Direct Multitype Cardiac Indices Estimation via Joint Representation and Regression Learning

Cardiac indices estimation is of great importance during identification and diagnosis of cardiac disease in clinical routine. However, estimation of multitype cardiac indices with consistently reliable and high accuracy is still a great challenge due to the high variability of cardiac structures and...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on medical imaging Ročník 36; číslo 10; s. 2057 - 2067
Hlavní autoři: Wufeng Xue, Islam, Ali, Bhaduri, Mousumi, Shuo Li
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.10.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Artificial neural networks
cardiac MR
Convolution
Coronary artery disease
deep convolution autoencoder
direct estimation
Error reduction
Estimation
Feature extraction
Heart - anatomy & histology
Heart - diagnostic imaging
Heart - physiology
Heart diseases
Heart Function Tests
Humans
Image Interpretation, Computer-Assisted - methods
Image processing
Image representation
Image segmentation
joint learning
Machine Learning
Magnetic Resonance Imaging, Cine - methods
Medical imaging
Multitype cardiac indices
Myocardium
Neural networks
Neural Networks (Computer)
Regression Analysis
Regression models
Representations
Thickness
Volume measurement
ISSN:0278-0062, 1558-254X, 1558-254X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Cardiac indices estimation is of great importance during identification and diagnosis of cardiac disease in clinical routine. However, estimation of multitype cardiac indices with consistently reliable and high accuracy is still a great challenge due to the high variability of cardiac structures and the complexity of temporal dynamics in cardiac MR sequences. While efforts have been devoted into cardiac volumes estimation through feature engineering followed by a independent regression model, these methods suffer from the vulnerable feature representation and incompatible regression model. In this paper, we propose a semi-automated method for multitype cardiac indices estimation. After the manual labeling of two landmarks for ROI cropping, an integrated deep neural network Indices-Net is designed to jointly learn the representation and regression models. It comprises two tightly-coupled networks, such as a deep convolution autoencoder for cardiac image representation, and a multiple output convolution neural network for indices regression. Joint learning of the two networks effectively enhances the expressiveness of image representation with respect to cardiac indices, and the compatibility between image representation and indices regression, thus leading to accurate and reliable estimations for all the cardiac indices. When applied with five-fold cross validation on MR images of 145 subjects, Indices-Net achieves consistently low estimation error for LV wall thicknesses (1.44 ± 0.71 mm) and areas of cavity and myocardium (204 ± 133 mm 2 ). It outperforms, with significant error reductions, segmentation method (55.1% and 17.4%), and two-phase direct volume-only methods (12.7% and 14.6%) for wall thicknesses and areas, respectively. These advantages endow the proposed method a great potential in clinical cardiac function assessment.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0278-0062
1558-254X
1558-254X
DOI:10.1109/TMI.2017.2709251