Advances in Auto-Segmentation Cardenas, Carlos E.; Yang, Jinzhong; Anderson, Brian M. ...
Seminars in radiation oncology,
July 2019, 2019-07-00, 20190701, Letnik:
29, Številka:
3
Journal Article
Recenzirano
Manual image segmentation is a time-consuming task routinely performed in radiotherapy to identify each patient's targets and anatomical structures. The efficacy and safety of the radiotherapy plan ...requires accurate segmentations as these regions of interest are generally used to optimize and assess the quality of the plan. However, reports have shown that this process can be subject to significant inter- and intraobserver variability. Furthermore, the quality of the radiotherapy treatment, and subsequent analyses (ie, radiomics, dosimetric), can be subject to the accuracy of these manual segmentations. Automatic segmentation (or auto-segmentation) of targets and normal tissues is, therefore, preferable as it would address these challenges. Previously, auto-segmentation techniques have been clustered into 3 generations of algorithms, with multiatlas based and hybrid techniques (third generation) being considered the state-of-the-art. More recently, however, the field of medical image segmentation has seen accelerated growth driven by advances in computer vision, particularly through the application of deep learning algorithms, suggesting we have entered the fourth generation of auto-segmentation algorithm development. In this paper, the authors review traditional (nondeep learning) algorithms particularly relevant for applications in radiotherapy. Concepts from deep learning are introduced focusing on convolutional neural networks and fully-convolutional networks which are generally used for segmentation tasks. Furthermore, the authors provide a summary of deep learning auto-segmentation radiotherapy applications reported in the literature. Lastly, considerations for clinical deployment (commissioning and QA) of auto-segmentation software are provided.
Coulomb Explosion of Multi-charged Atomic Alkaline Metal Clusters Donoso, Roberto; Cárdenas, Carlos; Fuentealba, Patricio
The journal of physical chemistry. A, Molecules, spectroscopy, kinetics, environment, & general theory,
04/2021, Letnik:
125, Številka:
12
Journal Article
Recenzirano
In the present work, a computational study of the Coulomb explosions of atomic metal clusters of the type X8 2+ was carried out, X = (Li–Cs). The work was done within the Kohn–Sham methodology using ...the Born–Oppenheimer molecular dynamics approximation. The dominant fission channels were established and the electron bonding patterns were analyzed with the help of the Electron Localization Function (ELF). A simple theoretical model was developed to understand and describe, in a qualitatively way, the main physical mechanism involved in the fission of these multicharged clusters. It has been found that the most possible fragments after explosion are the same considering the dynamics or the thermodynamics results. The bonds breaking and formation are well depicted by the ELF, and the main physical effects are well described by the developed model.
Context.
An accurate analysis of the physical-chemical conditions in the regions of the interstellar medium in which C
3
is observed requires knowing the collisional rate coefficients of this ...molecule with He, H
2
, electrons, and H.
Aims.
The main goals of this study are to present the first potential energy surface for the C
3
+H
2
complex, to study the dynamics of the system, and to report a set of rate coefficients at low temperature for the lower rotational states of C
3
with para- and ortho-H
2
.
Methods.
A large grid of ab initio energies was computed at the explicitly correlated coupled-cluster with single-, double-, and perturbative triple-excitation level of theory, together with the augmented correlation-consistent quadruple zeta basis set (CCSD(T)-F12a/aug-cc-pVQZ). This grid of energies was fit to an analytical function. The potential energy surface was employed in close-coupling calculations at low collisional energies.
Results.
We present a high-level four-dimensional potential energy surface (PES) for studying the collision of C
3
with H
2
. The global minimum of the surface is found in the linear HH-CCC configuration. Rotational deexcitation state-to-state cross sections of C
3
by collision with para- and ortho-H
2
are computed. Furthermore, a reduced two-dimensional surface is developed by averaging the surface over the orientation of H
2
. The cross sections for the collision with para-H
2
using this approximation and those from the four-dimensional PES agree excellently. Finally, a set of rotational rate coefficients for the collision of C
3
with para- and ortho-H
2
at low temperatures are reported.
Display omitted
► We explored Fukui potential at the nucleus as an alternative definition of the hardness. ► The Fukui potential recovers not only the correct trend of the hardness of atoms but also ...its values. ► It is surprising that the Fukui potential evaluated only in a point can give such a good description of the hardness.
The chemical hardness is, after the chemical potential, the most important concept in describing the chemical reactivity of atoms and molecules. Recently, we showed that the Fukui potential at the nucleus of an atom is proportional to its hardness. Based on this, we speculated that the Fukui potential at the nucleus could be an alternative definition of the hardness. In this Letter we verify that the Fukui potential successfully describe the hardness of atoms. It is surprising that a property that depends only on the density at the nucleus can give such a good description of the chemical hardness.
Purpose
To develop a head and neck normal structures autocontouring tool that could be used to automatically detect the errors in autocontours from a clinically validated autocontouring tool.
Methods
...An autocontouring tool based on convolutional neural networks (CNN) was developed for 16 normal structures of the head and neck and tested to identify the contour errors from a clinically validated multiatlas‐based autocontouring system (MACS). The computed tomography (CT) scans and clinical contours from 3495 patients were semiautomatically curated and used to train and validate the CNN‐based autocontouring tool. The final accuracy of the tool was evaluated by calculating the Sørensen–Dice similarity coefficients (DSC) and Hausdorff distances between the automatically generated contours and physician‐drawn contours on 174 internal and 24 external CT scans. Lastly, the CNN‐based tool was evaluated on 60 patients' CT scans to investigate the possibility to detect contouring failures. The contouring failures on these patients were classified as either minor or major errors. The criteria to detect contouring errors were determined by analyzing the DSC between the CNN‐ and MACS‐based contours under two independent scenarios: (a) contours with minor errors are clinically acceptable and (b) contours with minor errors are clinically unacceptable.
