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

Overview

Journal Tomography

Publisher MDPI

Specialty Radiology

Date 2023 Aug 25

PMID 37624116

Authors

Fernando U Kay

Cynthia Lumby

Yuki Tanabe

Suhny Abbara

Prabhakar Rajiah

Affiliations

Soon will be listed here.

Abstract

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 (-values < 0.01), except in the right atrium ( = 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.

References

Foster M, Nolan R, Lam M . Prediction of anemia on unenhanced computed tomography of the thorax. Can Assoc Radiol J. 2003; 54(1):26-30. View

Title R, Harper K, Nelson E, Evans T, Tello R . Observer performance in assessing anemia on thoracic CT. AJR Am J Roentgenol. 2005; 185(5):1240-4. DOI: 10.2214/AJR.04.1171. View

Decker J, Huber A, Senel F, Bette S, Braun F, Risch F . Anemia Detection by Hemoglobin Quantification on Contrast-enhanced Photon-counting CT Data Sets. Radiology. 2022; 305(3):650-652. DOI: 10.1148/radiol.220063. View

Norman D, Price D, Boyd D, Fishman R, Newton T . Quantitative aspects of computed tomography of the blood and cerebrospinal fluid. Radiology. 1977; 123(2):335-8. DOI: 10.1148/123.2.335. View

Corcoran H, Cook D, Proto A . Diagnosis of anemia on computed tomography scans of the thorax. J Comput Tomogr. 1988; 12(2):116-21. DOI: 10.1016/0149-936x(88)90064-1. View

Lan H, Nishihara S, Nishitani H . Accuracy of computed tomography attenuation measurements for diagnosing anemia. Jpn J Radiol. 2010; 28(1):53-7. DOI: 10.1007/s11604-009-0385-5. View

Jimenez D, Escobar C, Marti D, Diaz G, Cesar J, Garcia-Avello A . Association of anaemia and mortality in patients with acute pulmonary embolism. Thromb Haemost. 2009; 102(1):153-8. DOI: 10.1160/TH09-01-0003. View

. Nutritional anaemias. Report of a WHO scientific group. World Health Organ Tech Rep Ser. 1968; 405:5-37. View

Beghe C, Wilson A, Ershler W . Prevalence and outcomes of anemia in geriatrics: a systematic review of the literature. Am J Med. 2004; 116 Suppl 7A:3S-10S. DOI: 10.1016/j.amjmed.2003.12.009. View

10.

Kim N, Im D, Youn J, Hong Y, Choi B, Kang S . Synthetic Extracellular Volume Fraction Derived Using Virtual Unenhanced Attenuation of Blood on Contrast-Enhanced Cardiac Dual-Energy CT in Nonischemic Cardiomyopathy. AJR Am J Roentgenol. 2021; 218(3):454-461. DOI: 10.2214/AJR.21.26654. View

11.

Ananthakrishnan L, Rajiah P, Ahn R, Rassouli N, Xi Y, Soesbe T . Spectral detector CT-derived virtual non-contrast images: comparison of attenuation values with unenhanced CT. Abdom Radiol (NY). 2017; 42(3):702-709. DOI: 10.1007/s00261-016-1036-9. View

12.

Chaudhry A, Gul M, Chaudhry A, Sheikh M, Dunkin J . Quantitative Evaluation of Noncontrast Computed Tomography of the Head for Assessment of Anemia. J Comput Assist Tomogr. 2015; 39(6):842-8. DOI: 10.1097/RCT.0000000000000306. View

13.

Johnson T, Krauss B, Sedlmair M, Grasruck M, Bruder H, Morhard D . Material differentiation by dual energy CT: initial experience. Eur Radiol. 2006; 17(6):1510-7. DOI: 10.1007/s00330-006-0517-6. View

14.

Bland J, Altman D . Statistical methods for assessing agreement between two methods of clinical measurement. Lancet. 1986; 1(8476):307-10. View

15.

Rajkomar A, Dean J, Kohane I . Machine Learning in Medicine. N Engl J Med. 2019; 380(14):1347-1358. DOI: 10.1056/NEJMra1814259. View

16.

Prabhakar A, Misono A, Hemingway J, Hughes D, Duszak Jr R . Medicare Utilization of CT Angiography from 2001 through 2014: Continued Growth by Radiologists. J Vasc Interv Radiol. 2016; 27(10):1554-60. DOI: 10.1016/j.jvir.2016.05.031. View

17.

McLean E, Cogswell M, Egli I, Wojdyla D, de Benoist B . Worldwide prevalence of anaemia, WHO Vitamin and Mineral Nutrition Information System, 1993-2005. Public Health Nutr. 2008; 12(4):444-54. DOI: 10.1017/S1368980008002401. View

18.

Zhou Q, Yu Y, Chen Y, Ding B, Fang S, Yang X . Optimal threshold for the diagnosis of anemia severity on unenhanced thoracic CT: A preliminary study. Eur J Radiol. 2018; 108:236-241. DOI: 10.1016/j.ejrad.2018.10.007. View

19.

Spence R . Medical and economic impact of anemia in hospitalized patients. Am J Health Syst Pharm. 2007; 64(16 Suppl 11):S3-10. DOI: 10.2146/ajhp070244. View

20.

Knight K, Wade S, Balducci L . Prevalence and outcomes of anemia in cancer: a systematic review of the literature. Am J Med. 2004; 116 Suppl 7A:11S-26S. DOI: 10.1016/j.amjmed.2003.12.008. View