scholarly journals Deep learning for guidewire detection in intravascular ultrasound images

2021 ◽  
Vol 7 (1) ◽  
pp. 106-110
Author(s):  
Lennart Bargsten ◽  
Daniel Klisch ◽  
Katharina A. Riedl ◽  
Tobias Wissel ◽  
Fabian J. Brunner ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intravascular Ultrasound ◽  
Hausdorff Distance ◽  
Area Under Curve ◽  
Ground Truth ◽  
Automated Analysis ◽  
Ultrasound Images ◽  
Percutaneous Coronary Interventions ◽  
Task Learning ◽  
Percutaneous Coronary

Abstract Algorithms for automated analysis of intravascular ultrasound (IVUS) images can be disturbed by guidewires, which are often encountered when treating bifurcations in percutaneous coronary interventions. Detecting guidewires in advance can therefore help avoiding potential errors. This task is not trivial, since guidewires appear rather small compared to other relevant objects in IVUS images. We employed CNNs with additional multi-task learning as well as different guidewire-specific regularizations to enable and improve guidewire detection. In this context, we developed a network block which generates heatmaps that highlight guidewires without the need of localization annotations. The guidewire detection results reach values of 0.931 in terms of the F1-score and 0.996 in terms of area under curve (AUC). Comparing thresholded guidewire heatmaps with ground truth segmentation masks leads to a Dice score of 23.1 % and an average Hausdorff distance of 1.45 mm. Guidewire detection has proven to be a task that CNNs can handle quite well. Employing multi-task learning and guidewire-specific regularizations further improve detection results and enable generation of heatmaps that indicate the position of guidewires without actual labels.

scholarly journals Deep learning for calcium segmentation in intravascular ultrasound images

2021 ◽  
Vol 7 (1) ◽  
pp. 96-100
Author(s):  
Lennart Bargsten ◽  
Katharina A. Riedl ◽  
Tobias Wissel ◽  
Fabian J. Brunner ◽  
Klaus Schaefers ◽  
...  
Keyword(s):  
Intravascular Ultrasound ◽  
Hausdorff Distance ◽  
Automatic Segmentation ◽  
Image Data ◽  
Ultrasound Images ◽  
Dice Coefficient ◽  
Clinical Workflow ◽  
Auxiliary Data ◽  
Training Approach ◽  
Percutaneous Coronary

Abstract Knowing the shape of vascular calcifications is crucial for appropriate planning and conductance of percutaneous coronary interventions. The clinical workflow can therefore benefit from automatic segmentation of calcified plaques in intravascular ultrasound (IVUS) images. To solve segmentation problems with convolutional neural networks (CNNs), large datasets are usually required. However, datasets are often rather small in the medical domain. Hence, developing and investigating methods for increasing CNN performance on small datasets can help on the way towards clinically relevant results. We compared two state-of-the-art CNN architectures for segmentation, U-Net and DeepLabV3, and investigated how incorporating auxiliary image data with vessel wall and lumen annotations improves the calcium segmentation performance by using these either for pretraining or multi-task training. DeepLabV3 outperforms U-Net with up to 6.3 % by means of the Dice coefficient and 36.5 % by means of the average Hausdorff distance. Using auxiliary data improves the segmentation performance in both cases, whereas the multi-task approach outperforms the pre-training approach. The improvements of the multi-task approach in contrast to not using auxiliary data at all is 5.7 % for the Dice coefficient and 42.9 % for the average Hausdorff distance. Automatic segmentation of calcified plaques in IVUS images is a demanding task due to their relatively small size compared to the image dimensions and due to visual ambiguities with other image structures. We showed that this problem can generally be tackled by CNNs. Furthermore, we were able to improve the performance by a multi-task learning approach with auxiliary segmentation data.

Intravascular ultrasound guidance to minimize the use of contrast in percutaneous coronary interventions in diabetic patients with chronic stable angina

QJM ◽  
2021 ◽  
Vol 114 (Supplement_1) ◽  
Author(s):  
Mohamed Abdelfattah Marey ◽  
Hisham Ammar Mohamed ◽  
Ahmed Abdol Moneim Rezq ◽  
Ramy Raymond Elias
Keyword(s):  
Contrast Agent ◽  
Intravascular Ultrasound ◽  
Stable Angina ◽  
Ultrasound Guidance ◽  
Chronic Stable Angina ◽  
Diabetic Patients ◽  
Percutaneous Coronary Interventions ◽  
Coronary Interventions ◽  
Imaging Tool ◽  
Percutaneous Coronary

