Deep learning method for aortic root detection

Tahoces, Pablo G.; Varela, Rafael Vergara; Carreira, J. M.

doi:10.1016/j.compbiomed.2021.104533

Cited by 9 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While our models have significantly faster run times than previous studies, image segmentation and model generation are still relatively slow and tedious processes. Improving the efficiency of image segmentation is the aim of many advanced computational studies that utilize machine learning and artificial intelligence tools 33–36 . Combining our FE workflow with automatic image segmentation would result in an improved clinical tool for assessing the risks of PPVI.…”

Section: Discussionmentioning

confidence: 99%

Finite element modeling with patient‐specific geometry to assess clinical risks of percutaneous pulmonary valve implantation

Donahue,

Westman,

Faanes

et al. 2024

Cathet Cardio Intervent

View full text Add to dashboard Cite

BackgroundPercutaneous pulmonary valve implantation (PPVI) is a non‐surgical treatment for right ventricular outflow tract (RVOT) dysfunction. During PPVI, a stented valve, delivered via catheter, replaces the dysfunctional pulmonary valve. Stent oversizing allows valve anchoring within the RVOT, but overexpansion can intrude on the surrounding structures. Potentially dangerous outcomes include aortic valve insufficiency (AVI) from aortic root (AR) distortion and myocardial ischemia from coronary artery (CA) compression. Currently, risks are evaluated via balloon angioplasty/sizing before stent deployment. Patient‐specific finite element (FE) analysis frameworks can improve pre‐procedural risk assessment, but current methods require hundreds of hours of high‐performance computation.MethodsWe created a simplified method to simulate the procedure using patient‐specific FE models for accurate, efficient pre‐procedural PPVI (using balloon expandable valves) risk assessment. The methodology was tested by retrospectively evaluating the clinical outcome of 12 PPVI candidates.ResultsOf 12 patients (median age 14.5 years) with dysfunctional RVOT, 7 had native RVOT and 5 had RV‐PA conduits. Seven patients had undergone successful RVOT stent/valve placement, three had significant AVI on balloon testing, one had left CA compression, and one had both AVI and left CA compression. A model‐calculated change of more than 20% in lumen diameter of the AR or coronary arteries correctly predicted aortic valve sufficiency and/or CA compression in all the patients.ConclusionAgreement between FE results and clinical outcomes is excellent. Additionally, these models run in 2–6 min on a desktop computer, demonstrating potential use of FE analysis for pre‐procedural risk assessment of PPVI in a clinically relevant timeframe.

show abstract

Section: Discussionmentioning

confidence: 99%

Finite element modeling with patient‐specific geometry to assess clinical risks of percutaneous pulmonary valve implantation

Donahue,

Westman,

Faanes

et al. 2024

Cathet Cardio Intervent

View full text Add to dashboard Cite

show abstract

“…In conclusion, we believe that our novel model provides an efficient and reliable method to screen MHCs from a large number of protein sequences. In the future, we will pay more attention to deep learning classifiers and evolution strategies ( Tahoces et al, 2021 ; Tandel et al, 2021 ; Tavolara et al, 2021 ; Togacar, 2021 ; Tsiknakis et al, 2021 ; Turki and Taguchi, 2021 ; Usman et al, 2021 ; Vafaeezadeh et al, 2021 ; Wang et al, 2021 ; Watanabe et al, 2021 ; Yap et al, 2021 ; Yildirim et al, 2021 ).…”

Section: Discussionmentioning

confidence: 99%

PredMHC: An Effective Predictor of Major Histocompatibility Complex Using Mixed Features

Chen

2022

Front. Genet.

View full text Add to dashboard Cite

The major histocompatibility complex (MHC) is a large locus on vertebrate DNA that contains a tightly linked set of polymorphic genes encoding cell surface proteins essential for the adaptive immune system. The groups of proteins encoded in the MHC play an important role in the adaptive immune system. Therefore, the accurate identification of the MHC is necessary to understand its role in the adaptive immune system. An effective predictor called PredMHC is established in this study to identify the MHC from protein sequences. Firstly, PredMHC encoded a protein sequence with mixed features including 188D, APAAC, KSCTriad, CKSAAGP, and PAAC. Secondly, three classifiers including SGD, SMO, and random forest were trained on the mixed features of the protein sequence. Finally, the prediction result was obtained by the voting of the three classifiers. The experimental results of the 10-fold cross-validation test in the training dataset showed that PredMHC can obtain 91.69% accuracy. Experimental results on comparison with other features, classifiers, and existing methods showed the effectiveness of PredMHC in predicting the MHC.

show abstract

“…The typical implementation of DL, Convolutional Neural Network (CNN), exploits the inherent representation of data and accurately fits the model. Although some studies applied CNN-based methods to aortic valve landmark detection, 10,11 due to the difficulty of directly dealing with large-scale CT volumes, they only focus on patch-based or region-of-interest (RoI) based approaches. Noothout et al 10 leveraged randomly sampled sub images (patches) as the model input, which ensures accuracy within local areas.…”

Section: Introductionmentioning

confidence: 99%

“…However, the patches lack global information and rely excessively on local context information, which leads that the voxel spacings of volumes greatly influence the detection results (modification in voxel spacings leads to more changes in local receptive fields while fewer changes in the global field). Tahoces et al 11 aimed to detect the aortic root through the localization of the landmark of the sinus of Valsalva (SOV). However, it requires two times of manual interventions of radiologists for prepositioning the heart region.…”

Section: Introductionmentioning

confidence: 99%

Fully-automatic aortic valve landmarks detection with two-stage-based convolutional neural networks

Lemarchand

Chan-Sock-Line

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

Aortic valve landmarks detection in Computed Tomography (CT) images is essential for planning Transcatheter Aortic Valve Implantation (TAVI) and establishing predictive factors of cardiac conduction disturbance. The fully automatic detection facilitates the measurement and planning while reducing interobserver variability. Although the emerged Convolutional Neural Networks (CNNs) have been applied to fully automatic landmark detection, it is challenging for CNNs to directly process large-scale CT volumes due to the limited computational resources. Some common preprocessing to deal with the limitation of resources, such as down-sampling or center cropping, can cause the volume to lose detailed features or global information. To address these issues, we propose a two-stage detection method based on CNN. The proposed method initially detects the approximate positions of the landmarks in the global view and then obtains refined results in local regions, without overdependence on prior knowledge or labor-intensive preprocessing. Eight important aortic valve landmarks, including three hinge points, three commissure points, the middle point of the cusps, and the point of the lower part of the membranous septum are automatically detected from our network. An overall result of Mean Radial Error (MRE) of 2.23 mm is yielded from our data set containing 150 individual cardiac CT volumes. The method takes 0.15 seconds per stage to process one volume, showing high efficiency.

show abstract

Deep learning method for aortic root detection

Cited by 9 publications

References 24 publications

Finite element modeling with patient‐specific geometry to assess clinical risks of percutaneous pulmonary valve implantation

Finite element modeling with patient‐specific geometry to assess clinical risks of percutaneous pulmonary valve implantation

PredMHC: An Effective Predictor of Major Histocompatibility Complex Using Mixed Features

Fully-automatic aortic valve landmarks detection with two-stage-based convolutional neural networks

Contact Info

Product

Resources

About