Cross-attention fusion of biparametric MRI sequences with demographic and clinical variables for patient-level classification of clinically significant prostate cancer

Abstract Accurate patient-level risk stratification of clinically significant prostate cancer (csPCa) on biparametric MRI remains challenging, as most existing approaches require costly lesion-level annotations or have not been evaluated in large temporally separated cohorts. We developed and validated a multimodal deep learning framework combining T2-weighted (T2w), diffusion-weighted (DWI), and apparent diffusion coefficient (ADC) volumes with age, prostate-specific antigen (PSA), and PSA density (PSAD) for patient-level csPCa classification, trained without lesion-level annotations. The study included a retrospective development cohort of 3, 939 examinations and an independent temporal validation cohort comprising 1, 409 prospectively acquired examinations from 13 centers. The model employs three sequence-specific encoders with asymmetric cross-attention fusion and a two-stage transfer-learning strategy. Adding demographic and clinical variables consistently improved performance over MRI-only models, with PSAD emerging as the most informative complementary factor, primarily by improving specificity. The best-performing model—combining MRI, age, PSA, and PSAD with cross-attention—achieved a mean AUC of $$0.765\!\pm \!0.006$$ on the retrospective held-out test set and $$0.741\!\pm \!0.006$$ on the independent temporal validation cohort. Post hoc subgroup analyses suggested broadly stable rank-order discrimination (AUC) across most strata, though fixed-threshold sensitivity and specificity varied substantially, while Grad-CAM maps offered a qualitative indication of more frequent overlap with suspicious regions under cross-attention. These findings support PSAD-informed multimodal patient-level models as a viable tool for refined csPCa risk stratification on biparametric MRI, with potential to reduce false-positive classification of ISUP grade group 1 disease as clinically significant.

Authors

Publication Details

Journal
Scientific Reports
Published
2026-10-08
DOI
https://doi.org/10.1038/s41598-026-71998-x
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Cross-attention fusion of biparametric MRI sequences with demographic and clinical variables for patient-level classification of clinically significant prostate cancer

Jayashree Kalpathy-Cramer, Osuala Richard, Ali Devrim Karaosmanoğlu, Fırat Atak et al.
Scientific Reports
Radiomics and Machine Learning in Medical Imaging
article

Cross-attention fusion of biparametric MRI sequences with demographic and clinical variables for patient-level classification of clinically significant prostate cancer

Jayashree Kalpathy-Cramer, Osuala Richard, Ali Devrim Karaosmanoğlu, Fırat Atak, José Munuera Mora, Muşturay Karçaaltıncaba, Eugenia Mylona, Charalampos Kalantzopoulos, Oliver Díaz, Anindo Saha, Audrius Untanas, Giovanni Maimone, Jasper J. Twilt, Silvia Navarro, Simone Mazzetti, C Saillant, Simon Doran, Gianluca Carloni, Andrea Berti, Eva Pachetti, Maria Antonietta Pascali, Eleftherios Trivizakis, Zoi Giavri, Gloria Ribas, HenkJan J. Huisman, Nuno Rodrigues, Deniz Akata, Christos Pollalis, Vincenzo Mendola, Gracián García‐Martí, Nikolaos S. Tachos, Avtantil Dimitriadis, Giulio Del Corso, Theresa Henne, Joan Carles Vilanova, Daniele Regge, Giacomo Aringhieri, Ana Jiménez Pastor, Luis Martí‐Bonmatí, Sara Colantonio, Karim Lekadir, Danila Germanese, Lorenzo Tumminello, José Guilherme de Almeida, Grigorios Kalliatakis, Maarten de Rooij, Walter Hernández, Manolis Tsiknakis, Valentina Giannini, Mustafa Ozmen, Sharon Vit, Ana Carolina Rodrigues, Nikolaos Papanikolaou, Koh Dow-Mu, Jurgita Ušinskienė, Giovanni Cappello, Rūta Briedienė, Robby Emsley, João Correia, Leonor Cerdá-Alberich, Miguel Chambel, Kristina Slidevska, Katsaros Vasilis, Dimitrios Agraniotis, Sfakianakis Stelios, Dimitri Kessler, Emanuele Neri, Dimitrios Fotiadis, Dimitrios Zaridis, Georgiou Georgios, Kostas Marias, Manuel Marfil, Tiaan Jacobs, Valentina Napolitano, Varvara Kalokyri, Rodessa Marquez, Ana Castro Verde, Christopher Bridge, Ana Ribeiro, Jurgen Futterer
article en

Abstract

Abstract Accurate patient-level risk stratification of clinically significant prostate cancer (csPCa) on biparametric MRI remains challenging, as most existing approaches require costly lesion-level annotations or have not been evaluated in large temporally separated cohorts. We developed and validated a multimodal deep learning framework combining T2-weighted (T2w), diffusion-weighted (DWI), and apparent diffusion coefficient (ADC) volumes with age, prostate-specific antigen (PSA), and PSA density (PSAD) for patient-level csPCa classification, trained without lesion-level annotations. The study included a retrospective development cohort of 3, 939 examinations and an independent temporal validation cohort comprising 1, 409 prospectively acquired examinations from 13 centers. The model employs three sequence-specific encoders with asymmetric cross-attention fusion and a two-stage transfer-learning strategy. Adding demographic and clinical variables consistently improved performance over MRI-only models, with PSAD emerging as the most informative complementary factor, primarily by improving specificity. The best-performing model—combining MRI, age, PSA, and PSAD with cross-attention—achieved a mean AUC of $$0.765\!\pm \!0.006$$ on the retrospective held-out test set and $$0.741\!\pm \!0.006$$ on the independent temporal validation cohort. Post hoc subgroup analyses suggested broadly stable rank-order discrimination (AUC) across most strata, though fixed-threshold sensitivity and specificity varied substantially, while Grad-CAM maps offered a qualitative indication of more frequent overlap with suspicious regions under cross-attention. These findings support PSAD-informed multimodal patient-level models as a viable tool for refined csPCa risk stratification on biparametric MRI, with potential to reduce false-positive classification of ISUP grade group 1 disease as clinically significant.

Scientific Reports
Openalex Percentile: Top 13%
Radiomics and Machine Learning in Medical Imaging
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.