Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features
2017
Cardiac magnetic resonance imagingimproves on diagnosis of cardiovascular diseases by providing images at high spatiotemporal resolution. Manual evaluation of these time-series, however, is expensive and prone to biased and non-reproducible outcomes. In this paper, we present a method that addresses named
limitationsby
integratingsegmentation and disease classification into a fully automatic processing pipeline. We use an ensemble of UNet inspired architectures for segmentation of cardiac structures such as the left and right ventricular cavity (LVC, RVC) and the left ventricular myocardium (LVM) on each time instance of the
cardiac cycle. For the classification task, information is extracted from the segmented time-series in form of comprehensive features handcrafted to reflect diagnostic clinical procedures. Based on these features we train an ensemble of heavily regularized
multilayer perceptrons(MLP) and a random forest classifier to predict the pathologic target class. We evaluated our method on the
ACDCdataset (4 pathology groups, 1 healthy group) and achieve dice scores of 0.945 (LVC), 0.908 (RVC) and 0.905 (LVM) in a
cross-validationover the
training set(100 cases) and 0.950 (LVC), 0.923 (RVC) and 0.911 (LVM) on the
test set(50 cases). We report a classification accuracy of \(94 \%\) on a
training set
cross-validationand \(92\%\) on the
test set. Our results underpin the potential of machine learning methods for accurate, fast and reproducible segmentation and computer-assisted diagnosis (CAD).
Keywords:
-
Correction
-
Source
-
Cite
-
Save
14
References
44
Citations
NaN
KQI