STL Model Research Articles

A novel 3D-printed brachytherapy applicator and Monte Carlo model for the treatment of conjunctival tumors

PurposeTo develop a custom low dose rate brachytherapy applicator for the treatment of conjunctival malignancies which leverages 3D-printing technology to provide enhanced design flexibility and availability. MethodsAn elliptical shell applicator inspired by the ocular surgery post-operation conformer shells was developed for the placement of the applicator around the cornea of the eye, with a central hole provide patient comfort. The applicator featured two concentric circles of slots for iodine-125 seeds, providing customization of the dose distribution depending on the location of the target. The applicator was modeled using computer-aided design software. The resultant model STL file was used for 3D printing of the applicator and the development of a Monte Carlo model of the applicator and its dose distribution. ResultsThe applicator was successfully 3D printed using biocompatible resin, which could be sterilized for treatment after manual source loading. A Geant4 model of the applicator was created directly from the STL model and was applied to a phantom to estimate the dose distribution delivered by the applicator. The toroidal dose distribution allowed for treatment of the conjunctiva while reducing dose to the cornea compared to traditional eye plaque designs. ConclusionsA custom 3D-printed applicator was successfully developed and modeled for the treatment of conjunctival malignancies. This novel applicator design potentially provides higher quality, more customizable dose distributions for patients and the simplicity of the design makes it accessible for any clinic with 3D-printing technology.

3D printing turbine slicing path optimization based on FDM technology

Abstract In 3D printing technology, optimizing the slicing path is very important for printing efficiency and forming quality. In this study, the slicing path of the turbine STL model in 3D printing based on FDM technology is optimized. By improving the traditional slicing algorithm, data redundancy is reduced, and the efficiency of path generation is improved. An index-based optimization slicing algorithm is proposed, which effectively improves the efficiency of the algorithm, reduces the system consumption, and achieves more efficient slicing processing.

Assessment of cone-beam CT technical image quality indicators and radiation dose for optimal STL model used in visual surgical planning.

The aim of this study was to identify cone-beam computed tomography (CBCT) protocols that offer an optimal balance between effective dose (ED) and 3D model for orthognathic virtual surgery planning, using CT as a reference, and to assess whether such protocols can be defined based on technical image quality metrics. Eleven CBCT (VISO G7, Planmeca Oy, Helsinki, Finland) scan protocols were selected out of 32 candidate protocols, based on ED and technical image quality measurements. Next, an anthropomorphic RANDO SK150 phantom was scanned using these 11 CBCT protocols and 2 CT scanners for bone quantity assessments. The resulting DICOM (Digital Imaging and Communications in Medicine) files were converted into Standard Tessellation Language (STL) models that were used for bone volume and area measurements in the predefined orbital region to assess the validity of each CBCT protocol for virtual surgical planning. The highest CBCT bone volume and area of the STL models were obtained using normal dose protocol (F2) and ultra-low dose protocol (J13), which resulted in 48% and 96% of the mean STL bone volume and 48% and 95% of the bone area measured on CT scanners, respectively. The normal dose CBCT protocol "F2" offered optimal bone area and volume balance for STL. The optimal CBCT protocol can be defined using contrast-to-noise ratio and modulation transfer function values that were similar to those of the reference CT scanners'. CBCT scanners with selected protocols can offer a viable alternative to CT scanners for acquiring STL models for virtual surgical planning at a lower effective dose.

Hybrid Path Generation Method for Multi-Axis Laser Metal Deposition of Overhanging Thin-Walled Structures.

