Smart traffic management of vehicles using faster R-CNN based deep learning method.

With constant growth of civilization and modernization of cities all across the world since past few centuries smart traffic management of vehicles is one of the most sorted after problem by research community. Smart traffic management basically involves segmentation of vehicles, estimation of traffic density and tracking of vehicles. The vehicle segmentation from videos helps realization of niche applications such as monitoring of speed and estimation of traffic. When occlusions, background with clutters and traffic with density variations, this problem becomes more intractable in nature. Keeping this motivation in this research work, we investigate Faster R-CNN based deep learning method towards segmentation of vehicles. This problem is addressed in four steps viz minimization with adaptive background model, Faster R-CNN based subnet operation, Faster R-CNN initial refinement and result optimization with extended topological active nets. The computational framework uses adaptive background modeling. It also addresses shadow and illumination issues. Higher segmentation accuracy is achieved through topological active net deformable models. The topological and extended topological active nets help to achieve stated deformations. Mesh deformation is achieved with minimization of energy. The segmentation accuracy is improved with modified version of extended topological active net. The experimental results demonstrate superiority of this framework with respect to other methods.

Endosutured aneurysm repair (ESAR) of abdominal aortic aneurysms with short necks achieves acceptable mid-term outcomes - results from the PERU registry.

INTRODUCTION: The study aims to describe midterm outcomes following treatment of infrarenal abdominal aortic aneurysms (AAAs) with short necks by endosutured aneurysm repair (ESAR) using the Heli-FX EndoAnchor system. METHODS: This is a retrospective study of prospectively collected data from nine vascular surgery departments between June 2010 - December 2019, including treated AAAs with neck lengths ≤ 10mm. The decision for the use of EndoAnchors was made by the treating surgeon or multidisciplinary aortic committee according to each centre's practice. There were two subgroups further assessed according to neck length, A (≥4 and < 7mm) and B (≥7 and ≤10mm). The main outcomes analysed were technical success, freedom from type Ia endoleaks (TIaEL), sac size increase, all-cause (ACM) and aneurysm related mortality (ARM). RESULTS: 76 patients were included in the study, 17 fell into Subgroup A and 59 into subgroup B. Median follow-up for the cohort was 40.5 (IQR 12-61) months. A median of 6 (IQR 3) EndoAnchors were deployed in each subject. Technical success was 86.8% for the total group, 82.4% and 88.1% (p=0.534) for subgroups A and B respectively. Six out of ten (60%) of TIaELs at the completion angiographies showed spontaneous resolution. Cumulative freedom from TIaEL at 3 and 5 years for the total group was 89% and 84% respectively; this was 93% and 74% for subgroup A and 88% at both intervals in subgroup B (p=0.545). In total, there were 7 (9.2%) patients presenting with type Ia endoleaks over the entire study period. Two (11.8%) in subgroup A and 5 (8.5%) in subgroup B (p=0.679). There were more patients with sac regression in subgroup B (subgroup A=6 - 35.3% versus subgroup B=34 - 57.6%, p=0.230) with no statistical significance. ACM was 19 (25%) patients, with no difference (4 - 23.5% versus 15 - 25.4%, p=0.874) between subgroups; whereas ARM occurred in one patient from subgroup A and 3 from subgroup B. CONCLUSIONS: This study demonstrates reasonable outcomes for patients with short-necked AAAs treated by ESAR in terms of type Ia endoleaks up to 5 year follow up. EndoAnchor use should be judiciously evaluated in short necks and may be a reasonable option when anatomical constraints are encountered, mainly for those with 7-10mm neck lengths. Shorter neck length aspects, as indicated by the results from Group A, may be an alternative when no other options are available or feasible.

A Comparative Analysis of the Early and Late Complication Rates and the Effect of Calcification on the Efficacy of MANTA and ProGlide Vascular Closure Devices.

