System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Ppublish

PubMed: 39800174 DOI: 10.1016/j.neuroimage.2025.121002

Development and routine implementation of deep learning algorithm for automatic brain metastases segmentation on MRI for RANO-BM criteria follow-up.

Neuroimage 306:121002

Authors: Loïse Dessoude, Raphaëlle Lemaire, Romain Andres, Thomas Leleu, Alexandre G Leclercq, Alexis Desmonts, Typhaine Corroller, Amirath Fara Orou-Guidou, Luca Laduree, Loic Le Henaff, Joëlle Lacroix, Alexis Lechervy, Dinu Stefan, Aurélien Corroyer-Dulmont

Affiliations

  • Radiotherapy Department, Centre François Baclesse, Caen 14000, France.
  • Medical Physics Department, Centre François Baclesse, Caen 14000, France.
  • Radiology Department, Centre François Baclesse, Caen 14000, France.
  • ENSICAEN, CNRS, GREYC UMR6072, Normandie Université, Université Caen Normandie, Caen F-14000, France.
  • Medical Physics Department, Centre François Baclesse, Caen 14000, France; CNRS, ISTCT UMR6030, GIP CYCERON, Normandie Université, Université de Caen Normandie, Caen 14000, France.

Abstract

RATIONALE AND OBJECTIVES

The RANO-BM criteria, which employ a one-dimensional measurement of the largest diameter, are imperfect due to the fact that the lesion volume is neither isotropic nor homogeneous. Furthermore, this approach is inherently time-consuming. Consequently, in clinical practice, monitoring patients in clinical trials in compliance with the RANO-BM criteria is rarely achieved. The objective of this study was to develop and validate an AI solution capable of delineating brain metastases (BM) on MRI to easily obtain, using an in-house solution, RANO-BM criteria as well as BM volume in a routine clinical setting.

MATERIALS (PATIENTS) AND METHODS

A total of 27,456 post-Gadolinium-T1 MRI from 132 patients with BM were employed in this study. A deep learning (DL) model was constructed using the PyTorch and PyTorch Lightning frameworks, and the UNETR transfer learning method was employed to segment BM from MRI.

RESULTS

A visual analysis of the AI model results demonstrates confident delineation of the BM lesions. The model shows 100 % accuracy in predicting RANO-BM criteria in comparison to that of an expert medical doctor. There was a high degree of overlap between the AI and the doctor's segmentation, with a mean DICE score of 0.77. The diameter and volume of the BM lesions were found to be concordant between the AI and the reference segmentation. The user interface developed in this study can readily provide RANO-BM criteria following AI BM segmentation.

CONCLUSION

The in-house deep learning solution is accessible to everyone without expertise in AI and offers effective BM segmentation and substantial time savings.

MeSH

Brain, Algorithms, Solutions, Diagnostic Imaging, Neoplasm Metastasis, Deep Learning, Learning, Artificial Intelligence, Wounds And Injuries