Additive manufacturing has advantages over other traditional manufacturing technologies for the fabrication of complex thin-walled parts. Previous correlation path strategies, when applied to laser metal deposition processes, suffer from contour deposition transboundary and surface "scar" type overstacking. Therefore, this paper proposes a hybrid path generation method for the laser metal deposition process. First, the topological logic of the STL model of the part is restored to reduce redundant calculations at the stage of obtaining the layered contour. Then, the path points are planned on the basis of the offset contours in a helical upward trend to form a globally continuous composite path in space considering the melt channel width. Finally, vectors that adaptively fit to the model surface are generated for the path points as tool orientations and they are optimized by smoothing the rotation angles. The results of experiments conducted on a multi-axis machine equipped with a laser metal deposition module show that the path generated by the proposed method is not only capable of thin-walled structures with overhanging and curved surface features but also improves the surface imperfections of the part due to sudden changes in the angle of rotation while ensuring the boundary dimensions.

A Bayesian expert system for additive manufacturing design assessment

AbstractTools for analysing additive manufacturability often employ complex models that lack transparency; this impedes user understanding and has detrimental effects on the implementation of results. An expert system tool that transparently learns features for successful printing has been created. The tool uses accessible data from STL models and printer configurations to create explainable parameters and identify risks. Testing has shown good agreement to print behaviour and easy adaptability. The tool reduces the learning curves designers face in understanding design for additive manufacturing.

Quality Assessment and Comparison of 3D-Printed and Milled Zirconia Anterior Crowns and Veneers: In Vitro Pilot Study

AbstractThe esthetic rehabilitation of a patient is a demanding yet rewarding procedure, improving the form, function, and well-being of a patient. Three-dimensional (3D) printed, or additive manufactured, zirconia has recently entered the dental space, but without a thorough assessment or comparison. This pilot study utilized digital impressions of two demonstration casts: Cast 1 prepared both central incisors for full ceramic crown coverage, while cast 2 had a lateral incisor (#22) prepared for a ceramic veneer. Both casts underwent digital scanning (Straumann CARES 3, Straumann, Basel, Switzerland) to create virtual STL models. Cast 1 had two full zirconia anterior crowns digitally designed, and Cast 2 had a zirconia veneer digitally designed, using Exocad GmbH software by a certified dental technician at Schulich Dentistry. The STL files were used for fabricating six milled zirconia crowns for central incisor (#21) and six 3D-printed zirconia crowns for the other central incisor (#11). Similarly, for Cast 2, milled and 3D-printed zirconia veneers were made for the prepared lateral incisor (#22). Statistical analysis employed Minitab 16.1.0 software to construct a 2 × 2 table for cross-tabulation and chi-squared analysis. This statistical approach assessed the relationship between restoration design and processing method. Cochran–Mantel–Haenszel test evaluated categorical variables considering different classification variables. Milled restorations showed minor variations, while 3D-printed units displayed consistency. Statistical tests found no significant associations. This in vitro study suggests 3D-printed zirconia for crowns and veneers meets precementation standards akin to conventionally milled restorations. Further research can assess its potential benefits for dentistry's efficiency, cost, and sustainability.

Virtual Surgical Planning for Temporomandibular Joint Reconstruction with Stock TMJ Prostheses: Pilot Study.

The temporomandibular joint (TMJ) is one of the most complex joints in the human anatomy. In advanced degenerative stages, conservative or minimally invasive surgical therapies have failed to restore joint function, and joint replacement with prostheses has been required. Stock prostheses, compared to custom-made prostheses, are much less expensive and require less pre-operative preparation time. Four patients followed for years for temporomandibular dysfunction and previously operated on by arthroscopy or open joint surgery that have been reconstructed with stock TMJ prostheses (STMJP) through virtual surgical planning (VSP) and an STL model with surgical and positioning guides were included. The median follow-up was 15 months; the median number of previous TMJ surgeries was 2. The mean preoperative MIO was 24.6 mm and at longest follow-up was 36.4 mm. The median preoperative TMJ pain score was 8, and the median postoperative TMJ pain was 3. All patients have improved their mandibular function with a clear improvement of their initial situation. In conclusion, we believe that stock TMJ prostheses with virtual surgical planning and surgical guides are a good alternative for TMJ reconstruction at the present time. Nonetheless, prospective and randomized trials are required with long-term follow up to assess their performance and safety.

Comparison of accuracy of immediate implant placement between planned and actual position in pre-extractive versus conventional method - A prospective study

This study aims to evaluate the accuracy of immediate implants in mandibular molars between the conventional method and the pre-extractive inter-radicular method. Materials and methodsA total of 20 patients were equally divided into two groups. Implants were placed using the conventional method (Group A) and pre-extractive inte-rradicular method (Group B). Coronal, apical and angular deviation between planned and placed implants were evaluated by superimposing preoperative and postoperative three-dimensional (3D) STL models in Geomagic Freeform software. The data were subjected to an unpaired Student t-test. ResultsResults revealed that the coronal, apical and angular deviation were lower in the pre-extractive inter-radicular drilling method than in the conventional method, which was statistically significant. Apical deviation was greater than coronal deviation in both the sagittal and coronal planes. It was also found that the mean deviation was greater in the sagittal plane (mesio-distal axis) than in the coronal plane (bucco-lingual axis). ConclusionComparison of the two methods revealed significant changes between the planned and actual positions of implant. When stringent steps were followed, the degree of deviation was found to be less in the pre-extractive inter-radicular approach, proving it to be more accurate than the conventional method. However, large-scale research studies are required to extrapolate our findings.

An Emotion-Aware Multitask Approach to Fake News and Rumor Detection Using Transfer Learning

Social networking sites, blogs, and online articles are instant sources of news for internet users globally. However, in the absence of strict regulations mandating the genuineness of every text on social media, it is probable that some of these texts are fake news or rumors. Their deceptive nature and ability to propagate instantly can have an adverse effect on society. This necessitates the need for more effective detection of fake news and rumors on the web. In this work, we annotate four fake news detection (EFN) and rumor detection datasets with their emotion class labels using transfer learning. We show the correlation between the legitimacy of a text with its intrinsic emotion for fake news and rumor detection, and prove that even within the same emotion class, fake and real news are often represented differently, which can be used for improved feature extraction. Based on this, we propose a multitask framework for fake news and rumor detection, predicting both the emotion and legitimacy of the text. We train a variety of deep learning models in single-task (STL) and multitask settings for a more comprehensive comparison. We further analyze the performance of our multitask approach for EFN in cross-domain settings to verify its efficacy for better generalization across datasets, and to verify that emotions act as a domain-independent feature. Experimental results verify that our multitask models consistently outperform their STL counterparts in terms of accuracy, precision, recall, and F1 score, both for in-domain and cross-domain settings. We also qualitatively analyze the difference in performance in STL and multitask learning (MTL) models.

Research on adaptive slicing method for optimizing STL model manufacturing details

Research on adaptive slicing method for optimizing STL model manufacturing details

A layerwise geometric error compensation procedure for additive manufacturing

PurposeThe purpose of this paper is to provide a new procedure for in-plane compensation of geometric errors that often appear in the layers deposited by an additive manufacturing (AM) process when building a part, regardless of the complexity of the layer geometry.Design/methodology/approachThe procedure is based on comparing the real layer contours to the nominal ones extracted from the STL model of the part. Considering alignment and form deviations, the compensation algorithm generates new compensated contours that match the nominal ones as closely as possible. To assess the compensation effectiveness, two case studies were analysed. In the first case, the parts were not manufactured, but the distortions were simulated using a predictive model. In the second example, the test part was actually manufactured, and the distortions were measured on a coordinate measuring machine.FindingsThe geometric deviations detected in both case studies, as evaluated by various quality indicators, reduced significantly after applying the compensation procedure, meaning that the compensated and nominal contours were better matched both in shape and size.Research limitations/implicationsAlthough large contours showed deviations close to zero, dimensional overcompensation was observed when applied to small contours. The compensation procedure could be enhanced if the applied compensation factor took into account the contour size of the analysed layer and other geometric parameters that could have an influence.Originality/valueThe presented method of compensation is applicable to layers of any shape obtained in any AM process.

