Improving risk stratification of PI-RADS 3 + 1 lesions of the peripheral zone: expert lexicon of terms, multi-reader performance and contribution of artificial intelligence
Background: According to PI-RADS v2.1, peripheral PI-RADS 3 lesions are upgraded to PI-RADS 4 if dynamic contrast-enhanced MRI is positive (3+1 lesions), however those lesions are radiologically challenging. We aimed to define criteria by expert consensus and test applicability by other radiologists...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
19 August 2025
|
| In: |
Cancer imaging
Year: 2025, Jahrgang: 25, Pages: 1-14 |
| ISSN: | 1470-7330 |
| DOI: | 10.1186/s40644-025-00916-7 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s40644-025-00916-7
|
| Verfasserangaben: | Philip A. Glemser, Nils Netzer, Christian H. Ziener, Markus Wilhelm, Thomas Hielscher, Kevin Sun Zhang, Magdalena Görtz, Viktoria Schütz, Albrecht Stenzinger, Markus Hohenfellner, Heinz-Peter Schlemmer and David Bonekamp |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1948726998 | ||
| 003 | DE-627 | ||
| 005 | 20260114122119.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 260114s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s40644-025-00916-7 |2 doi | |
| 035 | |a (DE-627)1948726998 | ||
| 035 | |a (DE-599)KXP1948726998 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Glemser, Philip |e VerfasserIn |0 (DE-588)1029777756 |0 (DE-627)734092520 |0 (DE-576)377624667 |4 aut | |
| 245 | 1 | 0 | |a Improving risk stratification of PI-RADS 3 + 1 lesions of the peripheral zone |b expert lexicon of terms, multi-reader performance and contribution of artificial intelligence |c Philip A. Glemser, Nils Netzer, Christian H. Ziener, Markus Wilhelm, Thomas Hielscher, Kevin Sun Zhang, Magdalena Görtz, Viktoria Schütz, Albrecht Stenzinger, Markus Hohenfellner, Heinz-Peter Schlemmer and David Bonekamp |
| 246 | 3 | 0 | |a three one |
| 264 | 1 | |c 19 August 2025 | |
| 300 | |b Illustrationen | ||
| 300 | |a 14 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Veröffentlicht: 19. August 2025 | ||
| 500 | |a Gesehen am 14.01.2026 | ||
| 520 | |a Background: According to PI-RADS v2.1, peripheral PI-RADS 3 lesions are upgraded to PI-RADS 4 if dynamic contrast-enhanced MRI is positive (3+1 lesions), however those lesions are radiologically challenging. We aimed to define criteria by expert consensus and test applicability by other radiologists for sPC prediction of PI-RADS 3+1 lesions and determine their value in integrated regression models. Methods: From consecutive 3 Tesla MR examinations performed between 08/2016 to 12/2018 we identified 85 MRI examinations from 83 patients with a total of 94 PI-RADS 3+1 lesions in the official clinical report. Lesions were retrospectively assessed by expert consensus with construction of a newly devised feature catalogue which was utilized subsequently by two additional radiologists specialized in prostate MRI for independent lesion assessment. With reference to extended fused targeted and systematic TRUS/MRI-biopsy histopathological correlation, relevant catalogue features were identified by univariate analysis and put into context to typically available clinical features and automated AI image assessment utilizing lasso-penalized logistic regression models, also focusing on the contribution of DCE imaging (feature-based, bi- and multiparametric AI-enhanced and solely bi- and multiparametric AI-driven). Results: The feature catalog enabled image-based lesional risk stratification for all readers. Expert consensus provided 3 significant features in univariate analysis (adj. p-value <0.05; most relevant feature T2w configuration: “irregular/microlobulated/spiculated”, OR 9.0 (95%CI 2.3-44.3); adj. p-value: 0.016). These remained after lasso penalized regression based feature reduction, while the only selected clinical feature was prostate volume (OR<1), enabling nomogram construction. While DCE-derived consensus features did not enhance model performance (bootstrapped AUC), there was a trend for increased performance by including multiparametric AI, but not biparametric AI into models, both for combined and AI-only models. Conclusions: PI-RADS 3+1 lesions can be risk-stratified using lexicon terms and a key feature nomogram. AI potentially benefits more from DCE imaging than experienced prostate radiologists. | ||
