1
|
Mazzetti S, Defeudis A, Nicoletti G, Chiorino G, De Luca S, Faletti R, Gatti M, Gontero P, Manfredi M, Mello-Grand M, Peraldo-Neia C, Zitella A, Porpiglia F, Regge D, Giannini V. Development and validation of a clinical decision support system based on PSA, microRNAs, and MRI for the detection of prostate cancer. Eur Radiol 2024; 34:5108-5117. [PMID: 38177618 PMCID: PMC11255044 DOI: 10.1007/s00330-023-10542-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Revised: 11/29/2023] [Accepted: 12/02/2023] [Indexed: 01/06/2024]
Abstract
OBJECTIVES The aims of this study are to develop and validate a clinical decision support system based on demographics, prostate-specific antigen (PSA), microRNA (miRNA), and MRI for the detection of prostate cancer (PCa) and clinical significant (cs) PCa, and to assess if this system performs better compared to MRI alone. METHODS This retrospective, multicenter, observational study included 222 patients (mean age 66, range 46-75 years) who underwent prostate MRI, miRNA (let-7a-5p and miR-103a-3p) assessment, and biopsy. Monoparametric and multiparametric models including age, PSA, miRNA, and MRI outcome were trained on 65% of the data and then validated on the remaining 35% to predict both PCa (any Gleason grade [GG]) and csPCa (GG ≥ 2 vs GG = 1/negative). Accuracy, sensitivity, specificity, positive and negative predictive value (NPV), and area under the receiver operating characteristic curve were calculated. RESULTS MRI outcome was the best predictor in the monoparametric model for both detection of PCa, with sensitivity of 90% (95%CI 73-98%) and NPV of 93% (95%CI 82-98%), and for csPCa identification, with sensitivity of 91% (95%CI 72-99%) and NPV of 95% (95%CI 84-99%). Sensitivity and NPV of PSA + miRNA for the detection of csPCa were not statistically different from the other models including MRI alone. CONCLUSION MRI stand-alone yielded the best prediction models for both PCa and csPCa detection in biopsy-naïve patients. The use of miRNAs let-7a-5p and miR-103a-3p did not improve classification performances compared to MRI stand-alone results. CLINICAL RELEVANCE STATEMENT The use of miRNA (let-7a-5p and miR-103a-3p), PSA, and MRI in a clinical decision support system (CDSS) does not improve MRI stand-alone performance in the detection of PCa and csPCa. KEY POINTS • Clinical decision support systems including MRI improve the detection of both prostate cancer and clinically significant prostate cancer with respect to PSA test and/or microRNA. • The use of miRNAs let-7a-5p and miR-103a-3p did not significantly improve MRI stand-alone performance. • Results of this study were in line with previous works on MRI and microRNA.
Collapse
Affiliation(s)
- Simone Mazzetti
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Candiolo, Italy
- Department of Surgical Sciences, University of Turin, Turin, Italy
| | - Arianna Defeudis
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Candiolo, Italy.
- Department of Surgical Sciences, University of Turin, Turin, Italy.
| | - Giulia Nicoletti
- Department of Surgical Sciences, University of Turin, Turin, Italy
- Department of Electronics and Telecommunications, Polytechnic of Turin, Turin, Italy
| | | | - Stefano De Luca
- Department of Urology, San Luigi Gonzaga Hospital, University of Turin, Orbassano, Italy
| | - Riccardo Faletti
- Radiology Unit, Department of Surgical Sciences, University of Turin, Turin, Italy
| | - Marco Gatti
- Radiology Unit, Department of Surgical Sciences, University of Turin, Turin, Italy
| | - Paolo Gontero
- Division of Urology, Department of Surgical Sciences, University of Turin, Turin, Italy
| | - Matteo Manfredi
- Department of Urology, San Luigi Gonzaga Hospital, University of Turin, Orbassano, Italy
| | | | | | - Andrea Zitella
- Division of Urology, Department of Surgical Sciences, University of Turin, Turin, Italy
| | - Francesco Porpiglia
- Department of Urology, San Luigi Gonzaga Hospital, University of Turin, Orbassano, Italy
| | - Daniele Regge
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Candiolo, Italy
| | - Valentina Giannini
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Candiolo, Italy
- Department of Surgical Sciences, University of Turin, Turin, Italy
| |
Collapse
|
2
|
Panic J, Defeudis A, Balestra G, Giannini V, Rosati S. Normalization Strategies in Multi-Center Radiomics Abdominal MRI: Systematic Review and Meta-Analyses. IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY 2023; 4:67-76. [PMID: 37283773 PMCID: PMC10241248 DOI: 10.1109/ojemb.2023.3271455] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Revised: 03/18/2023] [Accepted: 04/25/2023] [Indexed: 06/08/2023] Open
Abstract
Goal: Artificial intelligence applied to medical image analysis has been extensively used to develop non-invasive diagnostic and prognostic signatures. However, these imaging biomarkers should be largely validated on multi-center datasets to prove their robustness before they can be introduced into clinical practice. The main challenge is represented by the great and unavoidable image variability which is usually addressed using different pre-processing techniques including spatial, intensity and feature normalization. The purpose of this study is to systematically summarize normalization methods and to evaluate their correlation with the radiomics model performances through meta-analyses. This review is carried out according to the PRISMA statement: 4777 papers were collected, but only 74 were included. Two meta-analyses were carried out according to two clinical aims: characterization and prediction of response. Findings of this review demonstrated that there are some commonly used normalization approaches, but not a commonly agreed pipeline that can allow to improve performance and to bridge the gap between bench and bedside.
Collapse
Affiliation(s)
- Jovana Panic
- Department of Surgical Science, and Polytechnic of Turin, Department of Electronics and TelecommunicationsUniversity of Turin10129TurinItaly
| | - Arianna Defeudis
- Department of Surgical ScienceUniversity of Turin10129TurinItaly
- Candiolo Cancer InstituteFPO-IRCCS10060CandioloItaly
| | - Gabriella Balestra
- Department of Electronics and TelecommunicationsPolytechnic of Turin10129TurinItaly
| | - Valentina Giannini
- Department of Surgical ScienceUniversity of Turin10129TurinItaly
- Candiolo Cancer InstituteFPO-IRCCS10060CandioloItaly
| | - Samanta Rosati
- Department of Electronics and TelecommunicationsPolytechnic of Turin10129TurinItaly
| |
Collapse
|