Application and Development of 3D Printing Technology in Clothing Design

Abstract As traditional hand knitting is limited, it can only make simple three-dimensional stacking and flat knitting texture of the garment. This paper applies 3D printing technology to improve this drawback. Establishing research variables for clothing design by combining the geometric characteristics of the STL model after layering with the characteristics of 3D printing technology to construct an optimization model for 3D printing technology. The contradiction between molding quality and molding efficiency is a typical multi-factor and multi-objective optimization problem. To solve this kind of optimization problem, a genetic algorithm is used to search for the optimal solution of the objective function in the feasible domain space, aiming to optimize the parameters of 3D printing technology. An in-depth analysis of the application practice of 3D printing technology in apparel design is presented, which further points out the implementation architecture of apparel design incorporating 3D printing technology, and the performance test of apparel incorporating 3D printing technology is carried out. The data show that the average values of ST (thickness difference), B1 (warp bending stiffness), B2 (weft bending stiffness), E51 (warp elongation), and E52 (weft elongation) are 8.386mm, 5.22 μNm, 0.16 μNm, 0.421%, 0.252%, which indicates that the garments designed based on 3D printing technology have good tensile properties and hand feel appearance, and are more in line with the comfort and aesthetic demands of consumers for garment design. It shows that the garments designed using 3D printing technology have good stretchability and a hand-feel appearance, which is more in line with the comfort and aesthetic demands of consumers nowadays.

Evaluation of efficacy, treatment outcome, and stability of tooth movement with clear aligner treatment (Mysmartalign) - Clinical study

The study was conducted to evaluate the efficacy, treatment outcomes, and stability of tooth movement with clear aligner therapy. Fifty subjects were selected for aligner treatment and followed a retention protocol as instructed by the orthodontist. To calculate efficacy, changes in Little's Irregularity Index from T0 to T4, T0 to T6, and T0 to T8 of clinical plaster models were compared with STL models for both the maxilla and mandible. A comparison of pre-treatment and posttreatment PAR scores was performed to assess treatment outcomes. Stability was evaluated using the PAR score by comparing post-treatment and one-year follow-up study casts. An independent t-test was used to compare the mean values acquired from the same sample. The mean change in Little's Irregularity Index from T0 to T4, T0 to T6, and T0 to T8 of clinical plaster models was compared with software STL models for both the maxilla and mandible. It was observed that the mean change was greater in the clinical models at each stage. Treatment outcomes showed significant improvement for 16 subjects (32%), while 34 subjects (68%) also showed improvement. A paired t-test was conducted to assess stability between post-treatment and the one-year follow-up, and the results were not statistically significant. The software models overestimated alignment and the resolution of crowding when compared to the actual clinical plaster models. Consequently, the PAR score assessment indicated successful treatment outcomes. However, regarding stability, mild relapses were observed after the one-year follow-up.

Guided Genioplasty: Comparison between Conventional Technique and Customized Guided Surgery.

Genioplasty as an isolated surgical technique is a highly demanded procedure in the maxillofacial surgery area. Advances in facial reconstructive surgery have been associated with less morbidity and more predictable results. In this paper, "conventional" genioplasty and genioplasty by means of virtual surgical planning (VSP), CAD-CAM cutting guides, and patient custom-made plates are compared. A descriptive observational study was designed and implemented, and 43 patients were treated, differentiating two groups according to the technique: 18 patients were treated by conventional surgery, and 25 patients were treated through virtual surgical planning (VSP), CAD-CAM cutting guides, STL models, and titanium patient-specific plates. The operation time ranged from 35 to 107 min. The mean operative time in the conventional group was 60.06 + 3.74 min.; in the custom treatment group it was 42.24 + 1.29 min (p < 0.001). The difference between planned and obtained chin changes in cases of advancement or retrusion was not statistically significant (p = 0.125; p = 0.216). In cases of chin rotation due to asymmetry, guided and personalized surgery was superior to conventional surgery (p < 0.01). The mean hospital stay was equal in both groups. A decrease in surgical complications was observed in the group undergoing VSP and customized treatment. Multi-stage implementation of VSP with CAD-CAM cutting guides, STL models, and patient-specific plates increased the accuracy of the genioplasty surgery, particularly in cases of chin asymmetry, reducing operation time and potential complications.

