A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections

Autor: Michele Rizzi, Irène Ollivier, Sebastien Ourselin, Vincent Navarro, Fernando Pérez-García, Valerio Frazzini, Reuben Dorent, Caroline Essert, Francesco Cardinale, Rachel Sparks, John S. Duncan, Tom Vercauteren
Přispěvatelé: Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie (ICube), Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Réseau nanophotonique et optique, Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Matériaux et nanosciences d'Alsace (FMNGE), Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Les Hôpitaux Universitaires de Strasbourg (HUS)-Centre National de la Recherche Scientifique (CNRS)-Matériaux et Nanosciences Grand-Est (MNGE), Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Réseau nanophotonique et optique, Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)
Jazyk: angličtina
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Technology
Source code
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
Convolutional neural network
030218 nuclear medicine & medical imaging
0302 clinical medicine
Engineering
Resective neurosurgery
Image Processing
Computer-Assisted
Segmentation
Cavity segmentation
Lesion simulation
EPILEPSY
media_common
Brain cavity
Image and Video Processing (eess.IV)
Radiology
Nuclear Medicine & Medical Imaging
Brain
General Medicine
Computer Graphics and Computer-Aided Design
Magnetic Resonance Imaging
3. Good health
Computer Science Applications
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
Original Article
Computer Vision and Pattern Recognition
Supervised Machine Learning
Life Sciences & Biomedicine
Self-supervised learning
media_common.quotation_subject
IMAGES
Biomedical Engineering
Health Informatics
Neuroimaging
03 medical and health sciences
FOS: Electrical engineering
electronic engineering
information engineering
Leverage (statistics)
Humans
Radiology
Nuclear Medicine and imaging
Engineering
Biomedical
Self supervised learning
Science & Technology
LESIONS
business.industry
Pattern recognition
Image segmentation
Electrical Engineering and Systems Science - Image and Video Processing
Informatique [cs]/Traitement des images [eess.IV]
Surgery
Artificial intelligence
Neural Networks
Computer
business
030217 neurology & neurosurgery
Zdroj: International Journal of Computer Assisted Radiology and Surgery
International Journal of Computer Assisted Radiology and Surgery, Springer Verlag, 2021, ⟨10.1007/s11548-021-02420-2⟩
International Journal of Computer Assisted Radiology and Surgery, 2021, ⟨10.1007/s11548-021-02420-2⟩
ISSN: 1861-6410
1861-6429
DOI: 10.1007/s11548-021-02420-2⟩
Popis: Accurate segmentation of brain resection cavities (RCs) aids in postoperative analysis and determining follow-up treatment. Convolutional neural networks (CNNs) are the state-of-the-art image segmentation technique, but require large annotated datasets for training. Annotation of 3D medical images is time-consuming, requires highly-trained raters, and may suffer from high inter-rater variability. Self-supervised learning strategies can leverage unlabeled data for training. We developed an algorithm to simulate resections from preoperative magnetic resonance images (MRIs). We performed self-supervised training of a 3D CNN for RC segmentation using our simulation method. We curated EPISURG, a dataset comprising 430 postoperative and 268 preoperative MRIs from 430 refractory epilepsy patients who underwent resective neurosurgery. We fine-tuned our model on three small annotated datasets from different institutions and on the annotated images in EPISURG, comprising 20, 33, 19 and 133 subjects. The model trained on data with simulated resections obtained median (interquartile range) Dice score coefficients (DSCs) of 81.7 (16.4), 82.4 (36.4), 74.9 (24.2) and 80.5 (18.7) for each of the four datasets. After fine-tuning, DSCs were 89.2 (13.3), 84.1 (19.8), 80.2 (20.1) and 85.2 (10.8). For comparison, inter-rater agreement between human annotators from our previous study was 84.0 (9.9). We present a self-supervised learning strategy for 3D CNNs using simulated RCs to accurately segment real RCs on postoperative MRI. Our method generalizes well to data from different institutions, pathologies and modalities. Source code, segmentation models and the EPISURG dataset are available at https://github.com/fepegar/ressegijcars .
To be published in the International Journal of Computer Assisted Radiology and Surgery (IJCARS) - Special issue MICCAI 2020
Databáze: OpenAIRE
Externí odkaz: