John J. Hermans
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
John J. Hermans has a total of 173 co-authors. Here are the top co-authors by number of shared publications:
- Cornelis Johannes Henricus Martinus van Laarhoven
Department of Surgery, Radboudumc, Geert Grooteplein 10 (route 618), Nijmegen, 6525 GA, The Netherlands, 31 0243668086
7 shared publications - Geke Litjens
Department of Medical Imaging, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
6 shared publications - Henkjan Huisman
Radboud University Medical Center, Radboud Institute for Health Sciences, Nijmegen
5 shared publications - Erwin J. M. van Geenen
Department of Gastroenterology and Hepatology, Radboud University Medical Center, Nijmegen, Netherlands
4 shared publications - Lodewijk Adriaan Anton Brosens
Department of Pathology, University Medical Center Utrecht, Utrecht, The Netherlands
4 shared publications - Mathias Prokop
Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands
4 shared publications
Latest Publications
- Open Access
- 14 October 2026
- Published by Springer Nature in Research Square
Towards guideline-grounded clinical decision-making: a multi-scale study of retrieval augmented generation based large language model agents
Large language models (LLMs) show promise for clinical decision support but are limited by opaque knowledge and inconsistent decision-making. Retrieval-Augmented Generation (RAG) mitigates these issues by injecting verifiable passages from a curated corpus at inference time. Using 2,400 real patient pathways from the MIMIC-CDM dataset, we evaluated RAG configurations over information gathering, diagnostic accuracy, treatment recommendations and guideline retrieval, identifying key factors for integrating RAG into clinical AI-agents. Across eight general and medical LLMs spanning 1B to 70B parameters, RAG consistently increased mean diagnostic accuracy from 55.64% to 64.29%, an 8.65-points gain (P=0.0039). In a matched three-backbone analysis, RAG improved physical-examination, imaging and laboratory clinician test-ordering alignment by 5.17 points and treatment alignment by 3.97 points, while surfacing verifiable guideline citations for clinicians. Benefits depended on retrieval design, with autonomous query rewriting producing the clearest effect on retrieval fidelity and downstream performance. These findings demonstrate that guideline-grounded RAG can improve both the outcomes and clinical-decision pathways of LLM-agents while increasing their traceability and transparency.
- 14 October 2026
- Published by Springer Nature in Research Square
Open AccessTowards guideline-grounded clinical decision-making: a multi-scale study of retrieval augmented generation based large language model agents
Large language models (LLMs) show promise for clinical decision support but are limited by opaque knowledge and inconsistent decision-making. Retrieval-Augmented Generation (RAG) mitigates these issues by injecting verifiable passages from a curated corpus at inference time. Using 2,400 real patient pathways from the MIMIC-CDM dataset, we evaluated RAG configurations over information gathering, diagnostic accuracy, treatment recommendations and guideline retrieval, identifying key factors for integrating RAG into clinical AI-agents. Across eight general and medical LLMs spanning 1B to 70B parameters, RAG consistently increased mean diagnostic accuracy from 55.64% to 64.29%, an 8.65-points gain (P=0.0039). In a matched three-backbone analysis, RAG improved physical-examination, imaging and laboratory clinician test-ordering alignment by 5.17 points and treatment alignment by 3.97 points, while surfacing verifiable guideline citations for clinicians. Benefits depended on retrieval design, with autonomous query rewriting producing the clearest effect on retrieval fidelity and downstream performance. These findings demonstrate that guideline-grounded RAG can improve both the outcomes and clinical-decision pathways of LLM-agents while increasing their traceability and transparency.