Short-term wind power forecasting based on multivariate/multi-step LSTM with temporal feature attention mechanism

Precision enhancement for short-term wind power forecasting can alleviate negative impact of the forecasting results on wind power generation. Due to complexities and nonlinearities among factors and facets in wind power, it is essential to achieve reliable and stable power generation via the long short-term memory (LSTM) forecasting. To this purpose, multi-task temporal feature attention (MTTFA) based LSTM, namely MTTFA-LSTM, is proposed for multivariate/multi-step wind power forecasting with historical power and meteorological data, in which task-sharing and task-specifying layers are designed for task co-features extracting and task specifics discriminating, respectively. More specifically, in the task-sharing layer, multi-dimensional inputs are fed into LSTM to extract long-term trends, while in the task-specifying layer, one-dimensional convolution operations extract temporal features hidden in each and all time steps. Furthermore, an attention mechanism is adopted to adaptively tune weights for temporal features. Finally, the proposed model is leveraged to cope with different short-term wind power forecasting (SWPF) problems based on the national renewable energy laboratory’s (NREL) wind power data. Simulation results show that the proposed MTTFA-LSTM achieves persistent excellent forecasting accuracy, comparing its backbone STL model, TFA-LSTM as well as the benchmark MTL models in the same setting, which indicate that the complex and non-linear interdependencies among multi-dimensional data can be well depicted by the proposed model.

Quantitative analysis of zirconia and titanium implant artefacts in three-dimensional virtual models of multi-slice CT and cone beam CT: does scan protocol matter?

Artefacts from dental implants in three-dimensional (3D) imaging may lead to incorrect representation of anatomical dimensions and impede virtual planning in navigated implantology. The aim of this study was quantitative assessment of artefacts in 3D STL models from cone beam CT (CBCT) and multislice CT (MSCT) using different scanning protocols and titanium-zirconium (Ti-Zr) and zirconium (ZrO2) implant materials. Three ZrO2 and three Ti-Zr implants were respectively placed in the mandibles of two fresh human specimens. Before (baseline) and after implant placement, 3D digital imaging scans were performed (10 repetitions per timepoint: voxel size 0.2 mm³ and 0.3 mm³ for CBCT; 80 and 140 kV in MSCT). DICOM data were converted into 3D STL models and evaluated in computer-aided design software. After precise merging of the baseline and post-op models, the surface deviation was calculated, representing the extent of artefacts in the 3D models. Compared with baseline, ZrO2 emitted 36.5-37.3% (±0.6-0.8) artefacts in the CBCT and 39.2-50.2% (±0.5-1.2) in the MSCT models. Ti-Zr implants produced 4.1-7.1% (±0.3-3.0) artefacts in CBCT and 5.4-15.7% (±0.5-1.3) in MSCT. Significantly more artefacts were found in the MSCT vs CBCT models for both implant materials (p < 0.05). Significantly fewer artefacts were visible in the 3D models from scans with higher kilovolts in MSCT and smaller voxel size in CBCT. Among the four applied protocols, the lowest artefact proportion of ZrO2 and Ti-Zr implants in STL models was observed with CBCT and the 0.3 mm³ voxel size.

Volumetric Assessment of Lisfranc Joint and Spaces in Hallux Valgus Deformity Patients: A Case- Control Study

