Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI
Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the ra...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.802964/full |
| _version_ | 1830209238344925184 |
|---|---|
| author | Elena Bertelli Laura Mercatelli Chiara Marzi Eva Pachetti Eva Pachetti Michela Baccini Michela Baccini Andrea Barucci Sara Colantonio Luca Gherardini Lorenzo Lattavo Maria Antonietta Pascali Simone Agostini Vittorio Miele |
| author_facet | Elena Bertelli Laura Mercatelli Chiara Marzi Eva Pachetti Eva Pachetti Michela Baccini Michela Baccini Andrea Barucci Sara Colantonio Luca Gherardini Lorenzo Lattavo Maria Antonietta Pascali Simone Agostini Vittorio Miele |
| author_sort | Elena Bertelli |
| collection | DOAJ |
| description | Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability. |
| first_indexed | 2024-12-18T05:03:45Z |
| format | Article |
| id | doaj.art-d19f9ec97f514b49a39787fa70188101 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-18T05:03:45Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-d19f9ec97f514b49a39787fa701881012022-12-21T21:20:04ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-01-011110.3389/fonc.2021.802964802964Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRIElena Bertelli0Laura Mercatelli1Chiara Marzi2Eva Pachetti3Eva Pachetti4Michela Baccini5Michela Baccini6Andrea Barucci7Sara Colantonio8Luca Gherardini9Lorenzo Lattavo10Maria Antonietta Pascali11Simone Agostini12Vittorio Miele13Department of Radiology, Careggi University Hospital, Florence, ItalyDepartment of Radiology, Careggi University Hospital, Florence, Italy“Nello Carrara” Institute of Applied Physics (IFAC), National Research Council of Italy (CNR), Sesto Fiorentino, Italy“Alessandro Faedo” Institute of Information Science and Technologies (ISTI), National Research Council of Italy (CNR), Pisa, ItalyDepartment of Information Engineering (DII), University of Pisa, Pisa, Italy“Giuseppe Parenti” Department of Statistics, Computer Science, Applications(DiSIA), University of Florence, Florence, ItalyFlorence Center for Data Science, University of Florence, Florence, Italy“Nello Carrara” Institute of Applied Physics (IFAC), National Research Council of Italy (CNR), Sesto Fiorentino, Italy“Alessandro Faedo” Institute of Information Science and Technologies (ISTI), National Research Council of Italy (CNR), Pisa, Italy“Giuseppe Parenti” Department of Statistics, Computer Science, Applications(DiSIA), University of Florence, Florence, ItalyDepartment of Radiology, Careggi University Hospital, Florence, Italy“Alessandro Faedo” Institute of Information Science and Technologies (ISTI), National Research Council of Italy (CNR), Pisa, ItalyDepartment of Radiology, Careggi University Hospital, Florence, ItalyDepartment of Radiology, Careggi University Hospital, Florence, ItalyProstate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.https://www.frontiersin.org/articles/10.3389/fonc.2021.802964/fullprostate cancermpMRI prostate cancer aggressivenessdeep learningmachine learningradiomics |
| spellingShingle | Elena Bertelli Laura Mercatelli Chiara Marzi Eva Pachetti Eva Pachetti Michela Baccini Michela Baccini Andrea Barucci Sara Colantonio Luca Gherardini Lorenzo Lattavo Maria Antonietta Pascali Simone Agostini Vittorio Miele Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI Frontiers in Oncology prostate cancer mpMRI prostate cancer aggressiveness deep learning machine learning radiomics |
| title | Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI |
| title_full | Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI |
| title_fullStr | Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI |
| title_full_unstemmed | Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI |
| title_short | Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI |
| title_sort | machine and deep learning prediction of prostate cancer aggressiveness using multiparametric mri |
| topic | prostate cancer mpMRI prostate cancer aggressiveness deep learning machine learning radiomics |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.802964/full |
| work_keys_str_mv | AT elenabertelli machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT lauramercatelli machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT chiaramarzi machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT evapachetti machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT evapachetti machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT michelabaccini machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT michelabaccini machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT andreabarucci machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT saracolantonio machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT lucagherardini machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT lorenzolattavo machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT mariaantoniettapascali machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT simoneagostini machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri AT vittoriomiele machineanddeeplearningpredictionofprostatecanceraggressivenessusingmultiparametricmri |