Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images

Multi-sequence of cardiac magnetic resonance (CMR) images can provide complementary information for myocardial pathology (scar and edema). However, it is still challenging to fuse these underlying information for pathology segmentation effectively. This work presents an automatic cascade pathology segmentation framework based on multi-modality CMR images. It mainly consists of two neural networks: an anatomical structure segmentation network (ASSN) and a pathological region segmentation network (PRSN). Specifically, the ASSN aims to segment the anatomical structure where the pathology may exist, and it can provide a spatial prior for the pathological region segmentation. In addition, we integrate a denoising auto-encoder (DAE) into the ASSN to generate segmentation results with plausible shapes. The PRSN is designed to segment pathological region based on the result of ASSN, in which a fusion block based on channel attention is proposed to better aggregate multi-modality information from multi-modality CMR images. Experiments from the MyoPS2020 challenge dataset show that our framework can achieve promising performance for myocardial scar and edema segmentation.

[1]  Alejandro F. Frangi,et al.  Healthy and Scar Myocardial Tissue Classification in DE-MRI , 2012, STACOM.

[2]  Septimiu E. Salcudean,et al.  Liver Segmentation in Magnetic Resonance Imaging via Mean Shape Fitting with Fully Convolutional Neural Networks , 2019, MICCAI.

[3]  Guang Yang,et al.  Fully automatic segmentation and objective assessment of atrial scars for long‐standing persistent atrial fibrillation patients using late gadolinium‐enhanced MRI , 2017, Medical physics.

[4]  Xiahai Zhuang,et al.  Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention , 2020, MICCAI.

[5]  Daniel Rueckert,et al.  Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge , 2020, ArXiv.

[6]  Lidia Chojnowska,et al.  Comparison of different quantification methods of late gadolinium enhancement in patients with hypertrophic cardiomyopathy. , 2010, European journal of radiology.

[7]  Fatemeh Zabihollahy,et al.  Convolutional neural network‐based approach for segmentation of left ventricle myocardial scar from 3D late gadolinium enhancement MR images , 2019, Medical physics.

[8]  Peter Kellman,et al.  Gadolinium delayed enhancement cardiovascular magnetic resonance correlates with clinical measures of myocardial infarction. , 2004, Journal of the American College of Cardiology.

[9]  J. Felblinger,et al.  Myocardial infarct sizing by late gadolinium‐enhanced MRI: Comparison of manual, full‐width at half‐maximum, and n‐standard deviation methods , 2016, Journal of magnetic resonance imaging : JMRI.

[10]  Xiahai Zhuang,et al.  Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Su Ruan,et al.  A review: Deep learning for medical image segmentation using multi-modality fusion , 2019, Array.

[12]  Sébastien Ourselin,et al.  Automatic Brain Tumor Segmentation Using Cascaded Anisotropic Convolutional Neural Networks , 2017, BrainLes@MICCAI.

[13]  Xiahai Zhuang,et al.  Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors , 2019, MICCAI.

[14]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Dan W Rettmann,et al.  Accurate and Objective Infarct Sizing by Contrast-enhanced Magnetic Resonance Imaging in a Canine Myocardial Infarction Model , 2022 .

[16]  P. Kellman,et al.  Magnetic Resonance Imaging Delineates the Ischemic Area at Risk and Myocardial Salvage in Patients With Acute Myocardial Infarction , 2010, Circulation. Cardiovascular imaging.

[17]  Martin Rajchl,et al.  Fully Automated Segmentation of Left Ventricular Scar from 3D Late Gadolinium Enhancement Magnetic Resonance Imaging Using a Cascaded Multi-Planar U-Net (CMPU-Net). , 2020, Medical physics.

[18]  Guang Yang,et al.  Atrial scar quantification via multi-scale CNN in the graph-cuts framework , 2019, Medical Image Anal..

[19]  Xiahai Zhuang,et al.  Multivariate Mixture Model for Cardiac Segmentation from Multi-Sequence MRI , 2016, MICCAI.

[20]  Ling Shao,et al.  Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis , 2020, IEEE Transactions on Medical Imaging.

[21]  Richard D. White,et al.  Segmentation of non-viable myocardium in delayed enhancement magnetic resonance images , 2005, The International Journal of Cardiovascular Imaging.