Traditional Artificial Neural Networks Versus Deep Learning in Optimization of Material Aspects of 3D Printing.
Ontology highlight
ABSTRACT:
SUBMITTER: Rojek I
PROVIDER: S-EPMC8707385 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The aim of this work was to investigate effects of the formulation factors on tablet printability as well as to optimize and predict extended drug release from cross-linked polymeric ibuprofen printlets using an artificial neural network (ANN). Printlets were printed using digital light processing (DLP) technology from formulations containing polyethylene glycol diacrylate, polyethylene glycol, and water in concentrations according to D-optimal mixture design and 0.1% w/w riboflavin and 5% w/w ibuprofen. It was observed that with higher water content longer exposure time was required for successful printing. For understanding the effects of excipients and printing parameters on drug dissolution rate in DLP printlets two different neural networks were developed with using two commercially available softwares. After comparison of experimental and predicted values of in vitro dissolution at the corresponding time points for optimized formulation, the R2 experimental vs. predicted value was 0.9811 (neural network 1) and 0.9960 (neural network 2). According to difference f1 and similarity factor f2 (f1 = 14.30 and f2 = 52.15) neural network 1 with supervised multilayer perceptron, backpropagation algorithm, and linear activation function gave a similar dissolution profile to obtained experimental results, indicating that adequate ANN is able to set out an input-output relationship in DLP printing of pharmaceutics.
| S-EPMC6835658 | biostudies-literature
Project description:Material informatics (MI) is a promising approach to liberate us from the time-consuming Edisonian (trial and error) process for material discoveries, driven by machine-learning algorithms. Several descriptors, which are encoded material features to feed computers, were proposed in the last few decades. Especially to solid systems, however, their insufficient representations of three dimensionality of field quantities such as electron distributions and local potentials have critically hindered broad and practical successes of the solid-state MI. We develop a simple, generic 3D voxel descriptor that compacts any field quantities, in such a suitable way to implement convolutional neural networks (CNNs). We examine the 3D voxel descriptor encoded from the electron distribution by a regression test with 680 oxides data. The present scheme outperforms other existing descriptors in the prediction of Hartree energies that are significantly relevant to the long-wavelength distribution of the valence electrons. The results indicate that this scheme can forecast any functionals of field quantities just by learning sufficient amount of data, if there is an explicit correlation between the target properties and field quantities. This 3D descriptor opens a way to import prominent CNNs-based algorithms of supervised, semi-supervised and reinforcement learnings into the solid-state MI.
| S-EPMC5717226 | biostudies-literature
Project description:BackgroundFor difficult or rare procedures, simulation offers an opportunity to provide education and training. In developing an adequate model to utilize in simulation, 3D printing has emerged as a useful technology to provide detailed, accessible, and high-fidelity models. Nasal osteotomy is an essential step in many rhinoplasty surgeries, yet it can be challenging to perform and difficult to receive adequate exposure to this nuanced portion of the procedure. As it currently stands, there are limited opportunities to practice nasal osteotomy due to the reliance on cadaveric bones, which are expensive, difficult to obtain, and require appropriate facilities and personnel. While previous designs have been developed, these models leave room for improvement in printing efficiency, cost, and material performance. This manuscript aims to describe the methodology for the design of an updated nasal osteotomy training model derived from anatomic data and optimized for printability, usability, and fidelity. Additionally, an analysis of multiple commercially available 3D printing materials and technologies was conducted to determine which offered superior equivalency to bone.MethodsThis model was updated from a first-generation model previously described to include a more usable base and form, reduce irrelevant structures, and optimize geometry for 3D printing, while maintaining the nasal bones with added stabilizers essential for function and fidelity. For the material comparison, this updated model was printed in five materials: Ultimaker Polylactic Acid, 3D Printlife ALGA, 3DXTECH SimuBone, FibreTuff, and FormLabs Durable V2. Facial plastic surgeons tested the models in a blinded, randomized fashion and completed surveys assessing tactile feedback, audio feedback, material limitation, and overall value.ResultsA model optimizing printability while maintaining quality in the area of interest was developed. In the material comparison, SimuBone emerged as the top choice amongst the evaluating physicians in an experience-based subjective comparison to human bone during a simulated osteotomy procedure using the updated model.ConclusionThe updated midface model that was user-centered, low-cost, and printable was designed. In material testing, Simubone was rated above other materials to have a more realistic feel.
