Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients

被引:60
作者
Alongi, Pierpaolo [1 ]
Stefano, Alessandro [2 ]
Comelli, Albert [3 ]
Laudicella, Riccardo [4 ]
Scalisi, Salvatore [1 ]
Arnone, Giuseppe [5 ]
Barone, Stefano [6 ]
Spada, Massimiliano [7 ]
Purpura, Pierpaolo [8 ]
Bartolotta, Tommaso Vincenzo [5 ,8 ]
Midiri, Massimo [5 ]
Lagalla, Roberto [5 ]
Russo, Giorgio [2 ]
机构
[1] Fdn Ist G Giglio, Nucl Med Unit, I-90015 Cefalu, PA, Italy
[2] Natl Res Council CNR, Inst Mol Bioimaging & Physiol, Cefalu, PA, Italy
[3] Ri MED Fdn, Palermo, Italy
[4] Univ Messina, Dept Biomed & Dent Sci & Morphofunct Imaging, Nucl Med Unit, Messina, Italy
[5] Univ Palermo, Dept Biomed Neurosci & Adv Diagnost, Palermo, Italy
[6] Univ Palermo, Dipartimento Sci Agron Alimentari & Forestali SAA, Palermo, Italy
[7] Fdn Ist G Giglio, Unit Oncol, Cefalu, PA, Italy
[8] Fdn Ist Giuseppe Giglio Ct Pietrapollastra, Dept Radiol, Via Pisciotto, I-90015 Palermo, Italy
关键词
Prostate cancer; Positron emission tomography computed tomography; Choline; Radiomics; Machine learning; RECURRENCE; ANTIGEN;
D O I
10.1007/s00330-020-07617-8
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Objective: The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging. Material and methods: Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M). Results: In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%. Conclusion: This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes.
引用
收藏
页码:4595 / 4605
页数:11
相关论文
共 36 条
[21]   Radiomics: Images Are More than Pictures, They Are Data [J].
Gillies, Robert J. ;
Kinahan, Paul E. ;
Hricak, Hedvig .
RADIOLOGY, 2016, 278 (02) :563-577
[22]   Radiomics in PET/CT: More Than Meets the Eye? [J].
Hatt, Mathieu ;
Tixier, Florent ;
Visvikis, Dimitris ;
Le Rest, Catherine Cheze .
JOURNAL OF NUCLEAR MEDICINE, 2017, 58 (03) :365-366
[23]  
INCERTI E, 2015, J NUCL MED, V56
[24]   Active Surveillance for Prostate Cancer: Overview and Update [J].
Klotz, Laurence .
CURRENT TREATMENT OPTIONS IN ONCOLOGY, 2013, 14 (01) :97-108
[25]   18F-Facbc in Prostate Cancer: A Systematic Review and Meta-Analysis [J].
Laudicella, Riccardo ;
Albano, Domenico ;
Alongi, Pierpaolo ;
Argiroffi, Giovanni ;
Bauckneht, Matteo ;
Baldari, Sergio ;
Bertagna, Francesco ;
Boero, Michele ;
De Vincentis, Giuseppe ;
Del Sole, Angelo ;
Rubini, Giuseppe ;
Fantechi, Lorenzo ;
Frantellizzi, Viviana ;
Ganduscio, Gloria ;
Guglielmo, Priscilla ;
Nappi, Anna Giulia ;
Evangelista, Laura .
CANCERS, 2019, 11 (09)
[26]   Management of patients with rising prostate-specific antigen after radical prostatectomy [J].
Laufer, M ;
Pound, CR ;
Carducci, MA ;
Eisenberger, MA .
UROLOGY, 2000, 55 (03) :309-315
[27]   18F-FDG PET/CT radiomic predictors of pathologic complete response (pCR) to neoadjuvant chemotherapy in breast cancer patients [J].
Li, Panli ;
Wang, Xiuying ;
Xu, Chongrui ;
Liu, Cheng ;
Zheng, Chaojie ;
Fulham, Michael J. ;
Feng, Dagan ;
Wang, Lisheng ;
Song, Shaoli ;
Huang, Gang .
EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2020, 47 (05) :1116-1126
[28]   CT Textural Analysis of Large Primary Renal Cell Carcinomas: Pretreatment Tumor Heterogeneity Correlates With Histologic Findings and Clinical Outcomes [J].
Lubner, Meghan G. ;
Stabo, Nicholas ;
Abel, E. Jason ;
del Rio, Alejandro Munoz ;
Pickhardt, Perry J. .
AMERICAN JOURNAL OF ROENTGENOLOGY, 2016, 207 (01) :96-105
[29]   11C- or 18F-Choline PET/CT for Imaging Evaluation of Biochemical Recurrence of Prostate Cancer [J].
Mapelli, Paola ;
Incerti, Elena ;
Ceci, Francesco ;
Castellucci, Paolo ;
Fanti, Stefano ;
Picchio, Maria .
JOURNAL OF NUCLEAR MEDICINE, 2016, 57 :43S-48S
[30]   Prostate specific antigen only progression of prostate cancer [J].
Moul, JW .
JOURNAL OF UROLOGY, 2000, 163 (06) :1632-1642