2021
DOI: 10.1007/s10278-020-00399-x
|View full text |Cite
|
Sign up to set email alerts
|

An Automated Deep Learning Method for Tile AO/OTA Pelvic Fracture Severity Grading from Trauma whole-Body CT

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
13
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 23 publications
(16 citation statements)
references
References 45 publications
0
13
0
Order By: Relevance
“…In this work, by leveraging the respective strengths of deep learning for feature detection and a BM for causal inference, we achieve automatic and interpretable Tile grading of pelvic fractures from CT images. Using the proposed pipeline, Tile grade prediction had an AUC of 83.3% and 85.1% for translational and rotational instability comparable to the previous black-box method [12] but with added interpretability and potential for human-machine teaming.…”
Section: Discussionmentioning
confidence: 79%
See 2 more Smart Citations
“…In this work, by leveraging the respective strengths of deep learning for feature detection and a BM for causal inference, we achieve automatic and interpretable Tile grading of pelvic fractures from CT images. Using the proposed pipeline, Tile grade prediction had an AUC of 83.3% and 85.1% for translational and rotational instability comparable to the previous black-box method [12] but with added interpretability and potential for human-machine teaming.…”
Section: Discussionmentioning
confidence: 79%
“…We obtained approval for use of the dataset initially described in [12], that consists of 373 admission CT scans of adult patients from two level I trauma centers with bleeding pelvic fractures and varying degrees of instability with IRBapproved waiver of consent. Imaging was performed with intravenous contrast in the arterial phase on 40-, 64-, and dual source 128-row CT scanners and reconstructed with 0.7 -5 mm slice thickness.…”
Section: Dataset and Metricsmentioning
confidence: 99%
See 1 more Smart Citation
“…It is the harmonic mean of the previous two measures: precision and sensitivity. F1 score [36] is defined as Two other indicators-Matthews correlation coefficient (MCC) [37] and Fowlkes-Mallows index (FMI)-are defined below:…”
Section: Measures and Indicatorsmentioning
confidence: 99%
“…The first four measures are sensitivity, specificity, precision and accuracy, common in most pattern recognition papers. The last three measures are F1 score, Matthews correlation coefficient (MCC) [38], and Fowlkes-Mallows index (FMI) [39]. They are defined as:…”
Section: Figure F-fold Cross Validationmentioning
confidence: 99%