Introduction The Perclose ProGlide and, more recently, MANTA Large-Bore Closure Device are commonly used vascular closure devices (VCDs) for managing large-bore vascular access haemostasis. The extent of calcification in the common femoral artery (CFA) plays a crucial role in choosing between these devices. ProGlide may face challenges with anterior calcification, while MANTA may have issues with posterior calcification. Our study compared their effectiveness, adjunct usage, calcification impact and early/late complications. Methods A retrospective analysis of procedures involving large-bore CFA access from 2017 to 2022 was conducted. Closure was grouped according to VCD as Group A (ProGlide) and Group B (MANTA). Calcification was designated as anterior and posterior and combined on pre-operative computed tomography angiography along 10 mm segments with 0.625 mm slice thickness. The success of haemostasis was graded as Grade 1 (haemostasis without adjuncts), Grade 2 (haemostasis with adjuncts) and Grade 3 (failed haemostasis needing rescue); Grades 1 and 2 were pooled as successful haemostasis. Statistical analysis was undertaken in Minitab 21 for Windows, particularly analysing calcification and its impact on the success of haemostasis. Results We evaluated 370 large-bore CFA accesses, distributed across two groups: Group A(64.9%, n=243) and Group B (35.1%, n=127), for a total of 205 endovascular procedures (93.1% (191) EVAR and 5.3% (11) TEVAR). The mean age was 74.9±8 years, predominantly males (88.2%, n=181). The average body mass index (BMI) was 28±5.8, with 20.9% (43) individuals having diabetes and 18.5% (37) current smokers. The mean sheath size OD was 16±2.5, with 4.5% (11) re-do groins in Group A and 6.2% (8) in Group B. Successful haemostasis was achieved in 91.8% (n=223) in Group A (44.8%, n=109 Grade 2) and 90.5% (n=115) in Group B (21%, n=27 Grade 2). Rescue operations were needed in 8.2% (20) in Group A and 9.1% (12) in Group B. Pseudoaneurysms developed more commonly in Grade 2 haemostasis with 9.9% (11) in Group A and 1.6% (2) in Group B (p=0.3). Anterior calcification was observed in 14.8% (36) in Group A and 18.8% (24) in Group B. In comparison, posterior calcification was present in 62.5% (152) in Group A and 66.9% (85) in Group B. Notably, calcification did not significantly impact haemostasis (p=0.79). Additional VCD deployment was necessary due to device failure in 4.5% (11) cases in Group A and 1.5% (2) cases in Group B. Conclusion The overall success rate was comparable between the two groups. However, Group A required more adjuncts to achieve successful haemostasis. The site of calcification did not impact the efficacy of closure devices. Pseudoaneurysm formation was more frequent when adjuncts were needed.

Artificial intelligence-based predictive models in vascular diseases.

Cardiovascular disease represents a source of major health problems worldwide, and although medical and technical advances have been achieved, they are still associated with high morbidity and mortality rates. Personalized medicine would benefit from novel tools to better predict individual prognosis and outcomes after intervention. Artificial intelligence (AI) has brought new insights to cardiovascular medicine, especially with the use of machine learning techniques that allow the identification of hidden patterns and complex associations in health data without any a priori assumptions. This review provides an overview on the use of artificial intelligence-based prediction models in vascular diseases, specifically focusing on aortic aneurysm, lower extremity arterial disease, and carotid stenosis. Potential benefits include the development of precision medicine in patients with vascular diseases. In addition, the main challenges that remain to be overcome to integrate artificial intelligence-based predictive models in clinical practice are discussed.

Artificial intelligence in vascular surgical decision making.

Despite advances in prevention, detection, and treatment, cardiovascular disease is a leading cause of mortality and represents a major health problem worldwide. Artificial intelligence and machine learning have brought new insights to the management of vascular diseases by allowing analysis of huge and complex datasets and by offering new techniques to develop advanced imaging analysis. Artificial intelligence-based applications have the potential to improve prognostic evaluation and evidence-based decision making and contribute to vascular therapeutic decision making. In this scoping review, we provide an overview on how artificial intelligence could help in vascular surgical clinical decision making, highlighting potential benefits, current limitations, and future challenges.

Machine Learning and Omics Analysis in Aortic Aneurysm.

Aortic aneurysm is a life-threatening condition and mechanisms underlying its formation and progression are still incompletely understood. Omics approach has brought new insights to identify a broad spectrum of biomarkers and better understand cellular and molecular pathways involved. Omics generate a large amount of data and several studies have highlighted that artificial intelligence (AI) and techniques such as machine learning (ML)/deep learning (DL) can be of use in analyzing such complex datasets. However, only a few studies have so far reported the use of ML/DL for omics analysis in aortic aneurysms. The aim of this study is to summarize recent advances on the use of ML/DL for omics analysis to decipher aortic aneurysm pathophysiology and develop patient-tailored risk prediction models. In the light of current knowledge, we discuss current limits and highlight future directions in the field.