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Extended fused biopsy | |
| 650 | 4 | |a Lexicon terms | |
| 650 | 4 | |a Prostate cancer | |
| 650 | 4 | |a Risk stratification | |
| 700 | 1 | |a Netzer, Nils |e VerfasserIn |0 (DE-588)1254537902 |0 (DE-627)1797012975 |4 aut | |
| 700 | 1 | |a Ziener, Christian H. |d 1978- |e VerfasserIn |0 (DE-588)137982755 |0 (DE-627)59885309X |0 (DE-576)306117355 |4 aut | |
| 700 | 1 | |a Wilhelm, Markus |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hielscher, Thomas |e VerfasserIn |0 (DE-588)1159594791 |0 (DE-627)1022977768 |0 (DE-576)50506068X |4 aut | |
| 700 | 1 | |a Zhang, Kevin Sun |e VerfasserIn |0 (DE-588)1207581461 |0 (DE-627)1694082342 |4 aut | |
| 700 | 1 | |a Görtz, Magdalena |d 1992- |e VerfasserIn |0 (DE-588)1166813657 |0 (DE-627)1030681392 |0 (DE-576)510916600 |4 aut | |
| 700 | 1 | |a Schütz, Viktoria |e VerfasserIn |0 (DE-588)1183860021 |0 (DE-627)1663385335 |4 aut | |
| 700 | 1 | |a Stenzinger, Albrecht |e VerfasserIn |0 (DE-588)139606106 |0 (DE-627)703395238 |0 (DE-576)312432755 |4 aut | |
| 700 | 1 | |a Hohenfellner, Markus |d 1958- |e VerfasserIn |0 (DE-588)133862518 |0 (DE-627)557857988 |0 (DE-576)300155263 |4 aut | |
| 700 | 1 | |a Schlemmer, Heinz-Peter |d 1961- |e VerfasserIn |0 (DE-588)1025559967 |0 (DE-627)722927142 |0 (DE-576)17334805X |4 aut | |
| 700 | 1 | |a Bonekamp, David |d 1977- |e VerfasserIn |0 (DE-588)128868104 |0 (DE-627)383668581 |0 (DE-576)297371797 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Cancer imaging |d London : BioMed Central, 2000 |g 25(2025), Artikel-ID 102, Seite 1-14 |h Online-Ressource |w (DE-627)36374732X |w (DE-600)2104862-9 |w (DE-576)34726624X |x 1470-7330 |7 nnas |a Improving risk stratification of PI-RADS 3 + 1 lesions of the peripheral zone expert lexicon of terms, multi-reader performance and contribution of artificial intelligence |
| 773 | 1 | 8 | |g volume:25 |g year:2025 |g elocationid:102 |g pages:1-14 |g extent:14 |a Improving risk stratification of PI-RADS 3 + 1 lesions of the peripheral zone expert lexicon of terms, multi-reader performance and contribution of artificial intelligence |
| 856 | 4 | 0 | |u https://doi.org/10.1186/s40644-025-00916-7 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |7 0 |
| 951 | |a AR | ||
| 992 | |a 20260114 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 128868104 |a Bonekamp, David |m 128868104:Bonekamp, David |d 50000 |e 50000PB128868104 |k 0/50000/ |p 12 |y j | ||
| 998 | |g 1025559967 |a Schlemmer, Heinz-Peter |m 1025559967:Schlemmer, Heinz-Peter |d 50000 |e 50000PS1025559967 |k 0/50000/ |p 11 | ||
| 998 | |g 133862518 |a Hohenfellner, Markus |m 133862518:Hohenfellner, Markus |d 910000 |d 910200 |e 910000PH133862518 |e 910200PH133862518 |k 0/910000/ |k 1/910000/910200/ |p 10 | ||
| 998 | |g 139606106 |a Stenzinger, Albrecht |m 139606106:Stenzinger, Albrecht |d 910000 |d 912000 |e 910000PS139606106 |e 912000PS139606106 |k 0/910000/ |k 1/910000/912000/ |p 9 | ||
| 998 | |g 1183860021 |a Schütz, Viktoria |m 1183860021:Schütz, Viktoria |d 910000 |d 910200 |e 910000PS1183860021 |e 910200PS1183860021 |k 0/910000/ |k 1/910000/910200/ |p 8 | ||
