Pierre Moulin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pierre Moulin has a total of 141 co-authors. Here are the top co-authors by number of shared publications:
- Benoit J. Van Den Eynde
Ludwig Institute for Cancer Research, Nuffield Department of Medicine, University of Oxford, Oxford, UK
10 shared publications - Caroline Hervé
GSK, Wavre, Belgium
10 shared publications - Christine Sempoux
Institute of Pathology, Lausanne University Hospital, 1011 Lausanne, Switzerland
10 shared publications - Etienne Marbaix
CELL Unit, De Duve Institute and Université Catholique de Louvain, B-1200 Brussels, Belgium; Pathology Department, Cliniques Universitaires Saint-Luc, B-1200 Brussels, Belgium
10 shared publications Ilse Gutierrez-Roelens
10 shared publicationsIvan Théate
10 shared publications
Latest Publications
- 24 March 2026
- Published by BMJ in Journal of Clinical Pathology
- Vol. 79 (6) , 389-395
Keratin 7 immunohistochemistry reveals patterns of cell populations in liver biopsies from patients with MASLD
Aims Metabolic-associated steatotic liver disease (MASLD), which encompasses metabolic associated steatotic liver (MASL) and metabolic-associated steatohepatitis (MASH), is the most common chronic liver disorder worldwide. Fibrosis stage remains the most dependable histological predictor of prognosis; however, routine stains do not fully capture regenerative and injury-related processes. Keratin 7 (K7) immunohistochemistry highlights bile ducts (BDs), ductular reaction (DR), hepatic progenitor cells (PCs) and intermediate hepatocytes (IHs), all of which are involved in regeneration and fibrogenesis. This study aims to quantify K7-positive cell populations across histological stages of MASLD to enhance disease characterisation and evaluate the diagnostic value of K7 immunohistochemistry in this setting. Methods Archived liver biopsies from a clinically well-characterised cohort of 36 patients (17 MASH, 19 MASL) were stained for K7, digitised and analysed using QuPath with manual expert review. K7-positive structures were classified into BD, DR, PC or IH, with over 10 000 objects quantified. Profile densities and portal tract normalised ratios were calculated and correlated with clinical, biochemical and histological grading and staging by the Steatosis Activity and Fibrosis score. Results PC showed the strongest association with necro-inflammatory activity, peaking at grade 3. DR density increased significantly with fibrosis, supporting its role as an early marker of disease progression. IH was notably higher in MASH than in MASL, resulting in higher IH/DR ratios. Conclusion Specific quantitation of K7-positive cell populations can refine the diagnosis of MASLD and complement routine scoring in clinical trials to improve patient stratification.
- 24 March 2026
- Published by BMJ in Journal of Clinical Pathology
- Vol. 79 (6) , 389-395
Keratin 7 immunohistochemistry reveals patterns of cell populations in liver biopsies from patients with MASLD
Aims Metabolic-associated steatotic liver disease (MASLD), which encompasses metabolic associated steatotic liver (MASL) and metabolic-associated steatohepatitis (MASH), is the most common chronic liver disorder worldwide. Fibrosis stage remains the most dependable histological predictor of prognosis; however, routine stains do not fully capture regenerative and injury-related processes. Keratin 7 (K7) immunohistochemistry highlights bile ducts (BDs), ductular reaction (DR), hepatic progenitor cells (PCs) and intermediate hepatocytes (IHs), all of which are involved in regeneration and fibrogenesis. This study aims to quantify K7-positive cell populations across histological stages of MASLD to enhance disease characterisation and evaluate the diagnostic value of K7 immunohistochemistry in this setting. Methods Archived liver biopsies from a clinically well-characterised cohort of 36 patients (17 MASH, 19 MASL) were stained for K7, digitised and analysed using QuPath with manual expert review. K7-positive structures were classified into BD, DR, PC or IH, with over 10 000 objects quantified. Profile densities and portal tract normalised ratios were calculated and correlated with clinical, biochemical and histological grading and staging by the Steatosis Activity and Fibrosis score. Results PC showed the strongest association with necro-inflammatory activity, peaking at grade 3. DR density increased significantly with fibrosis, supporting its role as an early marker of disease progression. IH was notably higher in MASH than in MASL, resulting in higher IH/DR ratios. Conclusion Specific quantitation of K7-positive cell populations can refine the diagnosis of MASLD and complement routine scoring in clinical trials to improve patient stratification.
