Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

An example of a low resolution, annotated echocardiographic image.

More »

Fig 1 Expand

Fig 2.

An example of the cone segmentation task executed in a renal liver ultrasound.

a, the original image features all the technical elements of the ultrasound scan. b, the predicted mask from the cone segmentation superimposed on the ultrasound scan, c, the mask smoothed and applied over the image. d, finally a dilation step is applied to improve the cone segmentation.

More »

Fig 2 Expand

Fig 3.

U-Net architecture implemented.

More »

Fig 3 Expand

Table 1.

Architecture summary of U-Net implemented, parameters for each block and the total of parameters.

More »

Table 1 Expand

Fig 4.

An example of a mask from the right ventricle (top-left in pink labeled VD) surrounding the right atrium (bottom-left in violet labeled AD).

More »

Fig 4 Expand

Fig 5.

Mask VD after the correction.

More »

Fig 5 Expand

Fig 6.

The final result improved for visualization purposes.

More »

Fig 6 Expand

Fig 7.

Some instances from the custom dataset with their respective ground truth masks.

More »

Fig 7 Expand

Fig 8.

Left (GT): Mask generated by the clinician’s labeling. Center (PR): Mask predicted by the model. Right (CR): Predicted mask after heuristic correction.

More »

Fig 8 Expand

Fig 9.

Visible differences between the PR mask and the CR mask.

More »

Fig 9 Expand

Table 2.

Comparison of Dice coefficients between U-Net vs ground truth (GT) and after correction vs GT for each chamber mask.

More »

Table 2 Expand

Fig 10.

Loss history for the training (red) and validation (blue) phases.

More »

Fig 10 Expand

Fig 11.

Dice Coefficient (dice_coeff), Intersection over Union (IoU) and mean pixel accuracy achieved in the validation phase.

More »

Fig 11 Expand

Fig 12.

Two examples from the first case where the segmentations were very close to the ground truth.

It can be proved the good quality of the images for this case (especially on the contrast between the cavities chambers and the rest of the heart structure).

More »

Fig 12 Expand

Fig 13.

There are larger left ventricles (b) and variable shapes for the rest of the cavities and less defined borders (a) for this two examples. The model achieved good segmentations for both.

More »

Fig 13 Expand

Fig 14.

In this third case, the quality drop is notorious for this two examples: (a) and (b). This is reflected in how segmentation quality is lower compared to the two previous cases but the model does not lose shape sense and keeps them regular given the cavity.

More »

Fig 14 Expand

Fig 15.

Two examples of the fourth case, where annotations are incorrect and additional areas have been marked.

More »

Fig 15 Expand