Classification of anatomic patterns of peripheral artery disease with automated machine learning (AutoML).

AIM: The aim of this study was to investigate the potential of novel automated machine learning (AutoML) in vascular medicine by developing a discriminative artificial intelligence (AI) model for the classification of anatomical patterns of peripheral artery disease (PAD). MATERIAL AND METHODS: Random open-source angiograms of lower limbs were collected using a web-indexed search. An experienced researcher in vascular medicine labelled the angiograms according to the most applicable grade of femoropopliteal disease in the Global Limb Anatomic Staging System (GLASS). An AutoML model was trained using the Vertex AI (Google Cloud) platform to classify the angiograms according to the GLASS grade with a multi-label algorithm. Following deployment, we conducted a test using 25 random angiograms (five from each GLASS grade). Model tuning through incremental training by introducing new angiograms was executed to the limit of the allocated quota following the initial evaluation to determine its effect on the software's performance. RESULTS: We collected 323 angiograms to create the AutoML model. Among these, 80 angiograms were labelled as grade 0 of femoropopliteal disease in GLASS, 114 as grade 1, 34 as grade 2, 25 as grade 3 and 70 as grade 4. After 4.5 h of training, the AI model was deployed. The AI self-assessed average precision was 0.77 (0 is minimal and 1 is maximal). During the testing phase, the AI model successfully determined the GLASS grade in 100% of the cases. The agreement with the researcher was almost perfect with the number of observed agreements being 22 (88%), Kappa = 0.85 (95% CI 0.69-1.0). The best results were achieved in predicting GLASS grade 0 and grade 4 (initial precision: 0.76 and 0.84). However, the AI model exhibited poorer results in classifying GLASS grade 3 (initial precision: 0.2) compared to other grades. Disagreements between the AI and the researcher were associated with the low resolution of the test images. Incremental training expanded the initial dataset by 23% to a total of 417 images, which improved the model's average precision by 11% to 0.86. CONCLUSION: After a brief training period with a limited dataset, AutoML has demonstrated its potential in identifying and classifying the anatomical patterns of PAD, operating unhindered by the factors that can affect human analysts, such as fatigue or lack of experience. This technology bears the potential to revolutionize outcome prediction and standardize evidence-based revascularization strategies for patients with PAD, leveraging its adaptability and ability to continuously improve with additional data. The pursuit of further research in AutoML within the field of vascular medicine is both promising and warranted. However, it necessitates additional financial support to realize its full potential.

Stroke rate after thoracic endovascular aortic repair using de-airing of stentgrafts with high-volume of saline solution.

Background: Our aim was to determine the rate of ischemic stroke following thoracic endovascular aortic repair (TEVAR) after reducing gas volume released during stentgraft deployment by de-airing of thoracic stentgrafts with high-volume of 0.9% heparinized saline solution. Patients and methods: A single center retrospective analysis of all consecutive patients undergoing TEVAR from 2014 to 2019 was performed. All thoracic stentgrafts were flushed with 120 ml 0.9% heparinized saline solution before implantation, according to our institutional protocol. Endpoints were in-hospital rates of ischemic stroke and spinal cord ischemia (SCI), and all-cause mortality. Results: One hundred and fifty-four patients (mean age: 66.8 ± 13.6 years, 64.9% males) were treated with TEVAR during the study period. Indications for treatment were thoracic aortic aneurysms (n = 75, 48.7%), acute type B aortic dissections (n = 46, 29.9%), aortic arch aneurysms and penetrating aortic ulcers (n = 28, 18.2%), and blunt traumatic aortic injuries (n = 5, 3.2%). Timing of procedure was urgent in 75 patients (48.7%). Proximal landing zone were zone 0-1-2 (n = 75, 48.7%), zone 3 (n = 66, 42.9%) and zone 4 (n = 13, 8.4%). Supra-aortic vessels were revascularized with custom-made fenestrated stentgrafts in 9 patients (5.8%), using chimney technique in 4 patients (2.6%), and with debranching procedures in 19 patients (12.3%). Left subclavian artery was covered without revascularization in 46 patients (29.9%). In-hospital stroke occurred in two patients (1.3%) and SCI in another two patients (1.3%). In-hospital mortality rate was 0.6%. No further in-hospital events were noted. Conclusions: De-airing of stentgrafts with high-volume of 0.9% heparinized saline solution seems to be safe and can be used as an adjunct to keep occurrence of neurological events after TEVAR as low as possible.

