Cargando…

Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer

BACKGROUND: around one third of clinically significant prostate cancer (CsPCa) foci are reported to be MRI non-visible (MRI─). OBJECTIVE: To quantify the differences between MR visible (MRI+) and MRI(─) CsPCa using intra- and peri-lesional radiomic features on bi-parametric MRI (bpMRI). METHODS: Thi...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Lin, Shiradkar, Rakesh, Tirumani, Sree Harsha, Bittencourt, Leonardo Kayat, Fu, Pingfu, Mahran, Amr, Buzzy, Christina, Stricker, Phillip D., Rastinehad, Ardeshir R., Magi-Galluzzi, Cristina, Ponsky, Lee, Klein, Eric, Purysko, Andrei S., Madabhushi, Anant
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10311200/
https://www.ncbi.nlm.nih.gov/pubmed/37396490
http://dx.doi.org/10.1016/j.ejro.2023.100496
_version_ 1785066691750789120
author Li, Lin
Shiradkar, Rakesh
Tirumani, Sree Harsha
Bittencourt, Leonardo Kayat
Fu, Pingfu
Mahran, Amr
Buzzy, Christina
Stricker, Phillip D.
Rastinehad, Ardeshir R.
Magi-Galluzzi, Cristina
Ponsky, Lee
Klein, Eric
Purysko, Andrei S.
Madabhushi, Anant
author_facet Li, Lin
Shiradkar, Rakesh
Tirumani, Sree Harsha
Bittencourt, Leonardo Kayat
Fu, Pingfu
Mahran, Amr
Buzzy, Christina
Stricker, Phillip D.
Rastinehad, Ardeshir R.
Magi-Galluzzi, Cristina
Ponsky, Lee
Klein, Eric
Purysko, Andrei S.
Madabhushi, Anant
author_sort Li, Lin
collection PubMed
description BACKGROUND: around one third of clinically significant prostate cancer (CsPCa) foci are reported to be MRI non-visible (MRI─). OBJECTIVE: To quantify the differences between MR visible (MRI+) and MRI(─) CsPCa using intra- and peri-lesional radiomic features on bi-parametric MRI (bpMRI). METHODS: This retrospective and multi-institutional study comprised 164 patients with pre-biopsy 3T prostate multi-parametric MRI from 2014 to 2017. The MRI(─) CsPCa referred to lesions with PI-RADS v2 score < 3 but ISUP grade group > 1. Three experienced radiologists were involved in annotating lesions and PI-RADS assignment. The validation set (D(v)) comprised 52 patients from a single institution, the remaining 112 patients were used for training (D(t)). 200 radiomic features were extracted from intra-lesional and peri-lesional regions on bpMRI. Logistic regression with least absolute shrinkage and selection operator (LASSO) and 10-fold cross-validation was applied on D(t) to identify radiomic features associated with MRI(─) and MRI(+) CsPCa to generate corresponding risk scores R(MRI─) and R(MRI+). R(bpMRI) was further generated by integrating R(MRI─) and R(MRI+). Statistical significance was determined using the Wilcoxon signed-rank test. RESULTS: Both intra-lesional and peri-lesional bpMRI Haralick and CoLlAGe radiomic features were significantly associated with MRI(─) CsPCa (p < 0.05). Intra-lesional ADC Haralick and CoLlAGe radiomic features were significantly different among MRI(─) and MRI(+) CsPCa (p < 0.05). R(bpMRI) yielded the highest AUC of 0.82 (95 % CI 0.72–0.91) compared to AUCs of R(MRI+) 0.76 (95 % CI 0.63–0.89), and PI-RADS 0.58 (95 % CI 0.50–0.72) on D(v). R(bpMRI) correctly reclassified 10 out of 14 MRI(─) CsPCa on D(v). CONCLUSION: Our preliminary results demonstrated that both intra-lesional and peri-lesional bpMRI radiomic features were significantly associated with MRI(─) CsPCa. These features could assist in CsPCa identification on bpMRI.