- Open Access
- 11 September 2026
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 41
Real-time tumor tracking for magnetic resonance-guided radiotherapy using label-efficient foundation model adaptation
- 11 September 2026
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 41
Open AccessReal-time tumor tracking for magnetic resonance-guided radiotherapy using label-efficient foundation model adaptation
- 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
- 21 August 2025
- Published by Elsevier in European Journal of Cancer
- Vol. 228, 115738
Total tumor volume predicts overall survival and response to induction chemotherapy in patients with colorectal cancer liver metastases: An ancillary study of the phase 3 CAIRO5 trial
- 21 August 2025
- Published by Elsevier in European Journal of Cancer
- Vol. 228, 115738
Open AccessTotal tumor volume predicts overall survival and response to induction chemotherapy in patients with colorectal cancer liver metastases: An ancillary study of the phase 3 CAIRO5 trial
- Open Access
- 1 February 2025
- Published by Elsevier in Pancreatology
- Vol. 25 (2) , 258-265
Contrast agent dispersion visualized by CE-EUS may be a prediction tool for FOLFIRINOX chemotherapy effectiveness in patients with pancreatic adenocarcinoma
- 1 February 2025
- Published by Elsevier in Pancreatology
- Vol. 25 (2) , 258-265
Open AccessContrast agent dispersion visualized by CE-EUS may be a prediction tool for FOLFIRINOX chemotherapy effectiveness in patients with pancreatic adenocarcinoma
- Open Access
- 7 March 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (6) , 573
Limited Role of the Apparent Diffusion Coefficient (ADC) for Tumor Grade and Overall Survival in Resectable Pancreatic Ductal Adenocarcinoma
This study evaluated the relationship between apparent diffusion coefficient (ADC) values in pancreatic ductal adenocarcinoma (PDAC) and tumor grades based on WHO, Adsay, and Kalimuthu classifications, using whole-mount pancreatectomy specimens. If glandular formation plays a key role in the degree of diffusion restriction, diffusion-weighted imaging could facilitate non-invasive grading of PDAC. A freehand region of interest (ROI) was drawn along tumor borders on the preoperative ADC map in each tumor-containing slice. Resection specimens were retrospectively graded according to WHO, Adsay, and Kalimuthu classifications and correlated with overall survival and the 10th percentile of whole-volume ADC values. Findings from 40 patients (23 male, median age 67) showed no correlation between ADC p10 values and WHO differentiation (p = 0.050), Adsay grade (p = 0.955), or Kalimuthu patterns (p = 0.117). There was no association between ADC p10 and overall survival (p = 0.082) and other clinicopathological variables. Survival was significantly lower for poor tumor differentiation (p = 0.046) and non-glandular Kalimuthu patterns (p = 0.016) and there was a trend towards inferior survival for Adsay G3 (p = 0.090) after correction for age, tumor location, and stage. Preoperative ADC measurements for determining PDAC aggressiveness had limited clinical utility, as there was no correlation with histological parameters or overall survival in resectable PDAC.
- 7 March 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (6) , 573
Open AccessLimited Role of the Apparent Diffusion Coefficient (ADC) for Tumor Grade and Overall Survival in Resectable Pancreatic Ductal Adenocarcinoma
This study evaluated the relationship between apparent diffusion coefficient (ADC) values in pancreatic ductal adenocarcinoma (PDAC) and tumor grades based on WHO, Adsay, and Kalimuthu classifications, using whole-mount pancreatectomy specimens. If glandular formation plays a key role in the degree of diffusion restriction, diffusion-weighted imaging could facilitate non-invasive grading of PDAC. A freehand region of interest (ROI) was drawn along tumor borders on the preoperative ADC map in each tumor-containing slice. Resection specimens were retrospectively graded according to WHO, Adsay, and Kalimuthu classifications and correlated with overall survival and the 10th percentile of whole-volume ADC values. Findings from 40 patients (23 male, median age 67) showed no correlation between ADC p10 values and WHO differentiation (p = 0.050), Adsay grade (p = 0.955), or Kalimuthu patterns (p = 0.117). There was no association between ADC p10 and overall survival (p = 0.082) and other clinicopathological variables. Survival was significantly lower for poor tumor differentiation (p = 0.046) and non-glandular Kalimuthu patterns (p = 0.016) and there was a trend towards inferior survival for Adsay G3 (p = 0.090) after correction for age, tumor location, and stage. Preoperative ADC measurements for determining PDAC aggressiveness had limited clinical utility, as there was no correlation with histological parameters or overall survival in resectable PDAC.
- Open Access
Automated Quantitative Analysis of CT Perfusion to Classify Vascular Phenotypes of Pancreatic Ductal Adenocarcinoma
CT perfusion (CTP) analysis is difficult to implement in clinical practice. Therefore, we investigated a novel semi-automated CTP AI biomarker and applied it to identify vascular phenotypes of pancreatic ductal adenocarcinoma (PDAC) and evaluate their association with overall survival (OS). Methods: From January 2018 to November 2022, 107 PDAC patients were prospectively included, who needed to undergo CTP and a diagnostic contrast-enhanced CT (CECT). We developed a semi-automated CTP AI biomarker, through a process that involved deformable image registration, a deep learning segmentation model of tumor and pancreas parenchyma volume, and a trilinear non-parametric CTP curve model to extract the enhancement slope and peak enhancement in segmented tumors and pancreas. The biomarker was validated in terms of its use to predict vascular phenotypes and their association with OS. A receiver operating characteristic (ROC) analysis with five-fold cross-validation was performed. OS was assessed with Kaplan–Meier curves. Differences between phenotypes were tested using the Mann–Whitney U test. Results: The final analysis included 92 patients, in whom 20 tumors (21%) were visually isovascular. The AI biomarker effectively discriminated tumor types, and isovascular tumors showed higher enhancement slopes (2.9 Hounsfield unit HU/s vs. 2.0 HU/s, p < 0.001) and peak enhancement (70 HU vs. 47 HU, p < 0.001); the AUC was 0.86. The AI biomarker’s vascular phenotype significantly differed in OS (p < 0.01). Conclusions: The AI biomarker offers a promising tool for robust CTP analysis. In PDAC, it can distinguish vascular phenotypes with significant OS prognostication.
