Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2019 Nov 27;9:17709. doi: 10.1038/s41598-019-54176-0

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2019

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Comparison of representative examples of predicted DNC images generated using the proposed CNN (middle column, display window (40, 80)), TNC images (left column (display window (40, 80)), and S-VNC images reconstructed using a conventional material decomposition algorithm (right panel, display window (20, 60)) in the evaluation of hemorrhagic stroke. Reduced SNR on the S-VNC images erroneously de-emphasizes areas of acute hemorrhage. In comparison, the predicted DNC images demonstrate increased conspicuity of normal brain anatomy and various intracranial pathologies, including vasogenic edema, hemorrhagic infarction and subarachnoid hemorrhage. Moreover, the predicted DNC images have less noise than the TNC images, improving the visibility of subtle intracranial hemorrhage. First row: 49-year-old male presenting with unilateral weakness and aphasia secondary to acute ICH within the left basal ganglia. Vasogenic edema surrounding the ICH is more easily identified on the DNC image than the S-VNC image. Second row: 47-year-old unresponsive female with a large acute ICH in the right basal ganglia and intraventricular hemorrhagic extension. There is trans-ependymal CSF flow, consistent with acute hydrocephalus as a result of intraventricular hemorrhagic extension, which is well-visualized on the predicted DNC and TNC images and not well seen on the S-VNC image. Third row: 72-year-old female with acute subarachnoid hemorrhage and acute ICH secondary to a ruptured anterior communicating artery aneurysm. The TNC and predicted DNC images depict multifocal acute subarachnoid hemorrhage and trans-ependymal CSF flow from acute hydrocephalus, which are not identifiable on the S-VNC image. Note that the differentiation and extent of acute subarachnoid hemorrhage is improved on the predicted DNC image compared to the TNC image, most notable along the anterior left frontal lobe. Fourth row: 64-year-old male presenting with altered mental status secondary to a large right parietal ICH, which is better evaluated in extent on the predicted DNC image compared to the S-VNC image. The extent of surrounding vasogenic edema is also better characterized on TNC and predicted DNC images. Slight posterior morphological differences between the TNC and other images are secondary to registration inaccuracy. Fifth row: 80-year-old male presenting with acute-onset right facial droop, right-sided weakness and expressive aphasia secondary to an acute ICH involving the left basal ganglia and left insula. Both TNC and predicted DNC images better delineate normal anatomy and the extent of vasogenic edema surrounding the ICH. Moreover, the predicted DNC image demonstrates reduced noise in comparison to the TNC image, allowing for better gray-white matter differentiation.