Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System.

Introduction: Visceral arterial aneurysms (VAAs) are life threatening. Due to the paucity of symptoms and rarity of the disease, VAAs are underdiagnosed and underestimated. Artificial intelligence (AI) offers new insights into segmentation of the vascular system, and opportunities to better detect VAAs. This pilot study aimed to develop an AI based method to automatically detect VAAs from computed tomography angiography (CTA). Methods: A hybrid method combining a feature based expert system with a supervised deep learning algorithm (convolutional neural network) was used to enable fully automatic segmentation of the abdominal vascular tree. Centrelines were built and reference diameters of each visceral artery were calculated. An abnormal dilatation (VAAs) was defined as a substantial increase in diameter at the pixel of interest compared with the mean diameter of the reference portion. The automatic software provided 3D rendered images with a flag on the identified VAA areas. The performance of the method was tested in a dataset of 33 CTA scans and compared with the ground truth provided by two human experts. Results: Forty-three VAAs were identified by human experts (32 in the coeliac trunk branches, eight in the superior mesenteric artery, one in the left renal, and two in the right renal arteries). The automatic system accurately detected 40 of the 43 VAAs, with a sensitivity of 0.93 and a positive predictive value of 0.51. The mean number of flag areas per CTA was 3.5 ± 1.5 and they could be reviewed and checked by a human expert in less than 30 seconds per CTA. Conclusion: Although the specificity needs to be improved, this study demonstrates the potential of an AI based automatic method to develop new tools to improve screening and detection of VAAs by automatically attracting clinicians' attention to suspicious dilatations of the visceral arteries.

Applications of artificial intelligence for patients with peripheral artery disease.

OBJECTIVE: Applications of artificial intelligence (AI) have been reported in several cardiovascular diseases but its interest in patients with peripheral artery disease (PAD) has been so far less reported. The aim of this review was to summarize current knowledge on applications of AI in patients with PAD, to discuss current limits, and highlight perspectives in the field. METHODS: We performed a narrative review based on studies reporting applications of AI in patients with PAD. The MEDLINE database was independently searched by two authors using a combination of keywords to identify studies published between January 1995 and December 2021. Three main fields of AI were investigated including natural language processing (NLP), computer vision and machine learning (ML). RESULTS: NLP and ML brought new tools to improve the screening, the diagnosis and classification of the severity of PAD. ML was also used to develop predictive models to better assess the prognosis of patients and develop real-time prediction models to support clinical decision-making. Studies related to computer vision mainly aimed at creating automatic detection and characterization of arterial lesions based on Doppler ultrasound examination or computed tomography angiography. Such tools could help to improve screening programs, enhance diagnosis, facilitate presurgical planning, and improve clinical workflow. CONCLUSIONS: AI offers various applications to support and likely improve the management of patients with PAD. Further research efforts are needed to validate such applications and investigate their accuracy and safety in large multinational cohorts before their implementation in daily clinical practice.

Impact of Female Sex on Outcomes of Patients Undergoing Thoracic Endovascular Aortic Aneurysm Repair: A Ten-Year Retrospective Nationwide Study in France.

The impact of sex on the outcomes of patients with cardiovascular disease is still incompletely understood. The aim of this nationwide multicenter observational study was to investigate the impact of sex on post-operative outcomes in patients undergoing thoracic endovascular aortic repair (TEVAR) for intact thoracic aortic aneurysm (iTAA). The French National Health Insurance Information System was searched to identify these patients over a ten-year retrospective period. Post-operative outcomes, 30-day and overall mortality were recorded. Among the 7383 patients included (5521 men and 1862 women), females were significantly older than males (66.8 vs. 64.8 years, p < 0.001). They were less frequently diagnosed with cardiovascular comorbidities. Post-operatively, women had less frequently respiratory (10.9 vs. 13.7%, p = 0.002) as well as cardiac complications (34.3 vs. 37.3%, p = 0.023), but they had more frequently arterial complications (52.8 vs. 49.8%, p = 0.024). There was no significant difference on overall mortality for a mean follow-up of 2.2 years (26.9 vs. 27.6%, p = 0.58). In the multivariable regression model, female sex was not associated with 30-day or overall mortality. Although women had a favorable comorbidity profile, the short-term and long-term survival was similar. The significantly higher rate of arterial complications suggests that women may be at higher risk of access-vessel-related complications.

Automatic Measurement of Vascular Calcifications in Patients with Aorto-Iliac Occlusive Disease to Predict the Risk of Re-intervention After Endovascular Repair.