Results
The average DSC and Hausdorff distance of our CNN‐based tool was 98.4%/1.23 cm for brain, 89.1%/0.42 cm for eyes, 86.8%/1.28 cm for mandible, 86.4%/0.88 cm for brainstem, 83.4%/0.71 cm for spinal cord, 82.7%/1.37 cm for parotids, 80.7%/1.08 cm for esophagus, 71.7%/0.39 cm for lenses, 68.6%/0.72 for optic nerves, 66.4%/0.46 cm for cochleas, and 40.7%/0.96 cm for optic chiasm. With the error detection tool, the proportions of the clinically unacceptable MACS contours that were correctly detected were 0.99/0.80 on average except for the optic chiasm, when contours with minor errors are clinically acceptable/unacceptable, respectively. The proportions of the clinically acceptable MACS contours that were correctly detected were 0.81/0.60 on average except for the optic chiasm, when contours with minor errors are clinically acceptable/unacceptable, respectively.
Conclusion
Our CNN‐based autocontouring tool performed well on both the publically available and the internal datasets. Furthermore, our results show that CNN‐based algorithms are able to identify ill‐defined contours from a clinically validated and used multiatlas‐based autocontouring tool. Therefore, our CNN‐based tool can effectively perform automatic verification of MACS contours.
The production of renewable fuels by co-hydrotreating is considered a very promising solution to make use of the existing petroleum refining infrastructure. Differently to stand-alone hydrotreating, ...co-hydrotreating requires lower investment costs. To design a co-hydrotreating of vegetable oil and gas oil, various issues need to be properly examined. This work reports an extensive review and discussion of such issues to provide a clear understanding of the effects on feedstocks, operating conditions, catalysts, corrosion, and product quality. The discussion also includes the challenges for modeling and simulation of co-hydrotreating processes.
Purpose
Radiation therapy treatment planning is a time‐consuming and iterative manual process. Consequently, plan quality varies greatly between and within institutions. Artificial intelligence shows ...great promise in improving plan quality and reducing planning times. This technical note describes our participation in the American Association of Physicists in Medicine Open Knowledge‐Based Planning Challenge (OpenKBP), a competition to accurately predict radiation therapy dose distributions.
Methods
A three‐dimensional (3D) densely connected U‐Net with dilated convolutions was developed to predict 3D dose distributions given contoured CT images of head and neck patients as input. While traditional augmentation techniques such as rotations and translations were explored, it was found that training on random patches alone resulted in the greatest model performance. A custom‐weighted mean squared error loss function was employed. Finally, an ensemble of best‐performing networks was used to generate the final challenge predictions.
Results
Our team (SuperPod) placed second in the dose stream of the OpenKBP challenge. The average mean absolute difference between the predicted and clinical dose distributions of the testing dataset was 2.56 Gy. On average, the predicted normalized target DVH metrics were within 3% of the clinical plans, and the predicted organ at risk DVH metrics were within 2 Gy of the clinical plans.
Conclusions
The developed 3D dense dilated U‐Net architecture can accurately predict 3D radiotherapy dose distributions and can be used as part of a fully automated radiation therapy planning pipeline.
Timber piles have been used for a long time in bridges and marine structures. Many of these structures have exceeded their service life and require maintenance or repair because of deterioration. To ...address this issue, repair/retrofit techniques utilizing ultra-high-performance concrete (UHPC) can provide many advantages, such as minimizing repair material amounts and high durability because of its superior mechanical characteristics. This paper presents preliminary tests to comprehend the behavior of composite specimens made of timber and UHPC, including the load transfer mechanism and load-carrying capacity. For load transfer between the timber pile and UHPC, push-off and slant shear tests were conducted on composite timber and UHPC specimens with different surface preparations for timber surfaces. It was concluded that because of the smoothness of the UHPC surface, mechanical connectors (nails) provided the highest interface shear strength between timber and UHPC. For the load-carrying capacity, several specimens were tested under compression loading and it was concluded that timber treatment before casting UHPC plays a vital role in restoring the load-carrying capacity of timber piles.
Display omitted
•Catalytic Enhancement with Small Bimetallic Clusters supported on ZrC and TiC(0 0 1)•Spillover Phenomenon and Thermodynamically Favorable Migration of H.•Barrier-Free or Low-Energy ...Dissociation using Bimetallic clusters supported on TMCs.•Polarity-Driven Activation Using Bimetallic Cluster on TMCs for activate and dissociate H2.
The adsorption and dissociation of hydrogen on bimetallic clusters of AuxPt4-x supported on TiC (0 0 1) and ZrC (0 0 1) surfaces, has been studied using periodic boundary density functional theory (DFT). Simulations reveal that H2 exhibits moderate adsorption energies on AuxPt4-x/TMC (TM = Ti and Zr) systems and dissociates with a tiny barrier comparable to archetypal catalyst such as Pt (0 0 1). The incorporation of two different metal atoms (Au and Pt) in the cluster results in a noticeable enhancement of catalytic activity compared to clusters of equivalent size composed of pure metals like Pd, Cu, and Pt when deposited on TiC (0 0 1). Furthermore, our calculations reveal that the adsorbed H atom on the AuPt3 cluster is prone to spill over the C sites on both surfaces, and the migration of hydrogen atoms on both supports is thermodynamically favorable. In essence, our results provide compelling evidence that when AuxPt4-x clusters are supported on surfaces with a significant degree of polarity, as TMCs, the complete system H2/AuxPt4-x/TMC can efficiently activate and dissociate H2 concurrently, highlighting the potential for enhanced catalytic efficiency in hydrogenation reactions.