Automatic Segmentation and Functional Assessment of the Left Ventricle using U-net Fully Convolutional Network

被引：5

作者：

Abdeltawab, Hisham ^{[1
]}

Khalifa, Fahmi ^{[1
]}

Taher, Fatma ^{[2
]}

Beache, Garth ^{[3
]}

Mohamed, Tamer ^{[4
]}

Elmaghraby, Adel ^{[5
]}

Ghazal, Mohammed ^{[1
]}

Keynton, Robert ^{[1
]}

El-Baz, Ayman ^{[1
]}

机构：

[1] Univ Louisville, Bioengn Dept, Louisville, KY 40292 USA

[2] Zayed Univ, Coll Technol Innovat, Dubai, U Arab Emirates

[3] Univ Louisville, Dept Radiol, Louisville, KY 40292 USA

[4] Univ Louisville, Inst Mol Cardiol, Louisville, KY 40292 USA

[5] Univ Louisville, Comp Engn & Comp Sci, Louisville, KY 40292 USA

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON IMAGING SYSTEMS & TECHNIQUES (IST 2019) | 2019年

关键词：

Cardiac MR; left ventricle; segmentation; deep learning; U-net; class imbalance;

D O I：

10.1109/ist48021.2019.9010123

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

A new method for the automatic segmentation and quantitative assessment of the left ventricle (LV) is proposed in this paper. The method is composed of two steps. First, a fully convolutional U-net is used for the segmentation of the epi- and endo-cardial boundaries of the LV from cine MR images. This step incorporates a novel loss function that accounts for the class imbalance problem caused by the binary cross entropy (BCE) loss function. Our novel loss function maximizes the segmentation accuracy and penalizes the effect of the class-imbalance caused by BCE. In the second step, the ventricular volume curves are constructed from which LV function parameter is estimated (i.e., ejection fraction). Our method demonstrated a statistical significance in the segmentation of the epi- and endo-cardial boundaries (Dice score of 0.94 and 0.96, respectively) compared with the BCE loss (Dice score of 0.89 and 0.86, respectively). Furthermore, a high positive correlation of 0.97 between the estimated ejection fraction and the gold standard was obtained.

引用

页数：5