Radiologists' Field Guide to Retrievable and Convertible Inferior Vena Cava Filters

Winokur, Ronald S.; Bassik, Noy; Madoff, David C.; Trost, David

doi:10.2214/ajr.19.21722

Cited by 7 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The copyright holder for this preprint this version posted June 8, 2020. ; https://doi.org/10.1101/2020.06.06.20124321 doi: medRxiv preprint 6 Ni et al previously demonstrated that a deep learning model can accurately classify 14 different types of filters with an overall accuracy of 97.1% (135/139) in their test set [9]. The overall accuracy was 85.0% (51/60) for the test set in this study.…”

Section: Discussionsupporting

confidence: 50%

“…One task that could feasibly be facilitated by ML algorithms is the identification of inferior vena cava (IVC) filters on radiographic images, owing to their fixed filter design and metallic density. With the increased awareness of IVC filter complications, knowledge of the exact filter type is important for providers, diagnostic radiologists, and interventional radiologists in determining appropriate patient management [5][6][7]. Plain radiography is often the first step in evaluating patients who have a history of filter placement.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feasibility and visualization of deep learning detection and classification of inferior vena cava filters

Park

Sotirchos

Adleberg

et al. 2020

Preprint

View full text Add to dashboard Cite

Purpose: This study assesses the feasibility of deep learning detection and classification of 3 retrievable inferior vena cava filters with similar radiographic appearances and emphasizes the importance of visualization methods to confirm proper detection and classification. Materials and Methods: The fast.ai library with ResNet-34 architecture was used to train a deep learning classification model. A total of 442 fluoroscopic images (N=144 patients) from inferior vena cava filter placement or removal were collected. Following image preprocessing, the training set included 382 images (110 Celect, 149 Denali, 123 Gunther Tulip), of which 80% were used for training and 20% for validation. Data augmentation was performed for regularization. A random test set of 60 images (20 images of each filter type), not included in the training or validation set, was used for evaluation. Total accuracy and receiver operating characteristic area under the curve were used to evaluate performance. Feature heatmaps were visualized using guided backpropagation and gradient-weighted class activation mapping. Results: The overall accuracy was 80.2% with mean receiver operating characteristic area under the curve of 0.96 for the validation set (N=76), and 85.0% with mean receiver operating characteristic area under the curve of 0.94 for the test set (N=60). Two visualization methods were used to assess correct filter detection and classification. Conclusions: A deep learning model can be used to automatically detect and accurately classify inferior vena cava filters on radiographic images. Visualization techniques should be utilized to ensure deep learning models function as intended.

show abstract

Section: Discussionsupporting

confidence: 50%

Section: Introductionmentioning

confidence: 99%

Feasibility and visualization of deep learning detection and classification of inferior vena cava filters

Park

Sotirchos

Adleberg

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…36 Since 2000, several retrievable filters were cleared by the FDA, with the goal of easier retrieval after a period of time, commonly via endovascular techniques and by an apical retrieval hook on the device. 37 More recently, temporary filters became available. These devices are typically connected to a central venous line and are planned to be kept in place for only a few days.…”

Section: Ivc Reconstructionmentioning

confidence: 99%

Developmental or Procedural Vena Cava Interruption and Venous Thromboembolism: A Review

Bikdeli,

Sadeghipour,

Lou

et al. 2024

Semin Thromb Hemost

View full text Add to dashboard Cite

The inferior vena cava (IVC) and superior vena cava are the main conduits of the systemic venous circulation into the right atrium. Developmental or procedural interruptions of vena cava might predispose to stasis and deep vein thrombosis (DVT) distal to the anomaly and may impact the subsequent rate of pulmonary embolism (PE). This study aimed to review the various etiologies of developmental or procedural vena cava interruption and their impact on venous thromboembolism. A systematic search was performed in PubMed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines per each clinical question. For management questions with no high-quality evidence and no mutual agreements between authors, Delphi methods were used. IVC agenesis is the most common form of congenital vena cava interruption, is associated with an increased risk of DVT, and should be suspected in young patients with unexpected extensive bilateral DVT. Surgical techniques for vena cava interruption (ligation, clipping, and plication) to prevent PE have been largely abandoned due to short-term procedural risks and long-term complications, although survivors of prior procedures are occasionally encountered. Vena cava filters are now the most commonly used method of procedural interruption, frequently placed in the infrarenal IVC. The most agreed-upon indication for vena cava filters is for patients with acute venous thromboembolism and coexisting contraindications to anticoagulation. Familiarity with different forms of vena cava interruption and their local and systemic adverse effects is important to minimize complications and thrombotic events.

show abstract

“…Filters have been widely used in clinical practice for more than 50 years now [13], and are mainly categorized into permanent and temporary types from a clinical use perspective [14]. Temporary filters have a lower incidence of adverse events than permanent filters [15].…”

Section: Introductionmentioning

confidence: 99%

“…1. The VenaTech filter is an IVCF with more flexible time limit for preventing PE, simpler conversion operation and positive effect, and is suitable for use in IVC diameters of up to 28 mm [13,16,17]. Therefore, the VenaTech filter is the most commonly used, and was chosen as the subject of this study.…”

Section: Introductionmentioning

confidence: 99%

CFD Study on Hemodynamic Characteristics of Inferior Vena Cava Filter Affected by Blood Vessel Diameter

Zhang,

Song,

Wang

et al. 2023

Molecular &Amp; Cellular Biomechanics

View full text Add to dashboard Cite

Pulmonary embolism (PE), caused by deep venous thrombosis (DVT), is a disease with high morbidity and mortality. Implantation of inferior vena cava filters is an important method for the clinical prevention of PE. The hemodynamic characteristics of filters implanted in the inferior vena cava (IVC) have a significant impact on their performance. However, IVC diameters vary among patients. This may have a direct impact on the hemodynamic properties of the filter. At present, there is no research on this kind of problem to be investigated. In this paper, the hemodynamic properties of the VenaTech convertible filter were simulated in three different IVC models of 15, 20 and 25 mm diameters, using computational fluid dynamics (CFD) as a control variable (only the IVC diameter is varied). The results showed that the diameter has a significant impact on the hemodynamic characteristics after filter implantation. The IVC diameter has a great influence on the stagnation zone of the blood flow, the maximum wall shear stress (WSS) on the upstream side along the filter wire, and the flow resistance. The case of 15 mm diameter was the most prone to thrombus formation downstream of the filter head in the IVC, but the larger WSS on the upstream along the filter wire may facilitate thrombus lysis. Therefore, the change in vessel diameter should be considered when performing filter implantation for patients.

show abstract

Radiologists' Field Guide to Retrievable and Convertible Inferior Vena Cava Filters

Cited by 7 publications

References 15 publications

Feasibility and visualization of deep learning detection and classification of inferior vena cava filters

Feasibility and visualization of deep learning detection and classification of inferior vena cava filters

Developmental or Procedural Vena Cava Interruption and Venous Thromboembolism: A Review

CFD Study on Hemodynamic Characteristics of Inferior Vena Cava Filter Affected by Blood Vessel Diameter

Contact Info

Product

Resources

About