Maarten de Rooij
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maarten de Rooij has a total of 442 co-authors. Here are the top co-authors by number of shared publications:
- Henkjan Huisman
Radboud University Medical Center, Radboud Institute for Health Sciences, Nijmegen
8 shared publications - Joeran Sander Bosma
Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
6 shared publications - Bram van Ginneken
Radboud University Medical Center
5 shared publications - Derya Yakar
Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands
5 shared publications Jelle O. Barentsz
Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
5 shared publications- Anindo Saha
Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands
4 shared publications
Latest Publications
- 1 October 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 321 (1)
Artificial Intelligence for Prostate Cancer Detection and Screening on MRI in Global Populations: The SCARLET-1 Study
In this study of 22,445 prostate MRI examinations from 22 countries, an AI system’s performance was comparable to radiology readings for prostate cancer detection in external diagnostic and screening datasets.
- 1 October 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 321 (1)
Artificial Intelligence for Prostate Cancer Detection and Screening on MRI in Global Populations: The SCARLET-1 Study
In this study of 22,445 prostate MRI examinations from 22 countries, an AI system’s performance was comparable to radiology readings for prostate cancer detection in external diagnostic and screening datasets.
- Open Access
- 28 September 2026
- Published by Elsevier in Diagnostic and Interventional Imaging
Inter-reader variability for quality assessment of synthetically degraded prostate MR images aligned with PIQUAL version 2
- 28 September 2026
- Published by Elsevier in Diagnostic and Interventional Imaging
Open AccessInter-reader variability for quality assessment of synthetically degraded prostate MR images aligned with PIQUAL version 2
- Open Access
- 18 September 2026
- Published by Springer Nature in European Radiology
- p. 1-13
Current status and future directions of AI in prostate cancer detection on MRI: a special report from the ESUR prostate MRI working group authors
This report from the ESUR Prostate MRI Working Group assesses the current role of artificial intelligence (AI) in MRI-based detection of prostate cancer. While deep learning tools demonstrate high technical accuracy, the report emphasizes a significant gap between research achievements and actual clinical application. Key statements include promoting a “human-in-the-loop” approach, where AI supports rather than replaces radiological expertise, to reduce risks such as automation bias and legal liability. There is an urgent need for prospective validation across multiple vendors and for implementing post-market surveillance to monitor algorithmic drift. Finally, the group identified research priorities focused on cost-effectiveness, transparency via explainable AI, and addressing the unique challenges of deploying these tools in population-based screening programs. Key Points: Question What challenges hinder the clinical adoption of AI-based medical devices for prostate cancer detection? Findings Major obstacles include insufficient real-world validation, complex dynamics of human-AI interactions that require a human-in-the-loop approach, and the need for ongoing post-market surveillance for oncologic safety . Clinical relevance This report highlights the gap between AI’s research promise and clinical readiness. It underscores the need for localvalidation, post-market surveillance, and adequate user training as AI tools become incorporated into diagnostic prostate MRI workflows .
- 18 September 2026
- Published by Springer Nature in European Radiology
- p. 1-13
Open AccessCurrent status and future directions of AI in prostate cancer detection on MRI: a special report from the ESUR prostate MRI working group authors
This report from the ESUR Prostate MRI Working Group assesses the current role of artificial intelligence (AI) in MRI-based detection of prostate cancer. While deep learning tools demonstrate high technical accuracy, the report emphasizes a significant gap between research achievements and actual clinical application. Key statements include promoting a “human-in-the-loop” approach, where AI supports rather than replaces radiological expertise, to reduce risks such as automation bias and legal liability. There is an urgent need for prospective validation across multiple vendors and for implementing post-market surveillance to monitor algorithmic drift. Finally, the group identified research priorities focused on cost-effectiveness, transparency via explainable AI, and addressing the unique challenges of deploying these tools in population-based screening programs. Key Points: Question What challenges hinder the clinical adoption of AI-based medical devices for prostate cancer detection? Findings Major obstacles include insufficient real-world validation, complex dynamics of human-AI interactions that require a human-in-the-loop approach, and the need for ongoing post-market surveillance for oncologic safety . Clinical relevance This report highlights the gap between AI’s research promise and clinical readiness. It underscores the need for localvalidation, post-market surveillance, and adequate user training as AI tools become incorporated into diagnostic prostate MRI workflows .
