CoordConv-Unet: Investigating CoordConv for Organ Segmentation
| Autor: | R. El Jurdi, Caroline Petitjean, Fahed Abdallah, Paul Honeine |
|---|---|
| Přispěvatelé: | Equipe Apprentissage (DocApp - LITIS), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Université Le Havre Normandie (ULH), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Université Le Havre Normandie (ULH), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA), Université Libanaise, Laboratoire Modélisation et Sûreté des Systèmes (LM2S), Institut Charles Delaunay (ICD), Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS)-Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS), ANR-18-CE23-0014,APi,Apprivoiser la Pré-image(2018), Laboratoire Informatique et Société Numérique (LIST3N), Université de Technologie de Troyes (UTT)-Université de Technologie de Troyes (UTT) |
| Rok vydání: | 2021 |
| Předmět: |
Computer science
0206 medical engineering Biomedical Engineering Biophysics 02 engineering and technology [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] Convolutional neural network [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] 030218 nuclear medicine & medical imaging Image (mathematics) Convolution Prior-based losses 03 medical and health sciences 0302 clinical medicine [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-CY]Computer Science [cs]/Computers and Society [cs.CY] [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] Spatial reference system Fully convolutional networks Segmentation business.industry [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Pattern recognition Image segmentation Medical image segmentation 020601 biomedical engineering Object detection Maxima and minima Artificial intelligence CoordConv business [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing MRI CT |
| Zdroj: | Innovation and Research in BioMedical engineering Innovation and Research in BioMedical engineering, Elsevier Masson, 2021, ⟨10.1016/j.irbm.2021.03.002⟩ Innovation and Research in BioMedical engineering, 2021, ⟨10.1016/j.irbm.2021.03.002⟩ |
| ISSN: | 1959-0318 |
| DOI: | 10.1016/j.irbm.2021.03.002 |
| Popis: | International audience; Objectives: Convolutional neural networks (CNNs) have established state-of-the-art performance in computer vision tasks such as object detection and segmentation. One of the major remaining challenges concerns their ability to capture consistent spatial and anatomically plausible attributes in medical image segmentation. To address this issue, many works advocate to integrate prior information at the level of the loss function. However, prior-based losses often suffer from local solutions and training instability. The CoordConv layers are extensions of convolutional neural network wherein convolution is conditioned on spatial coordinates. The objective of this paper is to investigate CoordConv as a proficient substitute to convolutional layers for medical image segmentation tasks when trained under prior-based losses.Methods: This work introduces CoordConv-Unet which is a novel structure that can be used to accommodate training under anatomical prior losses. The proposed architecture demonstrates a dual role relative to prior constrained CNN learning: it either demonstrates a regularizing role that stabilizes learning while maintaining system performance, or improves system performance by allowing the learning to be more stable and to evade local minima.Results: To validate the performance of the proposed model, experiments are conducted on two well-known public datasets from the Decathlon challenge: a mono-modal MRI dataset dedicated to segmentation of the left atrium, and a CT image dataset whose objective is to segment the spleen, an organ characterized with varying size and mild convexity issues.Conclusion: Results show that, despite the inadequacy of CoordConv when trained with the regular dice baseline loss, the proposed CoordConv-Unet structure can improve significantly model performance when trained under anatomically constrained prior losses. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect