METHODS: This study was approved by the institutional review board and comprised 50 men with biopsy-confirmed PCa that were referred for radical prostatectomy. Prior to surgery, patients received transrectal ultrasound (TRUS), SWE, and DCE-US for three imaging planes. The images were automatically segmented and registered. First, model-based features related to contrast perfusion and dispersion were extracted from the DCE-US videos. Subsequently, radiomics were retrieved from all modalities. Machine learning was applied through a random forest classification algorithm, using the co-registered histopathology from the radical prostatectomy specimens as a reference to draw benign and malignant regions of interest. To avoid overfitting, the performance of the multiparametric classifier was assessed through leave-one-patient-out cross-validation.RESULTS: The multiparametric classifier reached a region-wise area under the receiver operating characteristics curve (ROC-AUC) of 0.75 and 0.90 for PCa and Gleason > 3 + 4 significant PCa, respectively, thereby outperforming the best-performing single parameter (i.e., contrast velocity) yielding ROC-AUCs of 0.69 and 0.76, respectively. Machine learning revealed that combinations between perfusion-, dispersion-, and elasticity-related features were favored.CONCLUSIONS: In this paper, technical feasibility of multiparametric machine learning to improve upon single US modalities for the localization of PCa has been demonstrated. Extended datasets for training and testing may establish the clinical value of automatic multiparametric US classification in the early diagnosis of PCa.KEY POINTS: • Combination of B-mode ultrasound, shear-wave elastography, and contrast ultrasound radiomics through machine learning is technically feasible. • Multiparametric ultrasound demonstrated a higher prostate cancer localization ability than single ultrasound modalities. • Computer-aided multiparametric ultrasound could help clinicians in biopsy targeting.
KW - Aged
KW - Algorithms
KW - Area Under Curve
KW - Contrast Media
KW - Elasticity Imaging Techniques/methods
KW - Humans
KW - Image-Guided Biopsy/methods
KW - Machine Learning
KW - Male
KW - Middle Aged
KW - Neoplasm Grading
KW - Prostatectomy
KW - Prostatic Neoplasms/diagnostic imaging
KW - ROC Curve
KW - Reproducibility of Results
KW - Ultrasonography/methods
U2 - 10.1007/s00330-019-06436-w
DO - 10.1007/s00330-019-06436-w
M3 - SCORING: Journal article
C2 - 31602512
VL - 30
SP - 806
EP - 815
JO - EUR RADIOL
JF - EUR RADIOL
SN - 0938-7994
IS - 2
ER -