- 1 August 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 320 (2)
Diagnostically Calibrated AI Image Quality Framework Applied to Prostate Cancer Detection at MRI
Deep learning framework-derived image quality thresholds progressively excluding low-quality MRI scans correlated with improved diagnostic performance of an artificial intelligence model and radiologist accuracy in detecting clinically significant prostate cancer.
- 1 August 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 320 (2)
Diagnostically Calibrated AI Image Quality Framework Applied to Prostate Cancer Detection at MRI
Deep learning framework-derived image quality thresholds progressively excluding low-quality MRI scans correlated with improved diagnostic performance of an artificial intelligence model and radiologist accuracy in detecting clinically significant prostate cancer.
- Open Access
- 1 July 2026
- Published by Oxford University Press (OUP) in Radiology Advances
- Vol. 3 (5)
Multicenter AI-versus Expert-Assisted RECIST Target Lesion Measurements in Follow-Up Body CT of Cancer Patients
Background: Manual lesion measurements remain the standard for assessing oncologic treatment response, despite being time-consuming and prone to substantial inter-reader variability, which may lead to inconsistent response classification and subsequent variability in treatment decisions. Purpose: To evaluate the impact of an artificial intelligence (AI) system for assisted lesion measurement on reading time and measurement consistency in follow-up CT examinations using the Response Evaluation Criteria in Solid Tumors (RECIST 1.1). Methods and Materials: In this retrospective reader study, follow-up chest-abdomen-pelvis CT examinations from 212 oncology patients collected at two Dutch hospitals were assessed by 23 readers (15 radiologists, 8 residents) recruited from 11 international institutions under three conditions: unassisted, AI-assisted, and expert-assisted (using a prior radiologist’s unassisted measurement). To prevent bias related to the source of the measurements, readers were informed that all support was AI-derived. Primary outcomes were reading time to completion and inter-observer measurement variability. For each outcome, a Bayesian generalized linear mixed model was used to analyze the results. Results: AI assistance significantly reduced per-patient reading time versus unassisted reading (-36.0 s; 95% CI: -53.0, -22.1). At the lesion level, it was associated with a small increase in variability relative to the expert-derived reference standard (1.32 mm; 95% CI: 0.83, 1.91). At the patient level, AI assistance did not meaningfully affect change in the sum of longest diameters (SLD; -0.38 mm; 95% CI: -1.57, 0.72), but increased RECIST outcome agreement by 7.7% (95% CI: 2.8, 12.7) compared with unassisted reading. Expert-assisted reading yielded even higher inter-reader agreement (13.3%; 95% CI: 8.6, 18.1). Conclusion: AI assistance reduced reading time and improved patient-level RECIST agreement, despite a small increase in lesion-level measurement variability. These findings suggest that AI-assisted RECIST assessment may improve workflow and response classification consistency, while also providing a benchmark from expert-assisted reading for future AI development.
- 1 July 2026
- Published by Oxford University Press (OUP) in Radiology Advances
- Vol. 3 (5)
Open AccessMulticenter AI-versus Expert-Assisted RECIST Target Lesion Measurements in Follow-Up Body CT of Cancer Patients
Background: Manual lesion measurements remain the standard for assessing oncologic treatment response, despite being time-consuming and prone to substantial inter-reader variability, which may lead to inconsistent response classification and subsequent variability in treatment decisions. Purpose: To evaluate the impact of an artificial intelligence (AI) system for assisted lesion measurement on reading time and measurement consistency in follow-up CT examinations using the Response Evaluation Criteria in Solid Tumors (RECIST 1.1). Methods and Materials: In this retrospective reader study, follow-up chest-abdomen-pelvis CT examinations from 212 oncology patients collected at two Dutch hospitals were assessed by 23 readers (15 radiologists, 8 residents) recruited from 11 international institutions under three conditions: unassisted, AI-assisted, and expert-assisted (using a prior radiologist’s unassisted measurement). To prevent bias related to the source of the measurements, readers were informed that all support was AI-derived. Primary outcomes were reading time to completion and inter-observer measurement variability. For each outcome, a Bayesian generalized linear mixed model was used to analyze the results. Results: AI assistance significantly reduced per-patient reading time versus unassisted reading (-36.0 s; 95% CI: -53.0, -22.1). At the lesion level, it was associated with a small increase in variability relative to the expert-derived reference standard (1.32 mm; 95% CI: 0.83, 1.91). At the patient level, AI assistance did not meaningfully affect change in the sum of longest diameters (SLD; -0.38 mm; 95% CI: -1.57, 0.72), but increased RECIST outcome agreement by 7.7% (95% CI: 2.8, 12.7) compared with unassisted reading. Expert-assisted reading yielded even higher inter-reader agreement (13.3%; 95% CI: 8.6, 18.1). Conclusion: AI assistance reduced reading time and improved patient-level RECIST agreement, despite a small increase in lesion-level measurement variability. These findings suggest that AI-assisted RECIST assessment may improve workflow and response classification consistency, while also providing a benchmark from expert-assisted reading for future AI development.