Type II endoleak and aortic aneurysm sac shrinkage after preemptive embolization of aneurysm sac side branches.

OBJECTIVE: Type II endoleak (T2EL) is the most common endoleak after endovascular aneurysm repair (EVAR). Its optimal management has been controversially discussed. Thus, preliminary selective embolization of aneurysm sac side branches (ASSBs) has been adopted to prevent T2EL. Our goal was to determine the rate of T2EL and the diameter decrease of abdominal aortic aneurysms (AAAs) after EVAR performed after preemptive embolization of ASSBs. METHODS: From September 2014 to September 2019, 139 patients with AAAs underwent percutaneous ASSB embolization before EVAR. Follow-up imaging studies were performed at 1 and 6 months and annually thereafter. The end points included freedom from T2EL, AAA sac shrinkage, T2EL-related reinterventions, and all-cause mortality. RESULTS: The mean follow-up was 23 ± 16 months (range, 1-61 months). The patients had had a median of five (range, one to eight) patent ASSBs found on preoperative imaging studies. After completion of embolization, 76.4% of the initially patent ASSBs were occluded, with no major procedure-related complications. Follow-up imaging studies showed T2ELs in seven patients (5%), with an aneurysm sac increase seen in six of these patients. The number of ASSBs remaining patent after embolization was the only discriminative factor in patients with and without T2EL. Six T2EL-related reinterventions were performed during follow-up. Most patients (n = 91; 86.7%) had experienced aneurysm sac shrinkage, and the mean diameter reduction was 9.2 ± 7.7 mm (P < .001) in all patients with follow-up data available. One aneurysm-related death occurred within 30 days after EVAR. CONCLUSIONS: Preemptive embolization of ASSBs for patients with AAAs is safe and effective in preventing T2ELs after EVAR. Aneurysm sac shrinkage was observed in a high proportion of patients.

[Current concepts of perforated sigmoid diverticulitis]. / Aktuelle Konzepte der perforierten Sigmadivertikulitis.

Despite modern therapeutical options,perforated sigma diverticulitis still represents a life-threatening disease. In terms of diagnostic and therapeutic proceeding, the covered perforation has to be distinguished from free perforation.Primary therapeutic objective is the excision of the inflamed bowel segment to avoid abdominal sepsis.Therapeutic options for covered perforation include conservative treatment with or without placement of interventional drains. A free perforated diverticulitis implies the resection of the perforated bowel segment. Primary anastomosis should be aspired. In advanced cases, Hartmann procedure may be required. Individual decision making should be based on individual risk profile, on peritonitis severity score and on surgeon experience. In a two stage procedure, relevant morbidity of the second operation has to be considered.Recently suggested approaches,laparoscopic lavage or interventional drainage without resection, remain a matter of debate.

A reliable tool to determine cell viability in complex 3-d culture: the acid phosphatase assay.

Cell-based assays are more complex than cell-free test systems but still reflect a highly artificial cellular environment. Incorporation of organotypic 3-dimensional (3-D) culture systems into mainstream drug development processes is increasingly discussed but severely limited by complex methodological requirements. The objective of this study was to explore a panel of standard assays to provide an easy-handling, standardized protocol for rapid routine analysis of cell survival in multicellular tumor spheroid-based antitumor drug testing. Spheroids of 2 colon carcinoma cell lines were characterized for evaluation. One of the assay systems tested could reliably be used to determine cell viability in spheroids. The authors verified that the acid phosphatase assay (APH) is applicable for single spheroids in 96-well plates, does not require spheroid dissociation, and is linear and highly sensitive for HT29 and HCT-116 spheroids up to diameters of 650 microm and 900 microm, consisting of 40,000 and 80,000 cells, respectively. Treatment of HT29 and HCT-116 cells with 5-fluorouracil, Irinotecan, and C-1311 revealed critically reduced drug efficacies in 3-D versus monolayer culture, which is discussed in light of literature data. The experimental protocol presented herein is a small but substantial contribution to the establishment of sophisticated 3-D in vitro systems in the antitumor drug screening scenario.