format Online
Article
Text
id pubmed-10311200
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-103112002023-07-01 Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer Li, Lin Shiradkar, Rakesh Tirumani, Sree Harsha Bittencourt, Leonardo Kayat Fu, Pingfu Mahran, Amr Buzzy, Christina Stricker, Phillip D. Rastinehad, Ardeshir R. Magi-Galluzzi, Cristina Ponsky, Lee Klein, Eric Purysko, Andrei S. Madabhushi, Anant Eur J Radiol Open Article BACKGROUND: around one third of clinically significant prostate cancer (CsPCa) foci are reported to be MRI non-visible (MRI─). OBJECTIVE: To quantify the differences between MR visible (MRI+) and MRI(─) CsPCa using intra- and peri-lesional radiomic features on bi-parametric MRI (bpMRI). METHODS: This retrospective and multi-institutional study comprised 164 patients with pre-biopsy 3T prostate multi-parametric MRI from 2014 to 2017. The MRI(─) CsPCa referred to lesions with PI-RADS v2 score < 3 but ISUP grade group > 1. Three experienced radiologists were involved in annotating lesions and PI-RADS assignment. The validation set (D(v)) comprised 52 patients from a single institution, the remaining 112 patients were used for training (D(t)). 200 radiomic features were extracted from intra-lesional and peri-lesional regions on bpMRI. Logistic regression with least absolute shrinkage and selection operator (LASSO) and 10-fold cross-validation was applied on D(t) to identify radiomic features associated with MRI(─) and MRI(+) CsPCa to generate corresponding risk scores R(MRI─) and R(MRI+). R(bpMRI) was further generated by integrating R(MRI─) and R(MRI+). Statistical significance was determined using the Wilcoxon signed-rank test. RESULTS: Both intra-lesional and peri-lesional bpMRI Haralick and CoLlAGe radiomic features were significantly associated with MRI(─) CsPCa (p < 0.05). Intra-lesional ADC Haralick and CoLlAGe radiomic features were significantly different among MRI(─) and MRI(+) CsPCa (p < 0.05). R(bpMRI) yielded the highest AUC of 0.82 (95 % CI 0.72–0.91) compared to AUCs of R(MRI+) 0.76 (95 % CI 0.63–0.89), and PI-RADS 0.58 (95 % CI 0.50–0.72) on D(v). R(bpMRI) correctly reclassified 10 out of 14 MRI(─) CsPCa on D(v). CONCLUSION: Our preliminary results demonstrated that both intra-lesional and peri-lesional bpMRI radiomic features were significantly associated with MRI(─) CsPCa. These features could assist in CsPCa identification on bpMRI. Elsevier 2023-06-13 /pmc/articles/PMC10311200/ /pubmed/37396490 http://dx.doi.org/10.1016/j.ejro.2023.100496 Text en © 2023 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Li, Lin
Shiradkar, Rakesh
Tirumani, Sree Harsha
Bittencourt, Leonardo Kayat
Fu, Pingfu
Mahran, Amr
Buzzy, Christina
Stricker, Phillip D.
Rastinehad, Ardeshir R.
Magi-Galluzzi, Cristina
Ponsky, Lee
Klein, Eric
Purysko, Andrei S.
Madabhushi, Anant
Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer
title Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer
title_full Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer
title_fullStr Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer
title_full_unstemmed Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer
title_short Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer
title_sort novel radiomic analysis on bi-parametric mri for characterizing differences between mr non-visible and visible clinically significant prostate cancer
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10311200/
https://www.ncbi.nlm.nih.gov/pubmed/37396490
http://dx.doi.org/10.1016/j.ejro.2023.100496
work_keys_str_mv AT lilin novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT shiradkarrakesh novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT tirumanisreeharsha novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT bittencourtleonardokayat novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT fupingfu novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT mahranamr novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT buzzychristina novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT strickerphillipd novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT rastinehadardeshirr novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT magigalluzzicristina novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT ponskylee novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT kleineric novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT puryskoandreis novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer
AT madabhushianant novelradiomicanalysisonbiparametricmriforcharacterizingdifferencesbetweenmrnonvisibleandvisibleclinicallysignificantprostatecancer