- Open Access
- 27 June 2026
- Published by Springer Nature in Abdominal Radiology
- p. 1-13
Shifting from black box decisions to informed decision-making in using artificial intelligence to analyze prostate MRI
Prostate magnetic resonance imaging (MRI) is central to the detection and localization of clinically significant prostate cancers. However, its interpretation is time-consuming and variable. Artificial intelligence (AI) tools for prostate MRI are rapidly emerging, with their performance approaching that of expert readers in select settings, although robust external validation in unselected real-world cohorts remains incomplete. Moreover, many deep learning models are limited in terms of transparency; that is, the “black box” problem hinders trust, safe deployment, and regulatory acceptance. This review summarizes the core concepts of interpretability and explainable artificial intelligence (XAI), highlights commonly used approaches to explain the output of AI models, and discusses how the lack of transparency hinders clinical deployment and how this can be addressed using standardized reporting frameworks. Ultimately, the purpose of this review is to draw attention to the pressing need for XAI and to spark interest and awareness of how standardized frameworks may help us to shift from “black box” decisions to informed decision-making in clinical practice.
- 27 June 2026
- Published by Springer Nature in Abdominal Radiology
- p. 1-13
Open AccessShifting from black box decisions to informed decision-making in using artificial intelligence to analyze prostate MRI
Prostate magnetic resonance imaging (MRI) is central to the detection and localization of clinically significant prostate cancers. However, its interpretation is time-consuming and variable. Artificial intelligence (AI) tools for prostate MRI are rapidly emerging, with their performance approaching that of expert readers in select settings, although robust external validation in unselected real-world cohorts remains incomplete. Moreover, many deep learning models are limited in terms of transparency; that is, the “black box” problem hinders trust, safe deployment, and regulatory acceptance. This review summarizes the core concepts of interpretability and explainable artificial intelligence (XAI), highlights commonly used approaches to explain the output of AI models, and discusses how the lack of transparency hinders clinical deployment and how this can be addressed using standardized reporting frameworks. Ultimately, the purpose of this review is to draw attention to the pressing need for XAI and to spark interest and awareness of how standardized frameworks may help us to shift from “black box” decisions to informed decision-making in clinical practice.
- Open Access
- 12 March 2026
- Published by Springer Nature
- p. 465
Abstract: Annotation-efficient 3D Body Composition Segmentation
- 12 March 2026
- Published by Springer Nature
- p. 465
Open AccessAbstract: Annotation-efficient 3D Body Composition Segmentation
- Open Access
- 18 January 2026
- Published by Oxford University Press (OUP) in BJR|Open
- Vol. 8 (1)
Prostate imaging scoring systems: indications, interpretation, and clinical impact
Prostate imaging, and especially multiparametric magnetic resonance imaging (mpMRI), has become central to the diagnosis, risk stratification, treatment planning, and follow-up of prostate cancer. Its widespread adoption has driven the development of structured imaging scoring systems designed to standardize acquisition, interpretation, and reporting across diverse clinical scenarios. This narrative review summarizes the principles, clinical applications, strengths, and limitations of the main prostate imaging scoring systems currently in use. These include PI-RADS for cancer detection, PRECISE for monitoring patients on active surveillance, PI-RR for post-treatment local recurrence, PI-FAB and TARGET for assessment after focal therapy, Node-RADS for lymph node evaluation, MET-RADS-P for whole-body MRI assessment of metastatic disease, PSMA-RADS for molecular imaging interpretation, and PI-QUAL for prostate MRI quality assurance. Collectively, these systems provide a shared diagnostic language that improves inter-reader agreement, supports evidence-based decision-making, and facilitates multidisciplinary care. Despite their proven clinical impact, challenges remain, including inter-reader variability, heterogeneous MRI quality, limited access to advanced imaging, and incomplete validation of emerging tools. Future directions include the incorporation of artificial intelligence, hybrid PET/MRI, and combined clinical-genomic biomarkers, together with prospective multicenter validation, to advance precision, reproducibility, and personalization in prostate cancer imaging.