Comprehensive Review of Natural Language Processing (NLP) in Vascular Surgery.

Objective: The use of Natural Language Processing (NLP) has attracted increased interest in healthcare with various potential applications including identification and extraction of health information, development of chatbots and virtual assistants. The aim of this comprehensive literature review was to provide an overview of NLP applications in vascular surgery, identify current limitations, and discuss future perspectives in the field. Data sources: The MEDLINE database was searched on April 2023. Review methods: The database was searched using a combination of keywords to identify studies reporting the use of NLP and chatbots in three main vascular diseases. Keywords used included Natural Language Processing, chatbot, chatGPT, aortic disease, carotid, peripheral artery disease, vascular, and vascular surgery. Results: Given the heterogeneity of study design, techniques, and aims, a comprehensive literature review was performed to provide an overview of NLP applications in vascular surgery. By enabling identification and extraction of information on patients with vascular diseases, such technology could help to analyse data from healthcare information systems to provide feedback on current practice and help in optimising patient care. In addition, chatbots and NLP driven techniques have the potential to be used as virtual assistants for both health professionals and patients. Conclusion: While Artificial Intelligence and NLP technology could be used to enhance care for patients with vascular diseases, many challenges remain including the need to define guidelines and clear consensus on how to evaluate and validate these innovations before their implementation into clinical practice.

Natural Language Processing for Literature Search in Vascular Surgery: A Pilot Study Testing an Artificial Intelligence Based Application.

Introduction: The use of natural language processing (NLP) for a literature search has been poorly investigated in vascular surgery so far. The aim of this pilot study was to test the applicability of an artificial intelligence (AI) based mobile application for literature searching in a topic related to vascular surgery. Technique: A focused scientific question was defined to evaluate the performance of the AI application for a literature search and compare the results with the ground truth provided via a traditional literature search performed by human experts. Using pre-defined keywords, the literature search was performed automatically by the AI application through different steps, including quality assessment based on evaluation of the information available and quality filters using indicators of level of evidence, selection of publications based on relevancy filters using NLP, summarisation, and visualisation of the publications via the mobile app. A traditional literature search performed by human experts required 10 hours to check 154 original articles, among which 26 (16.9%) were truly related to the question, 63 (40.9%) related to the field but not to the specific question, and 65 (42.2%) were unrelated. The AI based search was performed in less than one hour, and, compared with traditional search, the method identified 17 original articles (48.6%) truly related to the question (p < .010), 18 (51.4%) related to the field but not to the specific question (p = .26), and no unrelated publications (p < .001). Fifteen truly related articles (88.2%) were identified jointly by the two methods. No significant difference was observed regarding the median number of citations, year of publications, and impact factor of journals. Discussion: The AI based method enabled a targeted, focused, and time saving literature search, although the selection of publications was not completely exhaustive. These results suggest that such an AI driven application is a complementary tool to help researchers and clinicians for continuous education and dissemination of knowledge.

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.

Nationwide Study in France To Predict One Year Major Bleeding and Validate the OAC3-PAD Score in Patients Undergoing Revascularisation for Lower Extremity Arterial Disease.

OBJECTIVE: Antithrombotic strategies are currently recommended for the treatment of lower extremity artery disease (LEAD) but specific scores to assess the risk of bleeding in these patients are scarce. To fill the gap, the OAC3-PAD bleeding score was recently developed and validated in German cohorts. The aim of this study was to determine whether this score performs appropriately in another real world nationwide cohort. METHODS: This 10 year retrospective, multicentre study based on French national electronic health data included patients who underwent revascularisation for LEAD between January 2013 and June 2022. The OAC3-PAD score was calculated and from this, the population was classified into four groups: low, low to moderate, moderate to high and high risk. A binary logistic regression model was applied, with major bleeding occurring at one year (defined using the International Classification of Diseases ICD-10) as the dependent variable. The performance of the OAC3-PAD bleeding score was investigated using a receiver operating characteristic curve. RESULTS: Among 161 205 patients hospitalised for LEAD treatment in French institutions, the one year incidence of major bleeding was 13 672 patients (8.5%). The distribution of the population according to the OAC3-PAD bleeding score was: 88 835 patients (55.1%), 34 369 (21.3%), 27 914 (17.3%), and 10 087 (6.3%) in the low, low to moderate, moderate to high, and high risk groups, respectively; with an incidence of one year major bleeding of 5.0%, 9.8%, 13.2%, and 21.3%. The OAC3-PAD model achieved an AUC of 0.650 to predict one year major bleeding following LEAD repair (95% CI 0.645 - 0.655), with a sensitivity of 0.67 and a specificity of 0.57. CONCLUSION: This nationwide analysis confirmed the accuracy of the OAC3-PAD model to predict one year major bleeding and served as external validation. Although further studies are required, it adds evidence and perspectives to further generalise its use to guide the management of patients with LEAD.

