Improved detection of aortic dissection in non-contrast-enhanced chest CT using an attention-based deep learning model

Rationale and objectives

This study investigated the effects of implementing an attention-based deep learning model for the detection of aortic dissection (AD) using non-contrast-enhanced chest computed tomography (CT).

Materials and methods

We analysed the records of 1300 patients who underwent contrast-enhanced chest CT at 2 medical centres between January 2015 and February 2023. We considered an internal cohort of 200 patients with AD and 200 patients without AD and an external test cohort of 40 patients with AD and 40 patients without AD. The internal cohort was divided into training and test sets, and a deep learning model was trained using 9600 CT images. A convolutional block attention module (CBAM) and a traditional deep learning architecture (namely, You Only Look Once version 5 [YOLOv5]) were combined into an attention-based model (i.e., YOLOv5-CBAM). Its performance was measured against the unmodified YOLOv5 model, and the accuracy, sensitivity, and specificity of the algorithm were evaluated by two independent radiologists.

Results

The CBAM-based model outperformed the traditional deep learning model. In the external testing set, YOLOv5-CBAM achieved an area under the curve (AUC) of 0.938, accuracy of 91.5 %, sensitivity of 90.0 %, and specificity of 92.9 %, whereas the unmodified model achieved an AUC of 0.844, accuracy of 83.6 %, sensitivity of 71.2 %, and specificity of 96.0 %. The sensitivity results of the unmodified algorithms were not significantly different from those of the radiologists; however, the proposed YOLOv5-CBAM algorithm outperformed the unmodified algorithms in terms of detection.

Conclusions

Incorporating the CBAM attention mechanism into a deep learning model can significantly improve AD detection in non-contrast-enhanced chest CT. This approach may aid radiologists in the timely and accurate diagnosis of AD, which is important for improving patient outcomes.

Advanced Warning of Aortic Dissection on Non-Contrast CT: The Combination of Deep Learning and Morphological Characteristics

Background: The identification of aortic dissection (AD) at baseline plays a crucial role in clinical practice. Non-contrast CT scans are widely available, convenient, and easy to perform. However, the detection of AD on non-contrast CT scans by radiologists currently lacks sensitivity and is suboptimal.

Methods: A total of 452 patients who underwent aortic CT angiography (CTA) were enrolled retrospectively from two medical centers in China to form the internal cohort (341 patients, 139 patients with AD, 202 patients with non-AD) and the external testing cohort (111 patients, 46 patients with AD, 65 patients with non-AD). The internal cohort was divided into the training cohort (n = 238), validation cohort (n = 35), and internal testing cohort (n = 68). Morphological characteristics were extracted from the aortic segmentation. A deep-integrated model based on the Gaussian Naive Bayes algorithm was built to differentiate AD from non-AD, using the combination of the three-dimensional (3D) deep-learning model score and morphological characteristics. The areas under the receiver operating characteristic curve (AUCs), accuracy, sensitivity, and specificity were used to evaluate the model performance. The proposed model was also compared with the subjective assessment of radiologists.

Results: After the combination of all the morphological characteristics, our proposed deep-integrated model significantly outperformed the 3D deep-learning model (AUC: 0.948 vs. 0.803 in the internal testing cohort and 0.969 vs. 0.814 in the external testing cohort, both p < 0.05). The accuracy, sensitivity, and specificity of our model reached 0.897, 0.862, and 0.923 in the internal testing cohort and 0.730, 0.978, and 0.554 in the external testing cohort, respectively. The accuracy for AD detection showed no significant difference between our model and the radiologists (p > 0.05).

Conclusion: The proposed model presented good performance for AD detection on non-contrast CT scans; thus, early diagnosis and prompt treatment would be available.

Multidetector Computed Tomography in Traumatic and Nontraumatic Aortic Emergencies: Emphasis on Acute Aortic Syndromes

Aortic emergencies comprise of a list of conditions which are uncommon but are potentially fatal. Prognosis is usually determined by emergent diagnosis and treatment and hence radiology plays a key role in patient management. In this article, we aim to review the various causes of aortic emergencies and the relevant imaging findings placing special emphasis on acute aortic syndromes.

High intimal flap mobility assessed by intravascular ultrasound is associated with better short-term results after TEVAR in chronic aortic dissection

Thoracic endovascular aortic repair (TEVAR) in chronic aortic dissection remains controversial. We analysed whether a high intimal flap mobility (IFM) of the dissection membrane has an impact on aortic remodelling after TEVAR in chronic Type B aortic dissection. Patients undergoing TEVAR with intravascular ultrasound (IVUS) were analysed and IFM was calculated. High IFM was defined as maximum flap amplitude >3 mm. For determining aortic remodelling, the degree of true lumen (TL) expansion was analysed in the last available follow-up CT. Fifty-two patients (63.6 ± 15.4 years) with a mean follow-up of 26.6 ± 20.7 months were analysed. The mobile flap group (n = 29) showed higher absolute TL expansion at the distal stent-graft (5.9 ± 3.1 vs. 3.3 ± 5.4 mm; p = 0.036) and a higher increase in TL diameter (18 ± 10 vs. 9 ± 15%; p = 0.017) compared to the non-mobile group (n = 23). Basic TEVAR-related outcome characteristics were comparable, but the mobile intimal flap group showed a lower re-intervention rate (3 vs. 8pts.; p = 0.032) in chronic dissections. High IFM in chronic Type B aortic dissection is linked to improved aortic remodelling and is associated with a lower re-intervention rate over time. IVUS assessment of IFM in chronic Type B aortic dissection might be helpful in identifying patients with better remodelling after TEVAR.

Intravascular ultrasound assisted sizing in thoracic endovascular aortic repair improves aortic remodeling in Type B aortic dissection

The precise sizing of the stent graft in thoracic endovascular aortic repair (TEVAR) affects aortic remodeling and hence, further outcome. Covering the proximal entry tear is essential for successful treatment of Type B aortic dissection. Intravascular ultrasound (IVUS) enables real-time aortic diameter assessment, and is especially useful when computed tomography (CT) image quality is poor. IVUS, however, is not routinely utilized due to cost inefficiency. We investigated the impact of IVUS-assisted stent graft sizing on aortic remodeling in TEVAR. In this single-center retrospective study we evaluated patients with Type B aortic dissection undergoing both CT and IVUS before TEVAR. We assessed the aortic diameter at the level of the left subclavian artery via both methods before stent implantation and analyzed due to which method the implanted stent graft was chosen, retrospectively. To determine the degrees of aortic remodeling involved, we evaluated true lumen and false lumen diameters, and total aortic remodeling in CT. We analyzed 45 patients with Type B aortic dissection undergoing TEVAR. The mean ages were 66.9±10.0 years fo0072 IVUS (n = 20) and 62.3±14.2 years for CT-assisted TEVAR (n = 25; p = 0.226). The follow-up time for both groups did not differ between the two groups (IVUS: 22.9±23.1 months, CT: 25.6±23.0 months; p = 0.700). While both methods were associated with advantages regarding aortic remodeling, IVUS-assisted sizing yielded a greater increase in true lumen (30.4±6.2 vs. 25.6±5.3; p = 0.008) and reductions in false lumen (14.4±8.5 vs. 23.9±9.3; p = 0.001) and total aortic diameter (35.5±6.0 vs. 39.9±8.1; p = 0.045). IVUS-guided stent graft sizing in Type B aortic dissection shows beneficial effects on aortic remodeling and might be of additional advantage in aortic diseases, especially when CT image quality is poor.