Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features
Background: The aim of our study was to develop a radiomic tool for the prediction of clinically significant prostate cancer. Methods: From September 2020 to December 2021, 91 patients who underwent magnetic resonance imaging prostate fusion biopsy at our institution were selected. Prostate cancer a...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Current Oncology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1718-7729/30/2/157 |
| _version_ | 1797621551008317440 |
|---|---|
| author | Francesco Prata Umberto Anceschi Ermanno Cordelli Eliodoro Faiella Angelo Civitella Piergiorgio Tuzzolo Andrea Iannuzzi Alberto Ragusa Francesco Esperto Salvatore Mario Prata Rosa Sicilia Giovanni Muto Rosario Francesco Grasso Roberto Mario Scarpa Paolo Soda Giuseppe Simone Rocco Papalia |
| author_facet | Francesco Prata Umberto Anceschi Ermanno Cordelli Eliodoro Faiella Angelo Civitella Piergiorgio Tuzzolo Andrea Iannuzzi Alberto Ragusa Francesco Esperto Salvatore Mario Prata Rosa Sicilia Giovanni Muto Rosario Francesco Grasso Roberto Mario Scarpa Paolo Soda Giuseppe Simone Rocco Papalia |
| author_sort | Francesco Prata |
| collection | DOAJ |
| description | Background: The aim of our study was to develop a radiomic tool for the prediction of clinically significant prostate cancer. Methods: From September 2020 to December 2021, 91 patients who underwent magnetic resonance imaging prostate fusion biopsy at our institution were selected. Prostate cancer aggressiveness was assessed by combining the three orthogonal planes-Llocal binary pattern the 3Dgray level co-occurrence matrix, and other first order statistical features with clinical (semantic) features. The 487 features were used to predict whether the Gleason score was clinically significant (≥7) in the final pathology. A feature selection algorithm was used to determine the most predictive features, and at the end of the process, nine features were chosen through a 10-fold cross validation. Results: The feature analysis revealed a detection accuracy of 83.5%, with a clinically significant precision of 84.4% and a clinically significant sensitivity of 91.5%. The resulting area under the curve was 80.4%. Conclusions: Radiomic analysis allowed us to develop a tool that was able to predict a Gleason score of ≥7. This new tool may improve the detection rate of clinically significant prostate cancer and overcome the limitations of the subjective interpretation of magnetic resonance imaging, reducing the number of useless biopsies. |
| first_indexed | 2024-03-11T08:57:35Z |
| format | Article |
| id | doaj.art-12298fa3abdc462098d04159c627878b |
| institution | Directory Open Access Journal |
| issn | 1198-0052 1718-7729 |
| language | English |
| last_indexed | 2024-03-11T08:57:35Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Current Oncology |
| spelling | doaj.art-12298fa3abdc462098d04159c627878b2023-11-16T19:58:07ZengMDPI AGCurrent Oncology1198-00521718-77292023-02-013022021203110.3390/curroncol30020157Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical FeaturesFrancesco Prata0Umberto Anceschi1Ermanno Cordelli2Eliodoro Faiella3Angelo Civitella4Piergiorgio Tuzzolo5Andrea Iannuzzi6Alberto Ragusa7Francesco Esperto8Salvatore Mario Prata9Rosa Sicilia10Giovanni Muto11Rosario Francesco Grasso12Roberto Mario Scarpa13Paolo Soda14Giuseppe Simone15Rocco Papalia16Department of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, IRCCS “Regina Elena” National Cancer Institute, 00144 Rome, ItalyUnit of Computer Systems and Bioinformatics, Department of Engineering, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Diagnostic and Interventional Radiology, Sant’Anna Hospital, 22042 San Fermo della Battaglia, ItalyDepartment of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalySimple Operating Unit of Lower Urinary Tract Surgery, SS. Trinità Hospital, 03039 Sora, ItalyUnit of Computer Systems and Bioinformatics, Department of Engineering, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, Humanitas Gradenigo University, 10153 Turin, ItalyDepartment of Diagnostic and Interventional Radiology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyUnit of Computer Systems and Bioinformatics, Department of Engineering, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyDepartment of Urology, IRCCS “Regina Elena” National Cancer Institute, 00144 Rome, ItalyDepartment of Urology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, ItalyBackground: The aim of our study was to develop a radiomic tool for the prediction of clinically significant prostate cancer. Methods: From September 2020 to December 2021, 91 patients who underwent magnetic resonance imaging prostate fusion biopsy at our institution were selected. Prostate cancer aggressiveness was assessed by combining the three orthogonal planes-Llocal binary pattern the 3Dgray level co-occurrence matrix, and other first order statistical features with clinical (semantic) features. The 487 features were used to predict whether the Gleason score was clinically significant (≥7) in the final pathology. A feature selection algorithm was used to determine the most predictive features, and at the end of the process, nine features were chosen through a 10-fold cross validation. Results: The feature analysis revealed a detection accuracy of 83.5%, with a clinically significant precision of 84.4% and a clinically significant sensitivity of 91.5%. The resulting area under the curve was 80.4%. Conclusions: Radiomic analysis allowed us to develop a tool that was able to predict a Gleason score of ≥7. This new tool may improve the detection rate of clinically significant prostate cancer and overcome the limitations of the subjective interpretation of magnetic resonance imaging, reducing the number of useless biopsies.https://www.mdpi.com/1718-7729/30/2/157clinically significantmachine-learningprostate biopsyprostate cancerradiomic |
| spellingShingle | Francesco Prata Umberto Anceschi Ermanno Cordelli Eliodoro Faiella Angelo Civitella Piergiorgio Tuzzolo Andrea Iannuzzi Alberto Ragusa Francesco Esperto Salvatore Mario Prata Rosa Sicilia Giovanni Muto Rosario Francesco Grasso Roberto Mario Scarpa Paolo Soda Giuseppe Simone Rocco Papalia Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features Current Oncology clinically significant machine-learning prostate biopsy prostate cancer radiomic |
| title | Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features |
| title_full | Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features |
| title_fullStr | Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features |
| title_full_unstemmed | Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features |
| title_short | Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features |
| title_sort | radiomic machine learning analysis of multiparametric magnetic resonance imaging in the diagnosis of clinically significant prostate cancer new combination of textural and clinical features |
| topic | clinically significant machine-learning prostate biopsy prostate cancer radiomic |
| url | https://www.mdpi.com/1718-7729/30/2/157 |
| work_keys_str_mv | AT francescoprata radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT umbertoanceschi radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT ermannocordelli radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT eliodorofaiella radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT angelocivitella radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT piergiorgiotuzzolo radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT andreaiannuzzi radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT albertoragusa radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT francescoesperto radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT salvatoremarioprata radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT rosasicilia radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT giovannimuto radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT rosariofrancescograsso radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT robertomarioscarpa radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT paolosoda radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT giuseppesimone radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures AT roccopapalia radiomicmachinelearninganalysisofmultiparametricmagneticresonanceimaginginthediagnosisofclinicallysignificantprostatecancernewcombinationoftexturalandclinicalfeatures |