Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI
In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify l...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/16/1/203 |
| _version_ | 1797358983902658560 |
|---|---|
| author | Giulia Nicoletti Simone Mazzetti Giovanni Maimone Valentina Cignini Renato Cuocolo Riccardo Faletti Marco Gatti Massimo Imbriaco Nicola Longo Andrea Ponsiglione Filippo Russo Alessandro Serafini Arnaldo Stanzione Daniele Regge Valentina Giannini |
| author_facet | Giulia Nicoletti Simone Mazzetti Giovanni Maimone Valentina Cignini Renato Cuocolo Riccardo Faletti Marco Gatti Massimo Imbriaco Nicola Longo Andrea Ponsiglione Filippo Russo Alessandro Serafini Arnaldo Stanzione Daniele Regge Valentina Giannini |
| author_sort | Giulia Nicoletti |
| collection | DOAJ |
| description | In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa. |
| first_indexed | 2024-03-08T15:10:05Z |
| format | Article |
| id | doaj.art-17682a3a03b34f88b6e4e8c988a41bc8 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-08T15:10:05Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-17682a3a03b34f88b6e4e8c988a41bc82024-01-10T14:53:01ZengMDPI AGCancers2072-66942024-01-0116120310.3390/cancers16010203Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRIGiulia Nicoletti0Simone Mazzetti1Giovanni Maimone2Valentina Cignini3Renato Cuocolo4Riccardo Faletti5Marco Gatti6Massimo Imbriaco7Nicola Longo8Andrea Ponsiglione9Filippo Russo10Alessandro Serafini11Arnaldo Stanzione12Daniele Regge13Valentina Giannini14Department of Electronics and Telecommunications, Polytechnic of Turin, Corso Duca degli Abruzzi, 24, 10129 Turin, ItalyRadiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, ItalyRadiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, ItalyDepartment of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, ItalyDepartment of Medicine, Surgery, and Dentistry, University of Salerno, Via Salvador Allende, 43, 84081 Baronissi, ItalyDepartment of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, ItalyDepartment of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, ItalyDepartment of Advanced Biomedical Sciences, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, ItalyDepartment of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, ItalyDepartment of Advanced Biomedical Sciences, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, ItalyRadiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, ItalyDepartment of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, ItalyDepartment of Advanced Biomedical Sciences, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, ItalyRadiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, ItalyDepartment of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, ItalyIn the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa.https://www.mdpi.com/2072-6694/16/1/203radiomicsprostate cancermagnetic resonance imagingfeature extractionexplainable artificial intelligencetumor aggressiveness |
| spellingShingle | Giulia Nicoletti Simone Mazzetti Giovanni Maimone Valentina Cignini Renato Cuocolo Riccardo Faletti Marco Gatti Massimo Imbriaco Nicola Longo Andrea Ponsiglione Filippo Russo Alessandro Serafini Arnaldo Stanzione Daniele Regge Valentina Giannini Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI Cancers radiomics prostate cancer magnetic resonance imaging feature extraction explainable artificial intelligence tumor aggressiveness |
| title | Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI |
| title_full | Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI |
| title_fullStr | Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI |
| title_full_unstemmed | Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI |
| title_short | Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI |
| title_sort | development and validation of an explainable radiomics model to predict high aggressive prostate cancer a multicenter radiomics study based on biparametric mri |
| topic | radiomics prostate cancer magnetic resonance imaging feature extraction explainable artificial intelligence tumor aggressiveness |
| url | https://www.mdpi.com/2072-6694/16/1/203 |
| work_keys_str_mv | AT giulianicoletti developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT simonemazzetti developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT giovannimaimone developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT valentinacignini developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT renatocuocolo developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT riccardofaletti developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT marcogatti developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT massimoimbriaco developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT nicolalongo developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT andreaponsiglione developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT filipporusso developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT alessandroserafini developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT arnaldostanzione developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT danieleregge developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri AT valentinagiannini developmentandvalidationofanexplainableradiomicsmodeltopredicthighaggressiveprostatecanceramulticenterradiomicsstudybasedonbiparametricmri |