Percutaneous mechanical thrombectomy for limb graft occlusion after endovascular aneurysm repair: Results of a case series.

OBJECTIVE: Limb graft occlusion (LGO) is a recognised complication after endovascular aneurysm repair (EVAR). We present outcomes of a case series of LGO treated by percutaneous mechanical thrombectomy (PMT). METHODS: Six male patients (mean age 70.5 ± 7.5 years) presented with LGO after EVAR (n = 4), fenestrated EVAR with an iliac branch device (n = 1), branched EVAR (n = 1). Median time to occlusion was 28.5(IQR 90) weeks; all occlusions were unilateral. The presenting symptom was intermittent claudication (n = 4), chronic limb-threatening ischaemia (n = 1) or acute limb ischaemia (n = 1). PMT was undertaken using the 10F Rotarex Rotational Excisional Atherectomy System (Becton, Dickinson and Company, Franklin Lakes, USA) with optional stenting/reline of the affected limb. RESULTS: LGO was cleared in all 6 cases by PMT with limb stenting (n = 4)/limb reline (n = 2)/outflow stenting (n = 2). Post-operatively, novel oral anticoagulant therapy supplemented prior antiplatelet therapy in all cases. Length of stay was 2 (IQR 19) days. All cleared limbs remain patent at median 15 (IQR 185) weeks follow-up. CONCLUSION: This case series indicates that percutaneous mechanical thrombectomy is associated with high technical success rates and subsequent acceptable ensuing short-to-midterm patency. This approach is a valid alternative to surgical interventions in such cases, and represents our primary approach when LGO is encountered after EVAR.

Mid-term outcomes of the use of endoanchors during thoracic endovascular aortic repair in multicentre analysis.

OBJECTIVE: To describe mid-term outcomes of the use of EndoAnchors as an adjunct for arch and thoracic endovascular aortic repair (TEVAR). METHODS: A retrospective multicentre series from nine centres using the Heli-FX EndoAnchor System (Medtronic Inc, Minneapolis, USA) at TEVAR over May 2014-May 2019 is presented. The study is registered at ClinicalTrials.gov with number NCT04100499. The primary outcome was freedom from Type I endoleak at EndoAnchors deployments; secondary outcomes included evaluation of aortic wall penetration (AWP) at first computed tomography scan, EndoAnchor-related issues and mortality. RESULTS: 54 high-risk patients (35 males/19 females, age 73 ± 11 years) with arch, thoracic and thoracoabdominal aneurysmal disease (3 chronic post-dissection and one patch pseudoaneurysm), with a mean neck length 19.7 ± 6.6 mm that were treated with multiple hybrid and endovascular techniques were included. A total of 329 EndoAnchors were used with a mean of 6.1 ± 2.5 per patient. Overall adequate AWP was 86%, whereas arch (Ishimaru's zones 0-2) deployments achieved 80.6% when compared to 87.3% in descending thoracic aorta (dTA); although there was no statistical significance. Freedom from type I endoleaks was 88% at 2 year follow-up, due to 4 type IA endoleaks, two of them successfully treated, one with conservative treatment due to complexity of repair and remaining patient died 1 year later due to endograft infection. There were reported five EndoAnchor-related issues; four losses and one renal stent-graft was crushed due to catheter deflection solved with balloon reinflation. None of the losses had clinical significance. Overall mortality is described for 7 (9.5%) patients, one of them aneurysm-related. CONCLUSIONS: The adjunctive use of EndoAnchors in TEVAR and complex TEVAR procedures achieved acceptable outcomes at midterm in a high-risk series with hostile seal zones. Still, they should be still judiciously used as there is lack of data to suggest a more liberal use; therefore, the landing zone should not be compromised in favour of their use.

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.