A Deep Learning Framework for Design and Analysis of Surgical Bioprosthetic Heart Valves

Balu, Aditya; Nallagonda, Sahiti; Xu, Fei; Krishnamurthy, Adarsh; Hsu, Ming‐Chen; Sarkar, Soumik

doi:10.1038/s41598-019-54707-9

Cited by 47 publications

(27 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these technologies can be updated or replaced through advancements in augmented reality (AR), 3D printing, and deep learning (DL) [19]. Specifically, by making use of the information gathered about blood vessels through AR and DL, materials like PLA [156], polydiolcitrate [94], or metallic glasses [181] can be 3D printed into cardiovascular devices with more distinct designs than commercially available ones [19,[182][183][184][185].…”

Section: Future Perspectivesmentioning

confidence: 99%

Cardiovascular Stents: A Review of Past, Current, and Emerging Devices

et al. 2021

View full text Add to dashboard Cite

One of the leading causes of morbidity and mortality worldwide is coronary artery disease, a condition characterized by the narrowing of the artery due to plaque deposits. The standard of care for treating this disease is the introduction of a stent at the lesion site. This life-saving tubular device ensures vessel support, keeping the blood-flow path open so that the cardiac muscle receives its vital nutrients and oxygen supply. Several generations of stents have been iteratively developed towards improving patient outcomes and diminishing adverse side effects following the implanting procedure. Moving from bare-metal stents to drug-eluting stents, and recently reaching bioresorbable stents, this research field is under continuous development. To keep up with how stent technology has advanced in the past few decades, this paper reviews the evolution of these devices, focusing on how they can be further optimized towards creating an ideal vascular scaffold.

show abstract

Section: Future Perspectivesmentioning

confidence: 99%

Cardiovascular Stents: A Review of Past, Current, and Emerging Devices

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For Bioprosthetic valves, ML applications are mainly focused on valve geometric reconstruction and critical geometric decision [44][45][46][47]. Moreover, research utilizes the autoencoder-based ML method to optimize the design of transcatheter aortic valves and explores valve deformation behavior [48,49]. The main objective of ML applications in AV is to correlate the AV critical geometric information to its functionality and bypass the complex and time-consuming computational analysis and clinical experiments.…”

Section: Machine Learning Application For Biological Materialsmentioning

confidence: 99%

A Review for Machine Learning Applications in Characterizing Biomaterials and Biological Materials Properties

Li¹

2021

AJBSR

View full text Add to dashboard Cite

Characterizing specific mechanical properties for biological materials and biomaterials remains an exciting topic within several research fields. The functionality of biological materials and biomaterials relies on their mechanical properties, such as elastic and shear modulus. While several sophisticated experimental techniques can perform in vivo and in vitro to characterize the material properties, the measurement exhibits a broad uncertainty due to the limitations in diagnostics and experimental randomness. Alternatively, Machine learning approaches evolve as an efficient and striking tool to process a massive amount of complex data sets simultaneously and discover the hidden correlation between the materials structure and dynamic responses. This work briefly reviews the advanced applications of machine learning algorithms in studies of the dynamic behavior of biological materials and the development of biomaterials. It is evident that machine learning approaches can significantly impact the clinical development in biomedical engineering and healthcare.

show abstract

“…In this context, recent advances in the field of deep learning and scientific machine learning show promise for solving inverse design problems [6][7][8][9][10][11][12] . Particularly promising are Generative Adversarial Networks (GANs) 13 , a class of generative deep learning models.…”

Section: Introductionmentioning

confidence: 99%

Fast inverse design of microstructures via generative invariance networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

The problem of efficient design of material microstructures exhibiting desired properties spans a variety of engineering and science applications. An ability to rapidly generate microstructures that exhibit user-specified property distributions transforms the iterative process of traditional microstructure-sensitive design. We reformulate the microstructure design process as a constrained Generative Adversarial Network (GAN). This approach explicitly encodes invariance constraints within a GAN to generate two-phase morphologies for photovoltaic applications obeying design specifications: specifically, various short circuit current density and fill-factor combinations. Such invariance constraints can be represented by deep learning-based surrogates of full physics models mapping microstructure to photovoltaic properties. To circumvent data generation bottlenecks, we utilize a multi-fidelity surrogate that reduces the requirements of expensive labels by 5X. Our approach enables fast generation of microstructures (in ≈190ms) with user-defined properties. Such physics-aware data-driven methods for inverse design problems are expected to democratize and accelerate the field of microstructure-sensitive design.

show abstract

A Deep Learning Framework for Design and Analysis of Surgical Bioprosthetic Heart Valves

Cited by 47 publications

References 53 publications

Cardiovascular Stents: A Review of Past, Current, and Emerging Devices

Cardiovascular Stents: A Review of Past, Current, and Emerging Devices

A Review for Machine Learning Applications in Characterizing Biomaterials and Biological Materials Properties

Fast inverse design of microstructures via generative invariance networks

Contact Info

Product

Resources

About