Key result
Indices-JSQ deep learning model achieves a 0.87 Dice Metric for automated cardiac MRI measurements.
Why the study?
Quantitative analysis of the heart is necessary for detecting and diagnosing heart disease, yet challenges remain in achieving accurate and comprehensive left ventricle quantification.
Does the Indices-JSQ deep learning model improve the accuracy of left ventricle quantification from cardiac MR images compared to other state-of-the-art methods?
Does the Indices-JSQ deep learning model improve the accuracy of left ventricle quantification from cardiac MR images compared to other state-of-the-art methods?
The proposed deep multi-task regression learning model provides accurate full quantification of the left ventricle from cardiac MR images, outperforming other state-of-the-art methods.
May aid automated LV quantification in research; leaves open prospective clinical validation before adoption.
Quantitative analysis of the heart is extremely necessary and significant for detecting and diagnosing heart disease, yet there are still some challenges. In this study, we propose a new end-to-end segmentation-based deep multi-task regression learning model (Indices-JSQ) to make a holonomic quantitative analysis of the left ventricle (LV), which contains a segmentation network (Img2Contour) and multi-task regression network (Contour2Indices). First, Img2Contour, which contains a deep convolutional encoder-decoder module, is designed to obtain the LV contour. Then, the predicted contour is fed as input to Contour2Indices for full quantification. On the whole, we take into account the relationship between different tasks, which can serve as a complementary advantage. Meanwhile, instead of using images directly from the original dataset, we creatively use the segmented contour of the original image to estimate the cardiac indices to achieve better and more accurate results. We make experiments on MR sequences of 145 subjects and gain the experimental results of 157 mm2, 2.43 mm, 1.29 mm, and 0.87 on areas, dimensions, regional wall thicknesses, and Dice Metric, respectively. It intuitively shows that the proposed method outperforms the other state-of-the-art methods and demonstrates that our method has a great potential in cardiac MR images segmentation, comprehensive clinical assessment, and diagnosis.
No takes yet. Share an insight, caveat, or question.
Du et al. (2018) studied Heart disease (Left ventricle quantification) (n=145). Indices-JSQ deep multi-task regression learning model vs. Other state-of-the-art methods was evaluated on Areas, dimensions, regional wall thicknesses, and Dice Metric. The proposed Indices-JSQ deep learning model achieved a Dice Metric of 0.87 and errors of 157 mm2 for areas, 2.43 mm for dimensions, and 1.29 mm for regional wall thicknesses on cardiac MRIs.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: