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.

Examples of nCCT images, (a)-(d), and the corresponding CTp, (e)-(h).

The color shows the cerebral blood volume (CBV), cerebral blood flow (CBF), the mean transit time (MTT) generated by CTp, the ischemic area- blue, the dead tissue-red.

More »

Fig 1 Expand

Fig 2.

Three basic steps of the proposed model 1) label assignment, 2) feature map extraction, 3) infarct localization.

More »

Fig 2 Expand

Fig 3.

CTp with the ground truth, ncCT aligned with the CTp.

More »

Fig 3 Expand

Fig 4.

The architecture of the input for the proposed DNN.

More »

Fig 4 Expand

Fig 5.

Input for feature extraction (a) brain region on an ncCT slice (b) corresponding CTp, (c) the mask of the brain region.

(a) ncCT Slice. (b) Label. (c) Mask.

More »

Fig 5 Expand

Fig 6.

CTp and ncCT slices, and the result of aligning CTp with ncCT.

More »

Fig 6 Expand

Fig 7.

The feature maps.

(a) DeepLabv3+ with. (b) DeepLabv3+ with MobileNet ResNet50. (c) DeepLabv3+ with. (d) Pixel-wised Feature ResNet101 and Neural Network.

More »

Fig 7 Expand

Fig 8.

Localizing the infarct region using the extracted feature maps.

More »

Fig 8 Expand

Table 1.

Performance of the model vs. the size of the block and post processing.

More »

Table 1 Expand

Fig 9.

Precision and recall values of Ensemble3 (left) and Ensemble5 (right) with different classification threshold.

More »

Fig 9 Expand

Table 2.

Testing the feature maps and input blocks.

More »

Table 2 Expand

Fig 10.

Accuracy (a), precision (b), recall (c), and F1 score (d) of Ensemble model with 3- and 5- blocks by MobileNet, ResNet101, and Resnet50.

(a) Accuracy of all model with (left) and without (right) post processing. (b) Precision of all model with (left) and without (right) post processing. (c) Recall of all model with (left) and without (right) post processing. (d) F1 score of all model with (left) and without (right) post processing.

More »

Fig 10 Expand

Table 3.

The average IoU of feature maps and input blocks.

More »

Table 3 Expand

Fig 11.

Average IoU of regions obtained from each model using different classification threshold values with postproceessing (left) and without it (right).

More »

Fig 11 Expand

Fig 12.

Box plots of IoU for MobileNet, hand-crafted feature map, ResNet101 and Resnet50.

Ensemble model with 1, 3 and 5 extended output blocks. Each plot shows the median values. IoU of all model with (left) and without (right) post processing.

More »

Fig 12 Expand

Fig 13.

Lesion detection of the original ncCT (a) label on CTp (b) of the case that achieved the best segmentation result. (c) Ensemble3 (e) Ensemble5 without postproceessing (d) Ensemble3 (f) Ensemble5 with postproceessing.

More »

Fig 13 Expand

Fig 14.

Lesion detection (a) CTp, (b), (d) Ensemble3 and Ensemble5 without postproceessing, (c), (e) Ensemble3 and Ensemble5 with postprocessing.

More »

Fig 14 Expand

Fig 15.

Lesion detection (a) ncCT and its corresponding CTp (b) of the case that achieved the lowest result due to the failed postprocessing, (b), (d) Ensemble3 and Ensemble5 without postprocessing (c), (e)Ensemble3 and Ensemble5 with postproceessing.

More »

Fig 15 Expand

Fig 16.

Lesion detection of the label on CTp (a) that achieve the low result. The result by Ensemble3 and 5 without postproceessing is depicted in (b) and (d), respectively. The result with postproceessing is in (c) and (e) respectively.

More »

Fig 16 Expand