- 18 January 2026
- Published by Oxford University Press (OUP) in BJR|Open
- Vol. 8 (1)
Open AccessProstate imaging scoring systems: indications, interpretation, and clinical impact
Prostate imaging, and especially multiparametric magnetic resonance imaging (mpMRI), has become central to the diagnosis, risk stratification, treatment planning, and follow-up of prostate cancer. Its widespread adoption has driven the development of structured imaging scoring systems designed to standardize acquisition, interpretation, and reporting across diverse clinical scenarios. This narrative review summarizes the principles, clinical applications, strengths, and limitations of the main prostate imaging scoring systems currently in use. These include PI-RADS for cancer detection, PRECISE for monitoring patients on active surveillance, PI-RR for post-treatment local recurrence, PI-FAB and TARGET for assessment after focal therapy, Node-RADS for lymph node evaluation, MET-RADS-P for whole-body MRI assessment of metastatic disease, PSMA-RADS for molecular imaging interpretation, and PI-QUAL for prostate MRI quality assurance. Collectively, these systems provide a shared diagnostic language that improves inter-reader agreement, supports evidence-based decision-making, and facilitates multidisciplinary care. Despite their proven clinical impact, challenges remain, including inter-reader variability, heterogeneous MRI quality, limited access to advanced imaging, and incomplete validation of emerging tools. Future directions include the incorporation of artificial intelligence, hybrid PET/MRI, and combined clinical-genomic biomarkers, together with prospective multicenter validation, to advance precision, reproducibility, and personalization in prostate cancer imaging.
- Open Access
- 14 January 2026
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 61 (3) , 185-192
The Current and Future Role of MRI and PSMA-PET/CT in Diagnosing Oligometastatic Prostate Cancer
This review describes the role of different imaging techniques in the initial diagnosis and staging of prostate cancer (PCa), with a focus on oligometastatic disease. Men with an elevated prostate-specific antigen level and/or with an abnormal digital rectal exam are subject to a multiparametric MRI examination to identify a possible lesion in the prostate. In patients with high-risk or intermediate-risk disease with an unfavorable prognosis, additional imaging with prostate-specific membrane antigen (PSMA) PET/CT is offered to assess the presence of local nodal or extensive metastatic disease. Oligometastatic disease, which is PCa with a limited number of 1 to 5 metastatic deposits, possibly provides a time window to delay the course of the disease, or perhaps even still cure the patient. To detect these first metastases in small or normal-sized lymph nodes, the most sensitive, noninvasive imaging method should be selected. In this review, we summarize the current use of MRI and PSMA-PET/CT and discuss the latest developments in these techniques that could further improve initial diagnosis and staging of oligometastatic PCa.
- 14 January 2026
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 61 (3) , 185-192
Open AccessThe Current and Future Role of MRI and PSMA-PET/CT in Diagnosing Oligometastatic Prostate Cancer
This review describes the role of different imaging techniques in the initial diagnosis and staging of prostate cancer (PCa), with a focus on oligometastatic disease. Men with an elevated prostate-specific antigen level and/or with an abnormal digital rectal exam are subject to a multiparametric MRI examination to identify a possible lesion in the prostate. In patients with high-risk or intermediate-risk disease with an unfavorable prognosis, additional imaging with prostate-specific membrane antigen (PSMA) PET/CT is offered to assess the presence of local nodal or extensive metastatic disease. Oligometastatic disease, which is PCa with a limited number of 1 to 5 metastatic deposits, possibly provides a time window to delay the course of the disease, or perhaps even still cure the patient. To detect these first metastases in small or normal-sized lymph nodes, the most sensitive, noninvasive imaging method should be selected. In this review, we summarize the current use of MRI and PSMA-PET/CT and discuss the latest developments in these techniques that could further improve initial diagnosis and staging of oligometastatic PCa.
- Open Access
- 21 November 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 199, 111321
Scalable Clinical Annotation with Location Evidence (SCALE)
- 21 November 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 199, 111321
Open AccessScalable Clinical Annotation with Location Evidence (SCALE)