Abstract Objective To evaluate the impact of Intravascular ultrasound guidance on the final volume of contrast agent utilized in diabetic patients undergoing PCI for chronic stable angina. Background To date, few approaches have been described to reduce the final dose of contrast agent in percutaneous coronary interventions (PCI). We hypothesized that intravascular ultrasound (IVUS) might serve as an adjuctive imaging tool in many steps during PCI, thereby reducing the use of iodine contrast. Methods A total of 100 Diabeic Egyptian patients were selected to angiography-guided PCI or IVUSguided PCI from June 2019 to January 2020 .The study type was case control and non consecutive . Both groups were treated according to a pre-defined meticulous procedural strategy. A written informed consent was taken from all patients.The primary endpoint was the total volume contrast agent used during PCI. Patients were followed clinically for an average of 6 months. Results The median total volume of contrast was 111.65 ml (interquartile range [IQR] 170.40 ± 52.91ml , range from 100 ml to 300 ml) in angiography-guided group vs. 56.99 ml (IQR 94.70 ± 19.28ml , range from 70 ml to 180 ml) in IVUS-guided group (p < 0.001).similary, the median total volume of contrast was 111.65 ml (interquartile range [IQR] 170.40 ± 52.91ml , range from 100 ml to 300 ml) in angiographyguided group vs. 56.99 ml (IQR 94.70 ± 19.28ml , range from 70 ml to 180 ml) in IVUS-guided group (p < 0.001).In-hospital and 6 month outcomes were not different between patients randomized to angiography-guided and IVUS-guided PCI according to : Death, Acute myocardial infarction, Unplanned revascularization, Stent thrombosis. Conclusions Thoughtful and extensive utilization of IVUS as the primary imaging tool to guide PCI is safe, and markedly reduces the volume of iodine contrast, compared to angiography alone guidance.

scholarly journals Intracoronary beta-irradiation 24 hours after percutaneous coronary interventions: A serial volumetric intravascular ultrasound study

2003 ◽  
Vol 41 (6) ◽  
pp. 38
Author(s):  
Christos S. Katsouras ◽  
Georgios E. Bozios ◽  
Lampros K. Michalis ◽  
John Kalef-Ezra ◽  
Dimitris Patsouras ◽  
...  
Keyword(s):  
Intravascular Ultrasound ◽  
Percutaneous Coronary Interventions ◽  
Coronary Interventions ◽  
Ultrasound Study ◽  
Percutaneous Coronary

scholarly journals Intravascular ultrasound-guided percutaneous coronary interventions in contemporary practice

2009 ◽  
Vol 102 (2) ◽  
pp. 143-151 ◽  
Author(s):  
Laurent Bonello ◽  
Axel De Labriolle ◽  
Gilles Lemesle ◽  
Probal Roy ◽  
Daniel H. Steinberg ◽  
...  
Keyword(s):  
Intravascular Ultrasound ◽  
Percutaneous Coronary Interventions ◽  
Ultrasound Guided ◽  
Coronary Interventions ◽  
Percutaneous Coronary ◽  
Contemporary Practice

scholarly journals Optical Coherence Tomography Versus Intravascular Ultrasound and Angiography to Guide Percutaneous Coronary Interventions

2021 ◽  
Vol 14 (3) ◽  
Author(s):  
Daniel Chamié ◽  
J. Ribamar Costa ◽  
Lucas P. Damiani ◽  
Dimytri Siqueira ◽  
Sérgio Braga ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Intravascular Ultrasound ◽  
Elastic Membrane ◽  
Complication Rates ◽  
Percutaneous Coronary Interventions ◽  
Optical Coherence ◽  
Coronary Interventions ◽  
Stent Expansion ◽  
Percutaneous Coronary ◽  
External Elastic Membrane

Background: Specific algorithms for use of optical coherence tomography (OCT) to guide percutaneous coronary intervention (PCI) are scarce. Also, the relative benefits of intravascular imaging guidance have not been tested against an optimized angiography-guided PCI strategy. In iSIGHT (Optical Coherence Tomography Versus Intravascular Ultrasound and Angiography to Guide Percutaneous Coronary Interventions), we aimed to investigate whether OCT-guided PCI achieves noninferior stent expansion compared with intravascular ultrasound (IVUS) guidance and if both imaging modalities lead to superior stent expansion compared with an optimized angiography-based strategy. Methods: Patients ≥18 years old undergoing PCI for ≥1 lesion in native coronaries of 2.25 to 4.00 mm in diameter were randomized 1:1:1 to OCT-, IVUS-, or angiography-guided PCI. Predetermined guidance protocols were applied in all groups. An external elastic membrane–based protocol was used for stent sizing by OCT and IVUS. The primary end point was noninferiority of stent expansion (minimum stent area ≥90% of the average reference lumen area), measured by post-PCI OCT, in OCT-guided versus IVUS-guided PCI (noninferiority margin, 6.5%). Results: One hundred fifty-one patients (156 lesions) were randomly allocated to OCT (51 lesions [32.7%]), IVUS (52 lesions [33.3%]), or angiography (53 lesions [34.0%]). Stent expansion with OCT guidance (98.01±16.14%) was noninferior to IVUS (91.69±15.75%; 1-sided lower 95% CI, 0.55 mm 2 ; P non-inferiority <0.001) and superior to angiography (90.53±14.84%, P =0.041). IVUS and angiography obtained similar stent expansions ( P =0.921). Stent edge dissection and periprocedural complication rates were not significantly different among the groups. Conclusions: Stent expansion with OCT guidance using a dedicated external elastic membrane–based sizing strategy was noninferior to that achieved with IVUS and superior to an optimized angiographic strategy. Registration: URL: plataformabrasil.saude.gov.br ; Unique identifier: 69968417.8.0000.5462.

Sign in / Sign up

Export Citation Format

Share Document