Open AccessAutomated Quantitative Analysis of CT Perfusion to Classify Vascular Phenotypes of Pancreatic Ductal Adenocarcinoma
CT perfusion (CTP) analysis is difficult to implement in clinical practice. Therefore, we investigated a novel semi-automated CTP AI biomarker and applied it to identify vascular phenotypes of pancreatic ductal adenocarcinoma (PDAC) and evaluate their association with overall survival (OS). Methods: From January 2018 to November 2022, 107 PDAC patients were prospectively included, who needed to undergo CTP and a diagnostic contrast-enhanced CT (CECT). We developed a semi-automated CTP AI biomarker, through a process that involved deformable image registration, a deep learning segmentation model of tumor and pancreas parenchyma volume, and a trilinear non-parametric CTP curve model to extract the enhancement slope and peak enhancement in segmented tumors and pancreas. The biomarker was validated in terms of its use to predict vascular phenotypes and their association with OS. A receiver operating characteristic (ROC) analysis with five-fold cross-validation was performed. OS was assessed with Kaplan–Meier curves. Differences between phenotypes were tested using the Mann–Whitney U test. Results: The final analysis included 92 patients, in whom 20 tumors (21%) were visually isovascular. The AI biomarker effectively discriminated tumor types, and isovascular tumors showed higher enhancement slopes (2.9 Hounsfield unit HU/s vs. 2.0 HU/s, p < 0.001) and peak enhancement (70 HU vs. 47 HU, p < 0.001); the AUC was 0.86. The AI biomarker’s vascular phenotype significantly differed in OS (p < 0.01). Conclusions: The AI biomarker offers a promising tool for robust CTP analysis. In PDAC, it can distinguish vascular phenotypes with significant OS prognostication.
- Open Access
- 1 December 2023
- Published by Springer Nature in European Radiology Experimental
- Vol. 7 (1) , 1-13
Deep learning models for automatic tumor segmentation and total tumor volume assessment in patients with colorectal liver metastases
Background: We developed models for tumor segmentation to automate the assessment of total tumor volume (TTV) in patients with colorectal liver metastases (CRLM). Methods: In this prospective cohort study, pre- and post-systemic treatment computed tomography (CT) scans of 259 patients with initially unresectable CRLM of the CAIRO5 trial (NCT02162563) were included. In total, 595 CT scans comprising 8,959 CRLM were divided into training (73%), validation (6.5%), and test sets (21%). Deep learning models were trained with ground truth segmentations of the liver and CRLM. TTV was calculated based on the CRLM segmentations. An external validation cohort was included, comprising 72 preoperative CT scans of patients with 112 resectable CRLM. Image segmentation evaluation metrics and intraclass correlation coefficient (ICC) were calculated. Results: In the test set (122 CT scans), the autosegmentation models showed a global Dice similarity coefficient (DSC) of 0.96 (liver) and 0.86 (CRLM). The corresponding median per-case DSC was 0.96 (interquartile range [IQR] 0.95–0.96) and 0.80 (IQR 0.67–0.87). For tumor segmentation, the intersection-over-union, precision, and recall were 0.75, 0.89, and 0.84, respectively. An excellent agreement was observed between the reference and automatically computed TTV for the test set (ICC 0.98) and external validation cohort (ICC 0.98). In the external validation, the global DSC was 0.82 and the median per-case DSC was 0.60 (IQR 0.29–0.76) for tumor segmentation. Conclusions: Deep learning autosegmentation models were able to segment the liver and CRLM automatically and accurately in patients with initially unresectable CRLM, enabling automatic TTV assessment in such patients. Relevance statement: Automatic segmentation enables the assessment of total tumor volume in patients with colorectal liver metastases, with a high potential of decreasing radiologist’s workload and increasing accuracy and consistency. Key points: • Tumor response evaluation is time-consuming, manually performed, and ignores total tumor volume. • Automatic models can accurately segment tumors in patients with colorectal liver metastases. • Total tumor volume can be accurately calculated based on automatic segmentations. Graphical
- 1 December 2023
- Published by Springer Nature in European Radiology Experimental
- Vol. 7 (1) , 1-13
Open AccessDeep learning models for automatic tumor segmentation and total tumor volume assessment in patients with colorectal liver metastases
