Atrial scar quantification via multi-scale CNN in the graph-cuts framework
Autor: | Jennifer Keegan, Guang Yang, Lei Li, David N. Firmin, Lingchao Xu, Tom Wong, Fuping Wu, Raad Mohiaddin, Xiahai Zhuang |
---|---|
Přispěvatelé: | British Heart Foundation |
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
FOS: Computer and information sciences
Computer science Image quality Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Initialization Contrast Media Health Informatics Dice LGE MRI Convolutional neural network 09 Engineering Article 030218 nuclear medicine & medical imaging 03 medical and health sciences Multi-scale CNN Cicatrix 0302 clinical medicine Cut medicine Image Processing Computer-Assisted Humans Radiology Nuclear Medicine and imaging Segmentation Heart Atria Graph learning 11 Medical and Health Sciences Radiological and Ultrasound Technology medicine.diagnostic_test business.industry Magnetic resonance imaging Pattern recognition Computer Graphics and Computer-Aided Design Atrial fibrillation Magnetic Resonance Imaging Nuclear Medicine & Medical Imaging Pulmonary Veins Left atrium Scar segmentation Catheter Ablation Graph (abstract data type) Computer Vision and Pattern Recognition Artificial intelligence Neural Networks Computer business 030217 neurology & neurosurgery |
Zdroj: | Medical Image Analysis |
ISSN: | 1361-8423 1361-8415 |
Popis: | Highlights • Propose a fully automatic method for left atrial scar quantification, with promising performance. • Formulate a new framework of scar quantification based on surface projection and graph-cuts framework. • Propose the multi-scale learning CNN, combined with the random shift training strategy, to learn and predict the graph potentials, which significantly improves the performance of the proposed method, and enables the full automation of the framework. • Provide thorough validation and parameter studies for the proposed techniques using fifty-eight clinical images. Graphical abstract The proposed framework for left atrium (LA) scar quantication and analysis. In this framework, we rst use a well-developed multi-atlas whole heart segmentation (MA-WHS) to obtain an initial segmentation of the LA. Then, we project the LA myocardium to generate a surface mesh, where the quantication is performed. At the same time, both the texture and anatomical features of the LA endocardium can be adequately extracted by employing the multi-scale patch (MSP) strategy. Thus, the features of the nodes in the graph are represented by a set of MSPs. Finally, the labeling of scars is achieved by optimizing a cost function based on the graph-cuts framework, whose potentials for edge weights are explicitly learned and predicted by the proposed multi-scale convolutional neural network (MS-CNN). Late gadolinium enhancement magnetic resonance imaging (LGE MRI) appears to be a promising alternative for scar assessment in patients with atrial fibrillation (AF). Automating the quantification and analysis of atrial scars can be challenging due to the low image quality. In this work, we propose a fully automated method based on the graph-cuts framework, where the potentials of the graph are learned on a surface mesh of the left atrium (LA) using a multi-scale convolutional neural network (MS-CNN). For validation, we have included fifty-eight images with manual delineations. MS-CNN, which can efficiently incorporate both the local and global texture information of the images, has been shown to evidently improve the segmentation accuracy of the proposed graph-cuts based method. The segmentation could be further improved when the contribution between the t-link and n-link weights of the graph is balanced. The proposed method achieves a mean accuracy of 0.856 ± 0.033 and mean Dice score of 0.702 ± 0.071 for LA scar quantification. Compared to the conventional methods, which are based on the manual delineation of LA for initialization, our method is fully automatic and has demonstrated significantly better Dice score and accuracy (p |
Databáze: | OpenAIRE |
Externí odkaz: |