- Open Access
- 3 June 2025
- Published by SAGE Publications in Toxicologic Pathology
- Vol. 53 (6) , 516-535
Digital Pathology and Artificial Intelligence Applied to Nonclinical Toxicology Pathology—The Current State, Challenges, and Future Directions
Advancements in digital pathology and artificial intelligence (AI) have enormous transformative potential for nonclinical toxicologic pathology and are already changing the ways in which pathologists work. However, due to the rapid evolution of digital pathology and AI, the toxicologic pathology community would benefit from an update on these advancements, which can be used to aid drug development. Here we identify key articles published on the use of digital pathology and AI in the field and provide current regulatory statuses and guidelines. For digital pathology, we outline the requirements for equipment, validation processes, workflows, and archiving. Challenges to achieve system interoperability and to establish harmonization through Digital Imaging and Communications in Medicine compatibility are also discussed. For AI, we highlight considerations for model development, including the determination of ground truth, problems that may arise due to bias, and how the accuracy and precision of AI algorithms can be assessed. Finally, we discuss the challenges and potential for AI-assisted toxicologic pathology, picturing a future where technology and scientific expertise work hand-in-hand to improve the quality and efficiency of nonclinical drug safety evaluation. This publication is a deliverable of the European Innovative Medicines Initiative 2 Joint Undertaking, “Bigpicture.”
- 3 June 2025
- Published by SAGE Publications in Toxicologic Pathology
- Vol. 53 (6) , 516-535
Open AccessDigital Pathology and Artificial Intelligence Applied to Nonclinical Toxicology Pathology—The Current State, Challenges, and Future Directions
Advancements in digital pathology and artificial intelligence (AI) have enormous transformative potential for nonclinical toxicologic pathology and are already changing the ways in which pathologists work. However, due to the rapid evolution of digital pathology and AI, the toxicologic pathology community would benefit from an update on these advancements, which can be used to aid drug development. Here we identify key articles published on the use of digital pathology and AI in the field and provide current regulatory statuses and guidelines. For digital pathology, we outline the requirements for equipment, validation processes, workflows, and archiving. Challenges to achieve system interoperability and to establish harmonization through Digital Imaging and Communications in Medicine compatibility are also discussed. For AI, we highlight considerations for model development, including the determination of ground truth, problems that may arise due to bias, and how the accuracy and precision of AI algorithms can be assessed. Finally, we discuss the challenges and potential for AI-assisted toxicologic pathology, picturing a future where technology and scientific expertise work hand-in-hand to improve the quality and efficiency of nonclinical drug safety evaluation. This publication is a deliverable of the European Innovative Medicines Initiative 2 Joint Undertaking, “Bigpicture.”
- 3 October 2024
- Published by Wiley in Histopathology
- Vol. 86 (3) , 373-384
A deep learning approach to case prioritisation of colorectal biopsies
Aims: To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis).Materials and methods: Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)‐stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision‐making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow.Results: Validation of the model was conducted on two cohorts: the first, on 100 single‐slide cases, achieved micro‐average model specificity of 0.984, micro‐average model sensitivity of 0.949 and micro‐average model F1 score of 0.949 across all classes. A secondary multi‐institutional validation cohort, of 101 single‐slide cases, achieved micro‐average model specificity of 0.978, micro‐average model sensitivity of 0.931 and micro‐average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities.Conclusions: We have developed a high‐performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non‐neoplastic biopsies.
- 3 October 2024
- Published by Wiley in Histopathology
- Vol. 86 (3) , 373-384
A deep learning approach to case prioritisation of colorectal biopsies
Aims: To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis).Materials and methods: Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)‐stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision‐making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow.Results: Validation of the model was conducted on two cohorts: the first, on 100 single‐slide cases, achieved micro‐average model specificity of 0.984, micro‐average model sensitivity of 0.949 and micro‐average model F1 score of 0.949 across all classes. A secondary multi‐institutional validation cohort, of 101 single‐slide cases, achieved micro‐average model specificity of 0.978, micro‐average model sensitivity of 0.931 and micro‐average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities.Conclusions: We have developed a high‐performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non‐neoplastic biopsies.