BACKGROUND: There is currently a lack of consensus and tools to easily measure vascular calcification using computed tomography angiography (CTA). The aim of this study was to develop a fully automatic software to measure calcifications and to evaluate the interest as predictive factor in patients with aorto-iliac occlusive disease. METHODS: This study retrospectively included 171 patients who had endovascular repair of an aorto-iliac occlusive lesion at the University Hospital of Nice between January 2011 and December 2019. Calcifications volumes were measured from CTA using an automatic method consisting in three sequential steps: image pre-processing, lumen segmentation using expert system, and deep learning algorithms and segmentation of calcifications. Calcification volumes were measured in the infrarenal abdominal aorta and the iliac arterial segments, corresponding to the common and the external iliac arteries. RESULTS: Among 171 patients included with a mean age of 65 years, the revascularization was performed on the native external and internal iliac arteries in, respectively: 83 patients (48.5%), 107 (62.3%), and 7 (4.1%). The mean volumes of calcifications were 2,759 mm3 in the infrarenal abdominal aorta, 1,821 mm3 and 1,795 mm3 in the right and left iliac arteries, respectively. For a mean follow-up of 39 months, target lesion re-intervention was performed in 55 patients (32.2%). These patients had higher volume of calcifications in the right and left iliac arteries, compared with patients who did not have a re-intervention (2,274 mm3 vs. 1,606 mm3, P = 0.0319 and 2,278 vs. 1,567 mm3, P = 0.0213). CONCLUSIONS: The development of a fully automatic software would be useful to facilitate the measurement of vascular calcifications and possibly better inform the prognosis of patients.

Applications of Artificial Intelligence in Non-cardiac Vascular Diseases: A Bibliographic Analysis.

Research output related to artificial intelligence (AI) in vascular diseases has been poorly investigated. The aim of this study was to evaluate scientific publications on AI in non-cardiac vascular diseases. A systematic literature search was conducted using the PubMed database and a combination of keywords and focused on three main vascular diseases (carotid, aortic and peripheral artery diseases). Original articles written in English and published between January 1995 and December 2020 were included. Data extracted included the date of publication, the journal, the identity, number, affiliated country of authors, the topics of research, and the fields of AI. Among 171 articles included, the three most productive countries were USA, China, and United Kingdom. The fields developed within AI included: machine learning (n = 90; 45.0%), vision (n = 45; 22.5%), robotics (n = 42; 21.0%), expert system (n = 15; 7.5%), and natural language processing (n = 8; 4.0%). The applications were mainly new tools for: the treatment (n = 52; 29.1%), prognosis (n = 45; 25.1%), the diagnosis and classification of vascular diseases (n = 38; 21.2%), and imaging segmentation (n = 38; 21.2%). By identifying the main techniques and applications, this study also pointed to the current limitations and may help to better foresee future applications for clinical practice.

Incidence of contrast-induced acute kidney injury in patients with acute mesenteric ischemia and identification of potential predictive factors.

OBJECTIVE: Contrast-enhanced computed tomography angiography (CTA) is commonly used to investigate acute abdominal conditions, but the risk of contrast-induced acute kidney injury (CI-AKI) has been poorly investigated in patients with acute mesenteric ischemia. The aim of the present study was to evaluate the incidence of CI-AKI in these patients and identify potential predictive factors. METHODS: Patients admitted for acute mesenteric ischemia who had a diagnostic CTA with contrast medium and a follow-up of creatinine concentration were retrospectively included. RESULTS: Among 53 patients included, 9 (16.9%) developed CI-AKI. The prevalence of chronic kidney disease did not differ significantly between those who developed CI-AKI and those who did not (33.3 vs 18.2%, p=.372). Plasma total bilirubin and conjugated bilirubin levels were significantly higher in patients who developed CI-AKI (17.5 vs 8.0 µmol/L, p=.013 and 8.0 vs 3.0 µmol/L, p=.031, respectively). The proportion of patients who had revascularization was similar between patients who developed CI-AKI and those who did not (11.1 vs 20.5%, p>.999). No significant difference was observed for 30-day mortality and all-cause mortality for a median follow-up of 168 days (22.2 vs 13.6%, p=.611; and 33.3 vs 61.4%, p=.153, respectively). CONCLUSION: This study reports the incidence of CI-AKI in patients with acute mesenteric ischemia after diagnostic CTA with contrast medium. Plasma bilirubin levels were a predictive factor of CI-AKI in these patients. The administration of contrast media during revascularization was not associated with an increased risk of CI-AKI.

Automatic Measurement of Maximal Diameter of Abdominal Aortic Aneurysm on Computed Tomography Angiography Using Artificial Intelligence.

INTRODUCTION: The treatment of abdominal aortic aneurysm relies on surgical repair and the indication mainly depends on its size evaluated by the maximal diameter (Dmax). The aim of this study was to evaluate a new automatic method based on artificial intelligence to measure the Dmax on computed tomography angiography. METHODS: A fully automatic segmentation of the vascular system was performed using a hybrid method combining expert system with supervised deep learning. The aorta centreline was extracted from the segmented aorta and the aortic diameters were automatically calculated. Results were compared to manual segmentation performed by two human operators. RESULTS: The median absolute error between the two human operators was 1.2 mm (IQR 0.5-1.9). The automatic method using the deep learning algorithm demonstrated correlation with the human segmentation, with a median absolute error of 0.8 (0.5-4.2) mm and a coefficient correlation of 0.91 (P < 0.001). CONCLUSIONS: Although validation in larger cohorts is required, this method brings perspectives to develop new tools to standardize and automate the measurement of abdominal aortic aneurysm Dmax in order to help clinicians in the decision-making process.