ESR Essentials: a step-by-step guide of segmentation for radiologists-practice recommendations by the European Society of Medical Imaging Informatics.
Authors
Affiliations (14)
Affiliations (14)
- Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands.
- GROW School for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands.
- Department of Diagnostic and Interventional Neuroradiology, University Hospital Basel, Basel, Switzerland.
- Department of Pediatric Radiology, University Children's Hospital Basel, Basel, Switzerland.
- London North West University Healthcare NHS Trust, London, UK.
- Department of Medical Imaging and Radiation Therapy, Hanze University of Applied Sciences, Groningen, The Netherlands.
- Department of Radiotherapy, University of Groningen, University Medical Centre Groningen, Groningen, The Netherlands.
- Research Group Healthy Ageing, Allied Health Care and Nursing, The Hanze University of Applied Sciences, Groningen, The Netherlands.
- Digital Surgery LAB, Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal.
- Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal.
- Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands.
- Department of Radiology & Nuclear Medicine, Erasmus University Medical Center, Rotterdam, The Netherlands.
- Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands. [email protected].
- Department of Thoracic Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands. [email protected].
Abstract
High-quality segmentation is important for AI-driven radiological research and clinical practice, with the potential to play an even more prominent role in the future. As medical imaging advances, accurately segmenting anatomical and pathological structures is increasingly used to obtain quantitative data and valuable insights. Segmentation and volumetric analysis could enable more precise diagnosis, treatment planning, and patient monitoring. These guidelines aim to improve segmentation accuracy and consistency, allowing for better decision-making in both research and clinical environments. Practical advice on planning and organization is provided, focusing on quality, precision, and communication among clinical teams. Additionally, tips and strategies for improving segmentation practices in radiology and radiation oncology are discussed, as are potential pitfalls to avoid. KEY POINTS: As AI continues to advance, volumetry will become more integrated into clinical practice, making it essential for radiologists to stay informed about its applications in diagnosis and treatment planning. There is a significant lack of practical guidelines and resources tailored specifically for radiologists on technical topics like segmentation and volumetric analysis. Establishing clear rules and best practices for segmentation can streamline volumetric assessment in clinical settings, making it easier to manage and leading to more accurate decision-making for patient care.