Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Aug 21;19(8):e0305839.
doi: 10.1371/journal.pone.0305839. eCollection 2024.

Artificial intelligence-based pulmonary embolism classification: Development and validation using real-world data

Luan Oliveira da Silva  1   2 , Maria Carolina Bueno da Silva  1 , Guilherme Alberto Sousa Ribeiro  1 , Thiago Fellipe Ortiz de Camargo  1   3 , Paulo Victor Dos Santos  1   3 , Giovanna de Souza Mendes  1 , Joselisa Peres Queiroz de Paiva  1 , Anderson da Silva Soares  2 , Márcio Rodrigues da Cunha Reis  1   4 , Rafael Maffei Loureiro  1 , Wesley Pacheco Calixto  3   4
Affiliations

Artificial intelligence-based pulmonary embolism classification: Development and validation using real-world data

Luan Oliveira da Silva et al. PLoS One. .

Abstract

This paper presents an artificial intelligence-based classification model for the detection of pulmonary embolism in computed tomography angiography. The proposed model, developed from public data and validated on a large dataset from a tertiary hospital, uses a two-dimensional approach that integrates temporal series to classify each slice of the examination and make predictions at both slice and examination levels. The training process consists of two stages: first using a convolutional neural network InceptionResNet V2 and then a recurrent neural network long short-term memory model. This approach achieved an accuracy of 93% at the slice level and 77% at the examination level. External validation using a hospital dataset resulted in a precision of 86% for positive pulmonary embolism cases and 69% for negative pulmonary embolism cases. Notably, the model excels in excluding pulmonary embolism, achieving a precision of 73% and a recall of 82%, emphasizing its clinical value in reducing unnecessary interventions. In addition, the diverse demographic distribution in the validation dataset strengthens the model's generalizability. Overall, this model offers promising potential for accurate detection and exclusion of pulmonary embolism, potentially streamlining diagnosis and improving patient outcomes.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Illustration of CT pulmonary angiography exams: (a) axial C+ classified as normal and (b) axial C+ classified with the presence of PE indicated in the markings.
Fig 2
Fig 2. Flowchart of the proposed methodology.
Fig 3
Fig 3. Application of automatic windowing and segmentation: (a) original image, (b) windowing for PE, (c) windowing for lungs, and (d) automatic segmentation.
Fig 4
Fig 4. CNN-LSTM model metrics for PE classification at slice and stack levels: (a) precision curve, (b) ROC curve, and (c) loss.
Fig 5
Fig 5. Classification of exams from the Universal Repository database: (a) Tp, (b) Fp, (c) Tn, and (d) Fn.
Fig 6
Fig 6. Universal Repository exam heatmaps: (a) Tp, (b) Fp, (c) Tn e (d) Fn.
See this image and copyright information in PMC

References

    1. Yang X, Lin Y, Su J, Wang X, Li X, Lin J, et al.. A two-stage convolutional neural network for pulmonary embolism detection from CTPA images. IEEE Access. 2019;7:84849–84857. doi: 10.1109/ACCESS.2019.2925210 - DOI
    1. Cowan IA, MacDonald SL, Floyd RA. Measuring and managing radiologist workload: Measuring radiologist reporting times using data from a R adiology I nformation S ystem. Journal of medical imaging and radiation oncology. 2013;57(5):558–566. doi: 10.1111/1754-9485.12092 - DOI - PubMed
    1. Cheikh AB, Gorincour G, Nivet H, May J, Seux M, Calame P, et al.. How artificial intelligence improves radiological interpretation in suspected pulmonary embolism. European Radiology. 2022;32(9):5831–5842. doi: 10.1007/s00330-022-08645-2 - DOI - PMC - PubMed
    1. Martin KA, Molsberry R, Cuttica MJ, Desai KR, Schimmel DR, Khan SS. Time trends in pulmonary embolism mortality rates in the United States, 1999 to 2018. Journal of the American Heart Association. 2020;9(17):e016784. doi: 10.1161/JAHA.120.016784 - DOI - PMC - PubMed
    1. Soffer S, Klang E, Shimon O, Barash Y, Cahan N, Greenspana H, et al.. Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis. Scientific reports. 2021;11(1):1–8. doi: 10.1038/s41598-021-95249-3 - DOI - PMC - PubMed

Publication types