Automatic detection of pulmonary embolism in computed tomography pulmonary angiography using Scaled‐YOLOv4

Background Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and mi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Medical physics (Lancaster) Ročník 50; číslo 7; s. 4340 - 4350
Hlavní autoři: Xu, Haijun, Li, Huiyao, Xu, Qifei, Zhang, Zewei, Wang, Ping, Li, Dong, Guo, Li
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 01.07.2023
Témata:
Algorithms
Angiography
computed tomography (CT)
Computed Tomography Angiography - methods
computer‐aided detection
deep learning
Humans
Probability
pulmonary embolism
Pulmonary Embolism - diagnostic imaging
Tomography
YOLO
YOLO
deep learning
computer-aided detection
computed tomography (CT)
pulmonary embolism
ISSN:0094-2405, 2473-4209, 2473-4209
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Background Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and missed. Methods In this study, we identified a deep learning model Scaled‐YOLOv4 that enables end‐to‐end automated detection of PE to help solve these problems. A total of 307 CTPA data (Tianjin 142 cases, Linyi 133 cases, and FUMPE 32 cases) were included in this study. The Tianjin dataset was divided 10 times in the ratio of training set: validation set: test set = 7:2:1 for model tuning, and both the Linyi and FUMPE datasets were used as independent external test sets to evaluate the generalization of the model. Results Scaled‐YOLOv4 was able to process one patient in average 3.55 s [95% CI: 3.51–3.59 s]. It also achieved an average precision (AP) of 83.04 [95% CI: 79.36–86.72] for PE detection on the Tianjin test set, and 75.86 [95% CI: 75.48–76.24] and 72.74 [95% CI: 72.10–73.38] on Linyi and FUMPE, respectively. Conclusions This deep learning algorithm helps detect PE in real time, providing radiologists with aided diagnostic evidence without increasing their workload, and can effectively reduce the probability of delayed patient diagnosis.
Bibliografie:Haijun Xu and Huiyao Li contributed equally to this study.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0094-2405
2473-4209
2473-4209
DOI:10.1002/mp.16218