Category: Midfoot/Forefoot; Bunion Introduction/Purpose: First ray or medial column instability has been linked to the development of hallux valgus deformity (HVD), in part due to potential instability of Lisfranc joints and ligamentous complex. However, no study has assessed the 3D weight- bearing (WB) relationship of the Lisfranc complex in patients with confirmed hallux valgus, particularly at the articulating surface of the first tarsometatarsal joint and the second metatarsal and medial cuneiform space, commonly described as the primary region- of-interest of the Lisfranc complex. In this case-control study, we aimed to assesses WB 3D volumetric measurements in the entire Lisfranc joint, as well as in between first and second rays, and to compare HVD patients and controls. We hypothesized that volumes would be increased in HVD patients. Methods: In this IRB-approved, retrospective case-control study, we analyzed weight-bearing Computed Tomography (WBCT) data of 20 consecutive HVD patients and 20 healthy control patients. Using an automated segmentation method (DISIOR Bonelogic 2.0, Paragon28, USA), 3D volumetric models of the bones of the foot were created from WBCT data. Opposing articular spaces in the Lisfranc joint were selected on the STL models of the bones. Interarticular distance mapping was then performed to characterize the joint space width (JSW) in each of the articulations. Interarticular volume was then assessed using an area-weighted volume measurement. Areas of each triangle from the triangulated surface were multiplied by the JSW at each triangle. The sum of individual volumes was then normalized by the total surface area. The final volume was estimated using the product of the normalized summation and average area of both surfaces. Comparisons were performed with independent t-tests. P-Values &lt; 0.05 were considered significant. Results: Estimates of volumetric assessment of the Lisfranc Complex were obtained using the automated method written in MATLAB. These outputs are reported in Table 1. As expected, the first tarsometatarsal joint volumes were the highest for both HVD patients and controls. No significant differences in the volumes were observed when comparing HVD patients and controls for any of the joints or spaces assessed (Figure). Particularly, no differences in the volumetric analysis of the first tarsometatarsal joint, 1-2 intercuneiform space or Lisfranc space (medial cuneiform-second metatarsal) were confirmed. Conclusion: In this retrospective case-control study, we hypothesized that joint volumes of the articulating surfaces and spaces-of- interest within the Lisfranc complex would be higher in HVD patients, consistent with first ray/medial column instability. Our study results demonstrated however no significant volume increases in Lisfranc joints or spaces assessed, particularly with no increases in the volumetric measurements at the first tarsometatarsal joint or between first and second rays. Even though our study could be underpowered to demonstrate potential differences between HVD and controls, our results support that no significant first ray instability in present when volumetric WBCT assessment is used.

Intercuneiform Instability is Present in Midfoot Arthritis Patients: A 3D Volumetric Case-Control Assessment

Category: Midfoot/Forefoot; Trauma Introduction/Purpose: Lisfranc complex stability, primarily coming from the tarsometatarsal ligaments, is crucial for midfoot integrity. It has been shown that Lisfranc injuries can lead to midfoot issues, such as midfoot arthritis when not properly diagnosed/treated. Previous studies have estimated the volumes of the articulating joint volumes of surgically confirmed Lisfranc Ligament injuries, but no study has assessed articulating joints and space-of-interest of the Lisfranc Complex in patients with midfoot arthritis. The objective of this retrospective study was to determine if patients with confirmed midfoot arthritis have increased volumes at the Lisfranc complex when compared to controls, particularly between the first and second rays. We hypothesized that volumes would be increased in midfoot arthritis patients, consistent with medial column/first ray instability. Methods: In this IRB-approved, retrospective case-control study, we analyzed WBCT data of 20 consecutive midfoot arthritis patients and 20 healthy controls. Using an automated segmentation method (DISIOR Bonelogic 2.0, Paragon28, USA), 3D volumetric models of the bones of the foot were created from WBCT data. Opposing articular spaces in the Lisfranc joint of the midfoot were selected on the STL models of the bones. Interarticular distance mapping was then performed to characterize the joint space width (JSW) in each of the articulations. Interarticular volume was then estimated using an area-weighted volume measurement. Areas of each triangle from the triangulated surface were multiplied by the JSW at each triangle. The sum of individual volumes was then normalized by the total surface area. The final volume was estimated using the product of the normalized summation and average area of both surfaces. Comparisons were performed with independent t-tests. P-values &gt;0.05 were considered significant. Results: Estimates of joint volume were obtained using the automated method written in MATLAB. These outputs are reported in Table 1. Significant increase of approximately 25% was observed in Midfoot arthritis patients at the 1-2 intercuneiform joint, consistent with intercuneiform instability. Conversely, a decrease in the space between the second metatarsal and medial cuneiform of about 30% was observed, what could be explained by pronation of the first ray secondary to first ray instability. All other changes in joint volumes were not significant (Figure). Conclusion: In this case-control study with midfoot arthritis patients and healthy controls we performed a 3D volumetric assessment of the Lisfranc Complex joints and spaces-of-interest. We found that midfoot arthritis patients have a significant increase in the 1-2 intercuneiform joint consistent with intercuneiform instability. Conversely, a decrease in the Lisfranc space (in between second metatarsal and medial cuneiform) was observed, what could be explained by first ray pronation in the setting of medial column instability. Additional prospective studies assessing angular measurements and patient reported outcomes are needed.