| S-EPMC10339601 | biostudies-literature
Project description:Additive manufacturing technologies, including three-dimensional printing (3DP), have unlocked new possibilities for bone tissue engineering. Long-term regeneration of normal anatomic structure, shape, and function is clinically important subsequent to bone trauma, tumor, infection, nonunion after fracture, or congenital abnormality. Due to the great complexity in structure and properties of bone across the population, along with variation in the type of injury or defect, currently available treatments for larger bone defects that support load often fail in replicating the anatomic shape and structure of the lost bone tissue. 3DP could provide the ability to print bone substitute materials with a controlled chemistry, shape, porosity, and topography, thus allowing printing of personalized bone grafts customized to the patient and the specific clinical condition. 3DP and related fabrication approaches of bone grafts may one day revolutionize the way clinicians currently treat bone defects. This article gives a brief overview of the current advances in 3DP and existing materials with an emphasis on ceramics used for 3DP of bone scaffolds. Furthermore, it addresses some of the current limitations of this technique and discusses potential future directions and strategies for improving fabrication of personalized artificial bone constructs.
| S-EPMC4981149 | biostudies-other
Project description:Material extrusion is the most widespread additive manufacturing method but its application in end-use products is limited by vulnerability to errors. Humans can detect errors but cannot provide continuous monitoring or real-time correction. Existing automated approaches are not generalisable across different parts, materials, and printing systems. We train a multi-head neural network using images automatically labelled by deviation from optimal printing parameters. The automation of data acquisition and labelling allows the generation of a large and varied extrusion 3D printing dataset, containing 1.2 million images from 192 different parts labelled with printing parameters. The thus trained neural network, alongside a control loop, enables real-time detection and rapid correction of diverse errors that is effective across many different 2D and 3D geometries, materials, printers, toolpaths, and even extrusion methods. We additionally create visualisations of the network's predictions to shed light on how it makes decisions.
| S-EPMC9378646 | biostudies-literature
Project description:A main challenge in drug discovery is finding molecules with a desirable balance of multiple properties. Here, we focus on the task of molecular optimization, where the goal is to optimize a given starting molecule towards desirable properties. This task can be framed as a machine translation problem in natural language processing, where in our case, a molecule is translated into a molecule with optimized properties based on the SMILES representation. Typically, chemists would use their intuition to suggest chemical transformations for the starting molecule being optimized. A widely used strategy is the concept of matched molecular pairs where two molecules differ by a single transformation. We seek to capture the chemist's intuition from matched molecular pairs using machine translation models. Specifically, the sequence-to-sequence model with attention mechanism, and the Transformer model are employed to generate molecules with desirable properties. As a proof of concept, three ADMET properties are optimized simultaneously: logD, solubility, and clearance, which are important properties of a drug. Since desirable properties often vary from project to project, the user-specified desirable property changes are incorporated into the input as an additional condition together with the starting molecules being optimized. Thus, the models can be guided to generate molecules satisfying the desirable properties. Additionally, we compare the two machine translation models based on the SMILES representation, with a graph-to-graph translation model HierG2G, which has shown the state-of-the-art performance in molecular optimization. Our results show that the Transformer can generate more molecules with desirable properties by making small modifications to the given starting molecules, which can be intuitive to chemists. A further enrichment of diverse molecules can be achieved by using an ensemble of models.
