EUVIMEDTutustu EUVIMEDiin
Open access · CC BY 4.0

Detection of Low Blood Hemoglobin Levels on Pulmonary CT Angiography: A Feasibility Study Combining Dual-Energy CT and Machine Learning

Fernando U Kay iD, Cynthia Lumby, Yuki Tanabe, Suhny Abbara, Prabhakar Rajiah

Tomography · 2023

DOI: 10.3390/tomography9040123 ↗

At a glance

Journal article in Tomography, 2023. Written by Fernando U Kay and 4 co-authors. Institution: Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA. Major MEDLINE topics: Computed Tomography Angiography, Angiography. Cited 4 times so far (Crossref); 43 references. The full text is freely available (open access, CC BY 4.0).

TiivistelmäSubjectsBibliografiset tiedotCiteRelated studies

Abstract (original language)

Objectives

To evaluate if dual-energy CT (DECT) pulmonary angiography (CTPA) can detect anemia with the aid of machine learning.

Methods

Inclusion of 100 patients (mean age ± SD, 51.3 ± 14.8 years; male-to-female ratio, 42/58) who underwent DECT CTPA and hemoglobin (Hb) analysis within 24 h, including 50 cases with Hb below and 50 controls with Hb ≥ 12 g/dL. Blood pool attenuation was assessed on virtual noncontrast (VNC) images at eight locations. A classification model using extreme gradient-boosted trees was developed on a training set (n = 76) for differentiating cases from controls. The best model was evaluated in a separate test set (n = 24).

Results

Blood pool attenuation was significantly lower in cases than controls (p-values < 0.01), except in the right atrium (p = 0.06). The machine learning model had sensitivity, specificity, and accuracy of 83%, 92%, and 88%, respectively. Measurements at the descending aorta had the highest relative importance among all features; a threshold of 43 HU yielded sensitivity, specificity, and accuracy of 68%, 76%, and 72%, respectively.

Conclusion

VNC imaging and machine learning shows good diagnostic performance for detecting anemia on DECT CTPA.

Subjects

MeSH terms (MEDLINE)

Computed Tomography AngiographyAngiographyHumansFeasibility StudiesMachine Learning

Author keywords

anemiacomputed tomography angiographymachine learningpulmonary embolism

Authors and institutions

  • Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
  • Veterans Affairs North Texas Health Care System, Dallas, TX 75216, USA.
  • Department of Radiology, Ehime University, Matsuyama 790-0825, Japan.
  • Department of Radiology, Mayo Clinic, Rochester, MN 55901, USA.

ORCID profiles: Fernando U Kay

Cite

APA

Kay, F. U., Lumby, C., Tanabe, Y., Abbara, S., & Rajiah, P. (2023). Detection of Low Blood Hemoglobin Levels on Pulmonary CT Angiography: A Feasibility Study Combining Dual-Energy CT and Machine Learning. Tomography. https://doi.org/10.3390/tomography9040123

Vancouver

Kay FU, Lumby C, Tanabe Y, Abbara S, Rajiah P. Detection of Low Blood Hemoglobin Levels on Pulmonary CT Angiography: A Feasibility Study Combining Dual-Energy CT and Machine Learning. Tomography. 2023. doi:10.3390/tomography9040123

BibTeX
@article{Kay2023,
  author = {Kay, Fernando U and Lumby, Cynthia and Tanabe, Yuki and Abbara, Suhny and Rajiah, Prabhakar},
  title = {Detection of Low Blood Hemoglobin Levels on Pulmonary CT Angiography: A Feasibility Study Combining Dual-Energy CT and Machine Learning},
  journal = {Tomography},
  year = {2023},
  doi = {10.3390/tomography9040123}
}
Start for free →