| 998 | |g 1166813657 |a Görtz, Magdalena |m 1166813657:Görtz, Magdalena |d 910000 |d 910200 |d 50000 |e 910000PG1166813657 |e 910200PG1166813657 |e 50000PG1166813657 |k 0/910000/ |k 1/910000/910200/ |k 0/50000/ |p 7 | ||
| 998 | |g 1207581461 |a Zhang, Kevin Sun |m 1207581461:Zhang, Kevin Sun |d 50000 |e 50000PZ1207581461 |k 0/50000/ |p 6 | ||
| 998 | |g 1159594791 |a Hielscher, Thomas |m 1159594791:Hielscher, Thomas |d 50000 |e 50000PH1159594791 |k 0/50000/ |p 5 | ||
| 998 | |g 137982755 |a Ziener, Christian H. |m 137982755:Ziener, Christian H. |d 50000 |e 50000PZ137982755 |k 0/50000/ |p 3 | ||
| 998 | |g 1254537902 |a Netzer, Nils |m 1254537902:Netzer, Nils |d 910000 |d 911400 |d 50000 |e 910000PN1254537902 |e 911400PN1254537902 |e 50000PN1254537902 |k 0/910000/ |k 1/910000/911400/ |k 0/50000/ |p 2 | ||
| 998 | |g 1029777756 |a Glemser, Philip |m 1029777756:Glemser, Philip |d 50000 |e 50000PG1029777756 |k 0/50000/ |p 1 |x j | ||
| 999 | |a KXP-PPN1948726998 |e 4847833082 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"id":{"doi":["10.1186/s40644-025-00916-7"],"eki":["1948726998"]},"name":{"displayForm":["Philip A. Glemser, Nils Netzer, Christian H. Ziener, Markus Wilhelm, Thomas Hielscher, Kevin Sun Zhang, Magdalena Görtz, Viktoria Schütz, Albrecht Stenzinger, Markus Hohenfellner, Heinz-Peter Schlemmer and David Bonekamp"]},"physDesc":[{"extent":"14 S.","noteIll":"Illustrationen"}],"recId":"1948726998","note":["Veröffentlicht: 19. August 2025","Gesehen am 14.01.2026"],"language":["eng"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"title":[{"subtitle":"expert lexicon of terms, multi-reader performance and contribution of artificial intelligence","title_sort":"Improving risk stratification of PI-RADS 3 + 1 lesions of the peripheral zone","title":"Improving risk stratification of PI-RADS 3 + 1 lesions of the peripheral zone"}],"relHost":[{"origin":[{"dateIssuedKey":"2000","publisherPlace":"London ; Heidelberg ; New York, NY","dateIssuedDisp":"2000-","publisher":"BioMed Central ; BMC, part of Springer Nature"}],"pubHistory":["1.2000 -"],"id":{"issn":["1470-7330"],"eki":["36374732X"],"zdb":["2104862-9"]},"part":{"extent":"14","text":"25(2025), Artikel-ID 102, Seite 1-14","volume":"25","year":"2025","pages":"1-14"},"title":[{"subtitle":"the official publication of the International Cancer Imaging Society","title_sort":"Cancer imaging","title":"Cancer imaging"}],"language":["eng"],"type":{"bibl":"periodical","media":"Online-Ressource"},"note":["Gesehen am 20.03.23"],"recId":"36374732X","physDesc":[{"extent":"Online-Ressource"}],"disp":"Improving risk stratification of PI-RADS 3 + 1 lesions of the peripheral zone expert lexicon of terms, multi-reader performance and contribution of artificial intelligenceCancer imaging"}],"person":[{"display":"Glemser, Philip","given":"Philip","role":"aut","family":"Glemser"},{"family":"Netzer","role":"aut","given":"Nils","display":"Netzer, Nils"},{"display":"Ziener, Christian H.","given":"Christian H.","role":"aut","family":"Ziener"},{"family":"Wilhelm","role":"aut","given":"Markus","display":"Wilhelm, Markus"},{"family":"Hielscher","role":"aut","given":"Thomas","display":"Hielscher, Thomas"},{"given":"Kevin Sun","role":"aut","family":"Zhang","display":"Zhang, Kevin Sun"},{"role":"aut","given":"Magdalena","family":"Görtz","display":"Görtz, Magdalena"},{"family":"Schütz","given":"Viktoria","role":"aut","display":"Schütz, Viktoria"},{"display":"Stenzinger, Albrecht","role":"aut","given":"Albrecht","family":"Stenzinger"},{"given":"Markus","role":"aut","family":"Hohenfellner","display":"Hohenfellner, Markus"},{"role":"aut","given":"Heinz-Peter","family":"Schlemmer","display":"Schlemmer, Heinz-Peter"},{"role":"aut","given":"David","family":"Bonekamp","display":"Bonekamp, David"}],"origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"19 August 2025"}]} | ||
| SRT | |a GLEMSERPHIIMPROVINGR1920 | ||