Enhanced classification performance using deep learning based segmentation for pulmonary embolism detection in CT angiography
(2024) In Heliyon 10(19).- Abstract
Purpose: To develop a deep learning-based algorithm that automatically and accurately classifies patients as either having pulmonary emboli or not in CT pulmonary angiography (CTPA) examinations. Materials and methods: For model development, 700 CTPA examinations from 652 patients performed at a single institution were used, of which 149 examinations contained 1497 PE traced by radiologists. The nnU-Net deep learning-based segmentation framework was trained using 5-fold cross-validation. To enhance classification, we applied logical rules based on PE volume and probability thresholds. External model evaluation was performed in 770 and 34 CTPAs from two independent datasets. Results: A total of 1483 CTPA examinations were evaluated. In... (More)
Purpose: To develop a deep learning-based algorithm that automatically and accurately classifies patients as either having pulmonary emboli or not in CT pulmonary angiography (CTPA) examinations. Materials and methods: For model development, 700 CTPA examinations from 652 patients performed at a single institution were used, of which 149 examinations contained 1497 PE traced by radiologists. The nnU-Net deep learning-based segmentation framework was trained using 5-fold cross-validation. To enhance classification, we applied logical rules based on PE volume and probability thresholds. External model evaluation was performed in 770 and 34 CTPAs from two independent datasets. Results: A total of 1483 CTPA examinations were evaluated. In internal cross-validation and test set, the trained model correctly classified 123 of 128 examinations as positive for PE (sensitivity 96.1 %; 95 % C.I. 91–98 %; P <. 05) and 521 of 551 as negative (specificity 94.6 %; 95 % C.I. 92–96 %; P <. 05), achieving an area under the receiver operating characteristic (AUROC) of 96.4 % (95 % C.I. 79–99 %; P <. 05). In the first external test dataset, the trained model correctly classified 31 of 32 examinations as positive (sensitivity 96.9 %; 95 % C.I. 84–99 %; P <. 05) and 2 of 2 as negative (specificity 100 %; 95 % C.I. 34–100 %; P <. 05), achieving an AUROC of 98.6 % (95 % C.I. 83–100 %; P <. 05). In the second external test dataset, the trained model correctly classified 379 of 385 examinations as positive (sensitivity 98.4 %; 95 % C.I. 97–99 %; P <. 05) and 346 of 385 as negative (specificity 89.9 %; 95 % C.I. 86–93 %; P <. 05), achieving an AUROC of 98.5 % (95 % C.I. 83–100 %; P <. 05). Conclusion: Our automatic pipeline achieved beyond state-of-the-art diagnostic performance of PE in CTPA using nnU-Net for segmentation and volume- and probability-based post-processing for classification.
(Less)
- author
- Kahraman, Ali Teymur ; Fröding, Tomas ; Toumpanakis, Dimitris ; Gustafsson, Christian Jamtheim LU and Sjöblom, Tobias
- organization
- publishing date
- 2024-10-15
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Computed tomography pulmonary angiography, Deep learning, nnU-net, Pulmonary embolism
- in
- Heliyon
- volume
- 10
- issue
- 19
- article number
- e38118
- publisher
- Elsevier
- external identifiers
-
- scopus:85205301926
- pmid:39398015
- ISSN
- 2405-8440
- DOI
- 10.1016/j.heliyon.2024.e38118
- language
- English
- LU publication?
- yes
- id
- cf21049c-2af9-43ab-b87b-e7f3e2510133
- date added to LUP
- 2024-12-11 10:47:50
- date last changed
- 2025-07-10 03:49:48
@article{cf21049c-2af9-43ab-b87b-e7f3e2510133,
abstract = {{<p>Purpose: To develop a deep learning-based algorithm that automatically and accurately classifies patients as either having pulmonary emboli or not in CT pulmonary angiography (CTPA) examinations. Materials and methods: For model development, 700 CTPA examinations from 652 patients performed at a single institution were used, of which 149 examinations contained 1497 PE traced by radiologists. The nnU-Net deep learning-based segmentation framework was trained using 5-fold cross-validation. To enhance classification, we applied logical rules based on PE volume and probability thresholds. External model evaluation was performed in 770 and 34 CTPAs from two independent datasets. Results: A total of 1483 CTPA examinations were evaluated. In internal cross-validation and test set, the trained model correctly classified 123 of 128 examinations as positive for PE (sensitivity 96.1 %; 95 % C.I. 91–98 %; P <. 05) and 521 of 551 as negative (specificity 94.6 %; 95 % C.I. 92–96 %; P <. 05), achieving an area under the receiver operating characteristic (AUROC) of 96.4 % (95 % C.I. 79–99 %; P <. 05). In the first external test dataset, the trained model correctly classified 31 of 32 examinations as positive (sensitivity 96.9 %; 95 % C.I. 84–99 %; P <. 05) and 2 of 2 as negative (specificity 100 %; 95 % C.I. 34–100 %; P <. 05), achieving an AUROC of 98.6 % (95 % C.I. 83–100 %; P <. 05). In the second external test dataset, the trained model correctly classified 379 of 385 examinations as positive (sensitivity 98.4 %; 95 % C.I. 97–99 %; P <. 05) and 346 of 385 as negative (specificity 89.9 %; 95 % C.I. 86–93 %; P <. 05), achieving an AUROC of 98.5 % (95 % C.I. 83–100 %; P <. 05). Conclusion: Our automatic pipeline achieved beyond state-of-the-art diagnostic performance of PE in CTPA using nnU-Net for segmentation and volume- and probability-based post-processing for classification.</p>}},
author = {{Kahraman, Ali Teymur and Fröding, Tomas and Toumpanakis, Dimitris and Gustafsson, Christian Jamtheim and Sjöblom, Tobias}},
issn = {{2405-8440}},
keywords = {{Computed tomography pulmonary angiography; Deep learning; nnU-net; Pulmonary embolism}},
language = {{eng}},
month = {{10}},
number = {{19}},
publisher = {{Elsevier}},
series = {{Heliyon}},
title = {{Enhanced classification performance using deep learning based segmentation for pulmonary embolism detection in CT angiography}},
url = {{http://dx.doi.org/10.1016/j.heliyon.2024.e38118}},
doi = {{10.1016/j.heliyon.2024.e38118}},
volume = {{10}},
year = {{2024}},
}