Dario Giambelluca1, Roberto Cannella1, Federica Vernuccio2, Albert Comelli3, Alice Pavone1, Leonardo Salvaggio1, Massimo Galia1, Massimo Midiri1, Roberto Lagalla1, Giuseppe Salvaggio1. 1. Dipartimento di Biomedicina, Neuroscienze e Diagnostica avanzata (BIND), University of Palermo, Palermo, Italy. 2. Dipartimento di Biomedicina, Neuroscienze e Diagnostica avanzata (BIND), University of Palermo, Palermo, Italy; Department of Health Promotion, Mother and Child Care, Internal Medicine and Medical Specialties (ProMISE), University of Palermo, Palermo, Italy; University Paris 7 Diderot, Sorbonne Paris Cité, Paris, France; I.R.C.C.S. Centro Neurolesi Bonino Pulejo, Messina, Italy. Electronic address: federicavernuccio@gmail.com. 3. Ri.MED Foundation, Palermo, Italy; Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta GA, US; Department of Industrial and Digital Innovation (DIID), University of Palermo, Italy.
Abstract
PURPOSE: To determine the diagnostic performance of texture analysis of prostate MRI for the diagnosis of prostate cancer among Prostate Imaging Reporting and Data System (PI-RADS) 3 lesions. MATERIALS AND METHODS: Forty-three patients with at least 1 PI-RADS 3 lesion on prostate MRI performed between June 2016 and January 2019 were retrospectively included. Reference standard was pathological analysis of radical prostatectomy specimens or MRI-targeted biopsies. Texture analysis extraction of target lesions was performed on axial T2-weighted images and apparent diffusion coefficient (ADC) maps using a radiomic software. Lesions were categorized as prostate cancer (Gleason score [GS] ≥ 6), and no prostate cancer. Statistical analysis was performed using the generalized linear model (GLM) regression and the discriminant analysis (DA). AUROC with 95% confidence intervals were calculated to assess the diagnostic performance of standalone features and predictive models for the diagnosis of prostate cancer (GS ≥ 6) and clinically-significant prostate cancer (GS ≥ 7). RESULTS: The analysis of 46 PI-RADS 3 lesions (ie, 27 [58.7%] no prostate cancers; 19 [41.3%] prostate cancers) revealed 9 and 6 independent texture parameters significantly correlated with the final histopathological results on T2-weighted and ADC maps images, respectively. The resulting GLM and DA predictive models for the diagnosis of prostate cancer yielded an AUROC of 0.775 and 0.779 on T2-weighted images or 0.815 and 0.821 on ADC maps images. For the diagnosis of clinically-significant prostate cancer, the resulting GLM and DA predictive models for the diagnosis of prostate cancer yielded an AUROC of 0.769 and 0.817 on T2-weighted images or 0.749 and 0.744 on ADC maps images. CONCLUSION: Texture analysis of PI-RADS 3 lesions on T2-weighted and ADC maps images helps identifying prostate cancer. The good diagnostic performance of the combination of multiple radiomic features for the diagnosis of prostate cancer may help predicting lesions where aggressive management may be warranted.
PURPOSE: To determine the diagnostic performance of texture analysis of prostate MRI for the diagnosis of prostate cancer among Prostate Imaging Reporting and Data System (PI-RADS) 3 lesions. MATERIALS AND METHODS: Forty-three patients with at least 1 PI-RADS 3 lesion on prostate MRI performed between June 2016 and January 2019 were retrospectively included. Reference standard was pathological analysis of radical prostatectomy specimens or MRI-targeted biopsies. Texture analysis extraction of target lesions was performed on axial T2-weighted images and apparent diffusion coefficient (ADC) maps using a radiomic software. Lesions were categorized as prostate cancer (Gleason score [GS] ≥ 6), and no prostate cancer. Statistical analysis was performed using the generalized linear model (GLM) regression and the discriminant analysis (DA). AUROC with 95% confidence intervals were calculated to assess the diagnostic performance of standalone features and predictive models for the diagnosis of prostate cancer (GS ≥ 6) and clinically-significant prostate cancer (GS ≥ 7). RESULTS: The analysis of 46 PI-RADS 3 lesions (ie, 27 [58.7%] no prostate cancers; 19 [41.3%] prostate cancers) revealed 9 and 6 independent texture parameters significantly correlated with the final histopathological results on T2-weighted and ADC maps images, respectively. The resulting GLM and DA predictive models for the diagnosis of prostate cancer yielded an AUROC of 0.775 and 0.779 on T2-weighted images or 0.815 and 0.821 on ADC maps images. For the diagnosis of clinically-significant prostate cancer, the resulting GLM and DA predictive models for the diagnosis of prostate cancer yielded an AUROC of 0.769 and 0.817 on T2-weighted images or 0.749 and 0.744 on ADC maps images. CONCLUSION: Texture analysis of PI-RADS 3 lesions on T2-weighted and ADC maps images helps identifying prostate cancer. The good diagnostic performance of the combination of multiple radiomic features for the diagnosis of prostate cancer may help predicting lesions where aggressive management may be warranted.
Authors: Albert Comelli; Samuel Bignardi; Alessandro Stefano; Giorgio Russo; Maria Gabriella Sabini; Massimo Ippolito; Anthony Yezzi Journal: Comput Biol Med Date: 2020-03-16 Impact factor: 4.589
Authors: Valentina Brancato; Marco Aiello; Luca Basso; Serena Monti; Luigi Palumbo; Giuseppe Di Costanzo; Marco Salvatore; Alfonso Ragozzino; Carlo Cavaliere Journal: Sci Rep Date: 2021-01-12 Impact factor: 4.379
Authors: Anna Damascelli; Francesca Gallivanone; Giulia Cristel; Claudia Cava; Matteo Interlenghi; Antonio Esposito; Giorgio Brembilla; Alberto Briganti; Francesco Montorsi; Isabella Castiglioni; Francesco De Cobelli Journal: Diagnostics (Basel) Date: 2021-03-26
Authors: Tao Peng; JianMing Xiao; Lin Li; BingJie Pu; XiangKe Niu; XiaoHui Zeng; ZongYong Wang; ChaoBang Gao; Ci Li; Lin Chen; Jin Yang Journal: Int J Comput Assist Radiol Surg Date: 2021-10-22 Impact factor: 2.924
Authors: Sarah M Ayyad; Mohamed A Badawy; Mohamed Shehata; Ahmed Alksas; Ali Mahmoud; Mohamed Abou El-Ghar; Mohammed Ghazal; Moumen El-Melegy; Nahla B Abdel-Hamid; Labib M Labib; H Arafat Ali; Ayman El-Baz Journal: Sensors (Basel) Date: 2022-02-26 Impact factor: 3.576