Background: We developed models for tumor segmentation to automate the assessment of total tumor volume (TTV) in patients with colorectal liver metastases (CRLM). Methods: In this prospective cohort study, pre- and post-systemic treatment computed tomography (CT) scans of 259 patients with initially unresectable CRLM of the CAIRO5 trial (NCT02162563) were included. In total, 595 CT scans comprising 8,959 CRLM were divided into training (73%), validation (6.5%), and test sets (21%). Deep learning models were trained with ground truth segmentations of the liver and CRLM. TTV was calculated based on the CRLM segmentations. An external validation cohort was included, comprising 72 preoperative CT scans of patients with 112 resectable CRLM. Image segmentation evaluation metrics and intraclass correlation coefficient (ICC) were calculated. Results: In the test set (122 CT scans), the autosegmentation models showed a global Dice similarity coefficient (DSC) of 0.96 (liver) and 0.86 (CRLM). The corresponding median per-case DSC was 0.96 (interquartile range [IQR] 0.95–0.96) and 0.80 (IQR 0.67–0.87). For tumor segmentation, the intersection-over-union, precision, and recall were 0.75, 0.89, and 0.84, respectively. An excellent agreement was observed between the reference and automatically computed TTV for the test set (ICC 0.98) and external validation cohort (ICC 0.98). In the external validation, the global DSC was 0.82 and the median per-case DSC was 0.60 (IQR 0.29–0.76) for tumor segmentation. Conclusions: Deep learning autosegmentation models were able to segment the liver and CRLM automatically and accurately in patients with initially unresectable CRLM, enabling automatic TTV assessment in such patients. Relevance statement: Automatic segmentation enables the assessment of total tumor volume in patients with colorectal liver metastases, with a high potential of decreasing radiologist’s workload and increasing accuracy and consistency. Key points: • Tumor response evaluation is time-consuming, manually performed, and ignores total tumor volume. • Automatic models can accurately segment tumors in patients with colorectal liver metastases. • Total tumor volume can be accurately calculated based on automatic segmentations. Graphical
- Open Access
- 13 October 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (20) , 3198
Computed Tomography-Based Radiomics Using Tumor and Vessel Features to Assess Resectability in Cancer of the Pancreatic Head
The preoperative prediction of resectability pancreatic ductal adenocarcinoma (PDAC) is challenging. This retrospective single-center study examined tumor and vessel radiomics to predict the resectability of PDAC in chemo-naïve patients. The tumor and adjacent arteries and veins were segmented in the portal-venous phase of contrast-enhanced CT scans, and radiomic features were extracted. Features were selected via stability and collinearity testing, and least absolute shrinkage and selection operator application (LASSO). Three models, using tumor features, vessel features, and a combination of both, were trained with the training set (N = 86) to predict resectability. The results were validated with the test set (N = 15) and compared to the multidisciplinary team’s (MDT) performance. The vessel-features-only model performed best, with an AUC of 0.92 and sensitivity and specificity of 97% and 73%, respectively. Test set validation showed a sensitivity and specificity of 100% and 88%, respectively. The combined model was as good as the vessel model (AUC = 0.91), whereas the tumor model showed poor performance (AUC = 0.76). The MDT’s prediction reached a sensitivity and specificity of 97% and 84% for the training set and 88% and 100% for the test set, respectively. Our clinician-independent vessel-based radiomics model can aid in predicting resectability and shows performance comparable to that of the MDT. With these encouraging results, improved, automated, and generalizable models can be developed that reduce workload and can be applied in non-expert hospitals.
- 13 October 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (20) , 3198
Open AccessComputed Tomography-Based Radiomics Using Tumor and Vessel Features to Assess Resectability in Cancer of the Pancreatic Head
The preoperative prediction of resectability pancreatic ductal adenocarcinoma (PDAC) is challenging. This retrospective single-center study examined tumor and vessel radiomics to predict the resectability of PDAC in chemo-naïve patients. The tumor and adjacent arteries and veins were segmented in the portal-venous phase of contrast-enhanced CT scans, and radiomic features were extracted. Features were selected via stability and collinearity testing, and least absolute shrinkage and selection operator application (LASSO). Three models, using tumor features, vessel features, and a combination of both, were trained with the training set (N = 86) to predict resectability. The results were validated with the test set (N = 15) and compared to the multidisciplinary team’s (MDT) performance. The vessel-features-only model performed best, with an AUC of 0.92 and sensitivity and specificity of 97% and 73%, respectively. Test set validation showed a sensitivity and specificity of 100% and 88%, respectively. The combined model was as good as the vessel model (AUC = 0.91), whereas the tumor model showed poor performance (AUC = 0.76). The MDT’s prediction reached a sensitivity and specificity of 97% and 84% for the training set and 88% and 100% for the test set, respectively. Our clinician-independent vessel-based radiomics model can aid in predicting resectability and shows performance comparable to that of the MDT. With these encouraging results, improved, automated, and generalizable models can be developed that reduce workload and can be applied in non-expert hospitals.