Computer-Aided Detection, Pulmonary Embolism, Computerized Tomography Pulmonary Angiography: Current Status

Al-Hinnawi, Abdel-Razzak

doi:10.5772/intechopen.79339

Cited by 2 publications

(1 citation statement)

References 50 publications

(106 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The emergence of deep learning (DL), a subfield of artificial intelligence (AI), has increased interest in automatized detection and diagnostic tools in radiology [ 13 ]. Before that, multiple different computer-aided detection (CAD) models for diagnosing PE had been developed using manually encoded methods like segmentation, detection of low-attenuated areas, and/or feature analysis [ 14 , 15 ]. Use of CAD as a concurrent reader has been shown to increase reader sensitivity [ 16 ], but high yield of false positives (FPs) has remained as a major drawback [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Automated detection of pulmonary embolism from CT-angiograms using deep learning

Huhtanen

Nyman

Mohsen³

et al. 2022

BMC Med Imaging

View full text Add to dashboard Cite

Background The aim of this study was to develop and evaluate a deep neural network model in the automated detection of pulmonary embolism (PE) from computed tomography pulmonary angiograms (CTPAs) using only weakly labelled training data. Methods We developed a deep neural network model consisting of two parts: a convolutional neural network architecture called InceptionResNet V2 and a long-short term memory network to process whole CTPA stacks as sequences of slices. Two versions of the model were created using either chest X-rays (Model A) or natural images (Model B) as pre-training data. We retrospectively collected 600 CTPAs to use in training and validation and 200 CTPAs to use in testing. CTPAs were annotated only with binary labels on both stack- and slice-based levels. Performance of the models was evaluated with ROC and precision–recall curves, specificity, sensitivity, accuracy, as well as positive and negative predictive values. Results Both models performed well on both stack- and slice-based levels. On the stack-based level, Model A reached specificity and sensitivity of 93.5% and 86.6%, respectively, outperforming Model B slightly (specificity 90.7% and sensitivity 83.5%). However, the difference between their ROC AUC scores was not statistically significant (0.94 vs 0.91, p = 0.07). Conclusions We show that a deep learning model trained with a relatively small, weakly annotated dataset can achieve excellent performance results in detecting PE from CTPAs.

show abstract