A customized anthropomorphic 3D-printed phantom to reproducibility assessment in computed tomography: an oncological case study.

Studies on computed tomography (CT) reproducibility at different acquisition parameters have to take into account radiation dose administered and related ethical issues. 3D-printed phantoms provide the possibility to investigate these features deeply and to foster CT research, also taking advantage by outperforming new generation scanners. The aim of this study is to propose a new anthropomorphic 3D-printed phantom for chest lesions, tailored on a real patient CT scan, to investigate the variability of volume and Hounsfield Unit (HU) measurements at different CT acquisition parameters. The chest CT of a 75-year-old patient with a paramediastinal lung lesion was segmented based on an eight-compartment approach related to HU ranges (air lung, lung interstitium, fat, muscle, vascular, skin, bone, and lesion). From each mask produced, the 3D.stl model was exported and linked to a different printing infill value, based on a preliminary test and HU ratios derived from the patient scan. Fused deposition modeling (FDM) technology printing was chosen with filament materials in polylactic acid (PLA). Phantom was acquired at 50 mAs and three different tube voltages of 80, 100, and 120 kVp on two different scanners, namely, Siemens Somatom Force (Siemens Healthineers, Erlangen, Germany; same setting of real patient for 80 kVp acquisition) and GE 750 HD CT (GE Healthcare, Chicago, IL). The same segmentation workflow was then applied on each phantom acquisition after coregistration pipeline, and Dice Similarity Coefficient (DSC) and HU averages were extracted and compared for each compartment. DSC comparison among real patient versus phantom scans at different kVp, and on both CT scanners, demonstrated a good overlap of different compartments and lesion vascularization with a higher similarity for lung and lesion masks for each setting (about 0.9 and 0.8, respectively). Although mean HU was not comparable with real data, due to the PLA material, the proportion of intensity values for each compartment remains respected. The proposed approach demonstrated the reliability of 3D-printed technology for personalized approaches in CT research, opening to the application of the same workflow to other oncological fields.

Applicability of energy consumption prediction models in a department store: A case study

Obtaining an accurate picture of energy consumption in public spaces is a critical first step for predicting and enhancing energy efficiency. In practice, such calculations are often complicated, necessitating use of artificial intelligence models which can account for multiple factors. In this study, we obtained four years of daily electricity usage, people flow, and ambient factor data from a department store in Taiwan to build an artificial intelligence model for predicting energy consumption. Previous literature on public spaces have mainly used Long Short-Term Memory (LSTM), gated recurrent unit (GRU), and other recurrent neural network (RNN) mechanisms. However, as our dataset spanned four years, we hypothesized that seasonal and trend decomposition using Loess (STL) was applicable as our data likely exhibited long cyclic patterns. We built and compared prediction results of three neural networks: LSTM-classic, STL, and GRU. As expected, the STL model provided better overall results (indicating a strong seasonality component in our data), as well as an optimal balance between accuracy and processing time. This case study provides a framework for others seeking to build neural networks for predicting and managing energy consumption in public spaces, and forms a theoretical basis for further discussion of energy efficiency topics.