↓ Skip to main content

Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT

Overview of attention for article published in American Journal of Neuroradiology, July 2018
Altmetric Badge

About this Attention Score

  • In the top 5% of all research outputs scored by Altmetric
  • Among the highest-scoring outputs from this source (#17 of 3,060)
  • High Attention Score compared to outputs of the same age (94th percentile)
  • High Attention Score compared to outputs of the same age and source (96th percentile)

Mentioned by

news
4 news outlets
twitter
25 tweeters

Citations

dimensions_citation
2 Dimensions

Readers on

mendeley
38 Mendeley
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Title
Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT
Published in
American Journal of Neuroradiology, July 2018
DOI 10.3174/ajnr.a5742
Pubmed ID
Authors

P.D. Chang, E. Kuoy, J. Grinband, B.D. Weinberg, M. Thompson, R. Homo, J. Chen, H. Abcede, M. Shafie, L. Sugrue, C.G. Filippi, M.-Y. Su, W. Yu, C. Hess, D. Chow

Abstract

Convolutional neural networks are a powerful technology for image recognition. This study evaluates a convolutional neural network optimized for the detection and quantification of intraparenchymal, epidural/subdural, and subarachnoid hemorrhages on noncontrast CT. This study was performed in 2 phases. First, a training cohort of all NCCTs acquired at a single institution between January 1, 2017, and July 31, 2017, was used to develop and cross-validate a custom hybrid 3D/2D mask ROI-based convolutional neural network architecture for hemorrhage evaluation. Second, the trained network was applied prospectively to all NCCTs ordered from the emergency department between February 1, 2018, and February 28, 2018, in an automated inference pipeline. Hemorrhage-detection accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value were assessed for full and balanced datasets and were further stratified by hemorrhage type and size. Quantification was assessed by the Dice score coefficient and the Pearson correlation. A 10,159-examination training cohort (512,598 images; 901/8.1% hemorrhages) and an 862-examination test cohort (23,668 images; 82/12% hemorrhages) were used in this study. Accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative-predictive value for hemorrhage detection were 0.975, 0.983, 0.971, 0.975, 0.793, and 0.997 on training cohort cross-validation and 0.970, 0.981, 0.951, 0.973, 0.829, and 0.993 for the prospective test set. Dice scores for intraparenchymal hemorrhage, epidural/subdural hemorrhage, and SAH were 0.931, 0.863, and 0.772, respectively. A customized deep learning tool is accurate in the detection and quantification of hemorrhage on NCCT. Demonstrated high performance on prospective NCCTs ordered from the emergency department suggests the clinical viability of the proposed deep learning tool.

Twitter Demographics

The data shown below were collected from the profiles of 25 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 38 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 38 100%

Demographic breakdown

Readers by professional status Count As %
Researcher 10 26%
Student > Ph. D. Student 10 26%
Other 5 13%
Student > Bachelor 4 11%
Student > Master 3 8%
Other 6 16%
Readers by discipline Count As %
Medicine and Dentistry 11 29%
Computer Science 9 24%
Engineering 9 24%
Unspecified 7 18%
Neuroscience 1 3%
Other 1 3%

Attention Score in Context

This research output has an Altmetric Attention Score of 47. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 15 September 2018.
All research outputs
#305,570
of 12,310,901 outputs
Outputs from American Journal of Neuroradiology
#17
of 3,060 outputs
Outputs of similar age
#14,008
of 263,886 outputs
Outputs of similar age from American Journal of Neuroradiology
#3
of 77 outputs
Altmetric has tracked 12,310,901 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 97th percentile: it's in the top 5% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 3,060 research outputs from this source. They receive a mean Attention Score of 4.2. This one has done particularly well, scoring higher than 99% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 263,886 tracked outputs that were published within six weeks on either side of this one in any source. This one has done particularly well, scoring higher than 94% of its contemporaries.
We're also able to compare this research output to 77 others from the same source and published within six weeks on either side of this one. This one has done particularly well, scoring higher than 96% of its contemporaries.