| S-EPMC7980633 | biostudies-literature
Project description:The 3D printing of fluorescent materials could help develop, validate, and translate imaging technologies, including systems for fluorescence-guided surgery. Despite advances in 3D printing techniques for optical targets, no comprehensive method has been demonstrated for the simultaneous incorporation of fluorophores and fine-tuning of absorption and scattering properties. Here, we introduce a photopolymer-based 3D printing method for manufacturing fluorescent material with tunable optical properties. The results demonstrate the ability to 3D print various individual fluorophores at reasonably high fluorescence yields, including IR-125, quantum dots, methylene blue, and rhodamine 590. Furthermore, tuning of the absorption and reduced scattering coefficients is demonstrated within the relevant mamalian soft tissue coefficient ranges of 0.005-0.05 mm-1 and 0.2-1.5 mm-1, respectively. Fabrication of fluorophore-doped biomimicking and complex geometric structures validated the ability to print feature sizes less than 200 μm. The presented methods and optical characterization techniques provide the foundation for the manufacturing of solid 3D printed fluorescent structures, with direct relevance to biomedical optics and the broad adoption of fast manufacturing methods in fluorescence imaging.
| S-EPMC8384872 | biostudies-literature
Project description:MotivationMany important cellular processes involve physical interactions of proteins. Therefore, determining protein quaternary structures provide critical insights for understanding molecular mechanisms of functions of the complexes. To complement experimental methods, many computational methods have been developed to predict structures of protein complexes. One of the challenges in computational protein complex structure prediction is to identify near-native models from a large pool of generated models.ResultsWe developed a convolutional deep neural network-based approach named DOcking decoy selection with Voxel-based deep neural nEtwork (DOVE) for evaluating protein docking models. To evaluate a protein docking model, DOVE scans the protein-protein interface of the model with a 3D voxel and considers atomic interaction types and their energetic contributions as input features applied to the neural network. The deep learning models were trained and validated on docking models available in the ZDock and DockGround databases. Among the different combinations of features tested, almost all outperformed existing scoring functions.Availability and implementationCodes available at http://github.com/kiharalab/DOVE, http://kiharalab.org/dove/.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC7141855 | biostudies-literature
Project description:Visual scene category representations emerge very rapidly, yet the computational transformations that enable such invariant categorizations remain elusive. Deep convolutional neural networks (CNNs) perform visual categorization at near human-level accuracy using a feedforward architecture, providing neuroscientists with the opportunity to assess one successful series of representational transformations that enable categorization in silico. The goal of the current study is to assess the extent to which sequential scene category representations built by a CNN map onto those built in the human brain as assessed by high-density, time-resolved event-related potentials (ERPs). We found correspondence both over time and across the scalp: earlier (0-200 ms) ERP activity was best explained by early CNN layers at all electrodes. Although later activity at most electrode sites corresponded to earlier CNN layers, activity in right occipito-temporal electrodes was best explained by the later, fully-connected layers of the CNN around 225 ms post-stimulus, along with similar patterns in frontal electrodes. Taken together, these results suggest that the emergence of scene category representations develop through a dynamic interplay between early activity over occipital electrodes as well as later activity over temporal and frontal electrodes.
| S-EPMC6075788 | biostudies-literature
Project description:Purpose To develop and test an artificial intelligence (AI) system, based on deep convolutional neural networks (CNNs), for automated real-time triaging of adult chest radiographs on the basis of the urgency of imaging appearances. Materials and Methods An AI system was developed by using 470 388 fully anonymized institutional adult chest radiographs acquired from 2007 to 2017. The free-text radiology reports were preprocessed by using an in-house natural language processing (NLP) system modeling radiologic language. The NLP system analyzed the free-text report to prioritize each radiograph as critical, urgent, nonurgent, or normal. An AI system for computer vision using an ensemble of two deep CNNs was then trained by using labeled radiographs to predict the clinical priority from radiologic appearances only. The system's performance in radiograph prioritization was tested in a simulation by using an independent set of 15 887 radiographs. Prediction performance was assessed with the area under the receiver operating characteristic curve; sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were also determined. Nonparametric testing of the improvement in time to final report was determined at a nominal significance level of 5%. Results Normal chest radiographs were detected by our AI system with a sensitivity of 71%, specificity of 95%, PPV of 73%, and NPV of 94%. The average reporting delay was reduced from 11.2 to 2.7 days for critical imaging findings (P < .001) and from 7.6 to 4.1 days for urgent imaging findings (P < .001) in the simulation compared with historical data. Conclusion Automated real-time triaging of adult chest radiographs with use of an artificial intelligence system is feasible, with clinically acceptable performance. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Auffermann in this issue.
| S-EPMC6438359 | biostudies-literature