课程文献中心 更多>>

关键词： Computer-aided design   computer-aided manufacturing   Orthodontic treatment   Bonded retainer   Breakage   Fixed orthodontic appliances  

摘要： PurposeTo compare failure rates and maximum load capacity (F-max) of six different computer-aided design/computer-aided manufacturing (CAD/CAM) retainers with those of the hand-bent five-stranded stainless steel twistflex retainer.Materials and methodsSix groups (n = 8 per group) of commercially available CAD/CAM retainers (cobalt-chromium [CoCr titanium grade 5 [Ti5 nickel-titanium [NiTi zirconia [ZrO2 polyetheretherketone [PEEK and gold) and twistflex retainers were tested for long-term sufficiency and for F-max using a self-developed in vitro model. All retainer models underwent a simulated ageing process of about 15 years (1,200,000 chewing cycles with a force magnitude of 65 N at 45 & DEG;followed by storage in water at 37 & DEG;C for 30 days). If retainers did not debond or break during ageing, their F-max was determined in a universal testing machine. Data were statistically analysed using Kruskal-Wallis and Mann-Whitney U-tests.ResultsTwistflex retainers did not fail (0/8) during ageing and had the highest F-max (445 N & PLUSMN;51 N). Ti5 retainers were the only CAD/CAM retainers that also did not fail (0/8) and had similar F-max values (374 N & PLUSMN;62 N). All other CAD/CAM retainers had higher failure rates during ageing and significantly lower F-max values (p < 0.01;ZrO2: 1/8, 168 N & PLUSMN;52 N;gold: 3/8, 130 N & PLUSMN;52 N;NiTi: 5/8, 162 N & PLUSMN;132 N;CoCr: 6/8, 122 N & PLUSMN;100 N;PEEK: 8/8, 65 & PLUSMN;0 N). Failure was due to breakage in the NiTi retainers and debonding in all other retainers.ConclusionTwistflex retainers remain the gold standard regarding biomechanical properties and long-term sufficiency. Of the CAD/CAM retainers tested, Ti5 retainers seem to be the most suitable alternative. In contrast, all other CAD/CAM retainers investigated in this study showed high failure rates and had significantly lower F-max values.

关键词： 3D CAD model classification   deep learning   MVCNN   pruning   quantization   compression techniques  

摘要： In the realm of product design and development, efficient retrieval and reuse of 3D CAD models are vital for optimizing workflows and minimizing redundant efforts. Manual labeling of CAD models, while traditional, is labor-intensive and prone to inconsistency, highlighting the need for automated classification systems. Multi-view convolutional neural networks (MVCNNs) offer an automated solution by leveraging 2D projections to represent 3D objects, balancing high classification accuracy with computational efficiency. Despite their effectiveness, the computational demands of MVCNNs pose challenges in large-scale CAD applications. This study investigates the use of optimization strategies, precisely pruning and quantization, in the scenario of MVCNN applied to the classification of 3D CAD mechanical models. By using different pruning and quantization strategies, we evaluate trade-offs between classification accuracy, execution time, and memory usage. In our evaluation of pruning and quantization techniques, 8-bit quantization reduced the memory used by the model from 83.78 MB to 21.01 MB, with accuracy only slightly decreasing from 93.83% to 93.59%. When applying 25% structured pruning, the model's memory usage was reduced to 47.16 MB, execution time decreased from 133 to 97 s, and accuracy decreased to 92.14%. A combined approach of 25% pruning and 8-bit quantization achieved even better resource efficiency, with memory usage at 11.86 MB, execution time at 99 s, and accuracy at 92.06%. This combination of pruning and quantization leads to efficient MVCNN model optimization, balancing resource usage and classification performance, which is especially relevant in large-scale applications.

关键词： Convolution Neural Network (CNN)   Ablation-CAM   Grad-CAM   Explainable AI  

摘要： Many cutting-edge computer vision systems now rely heavily on convolutional neural networks, or CNNs. However, conventional interpretation techniques frequently concentrate on 2D feature maps, ignoring the intricate contributions of individual pixels. This work aims to produce "visual explanations" that improve the explainability and transparency of decisions made by various CNN-based algorithms. We provide Pixel Ablation-CAM, a new method that builds on the ideas of Ablation-CAM by using pixel-wise ablation, which enables a finer-grained comprehension of model choices. With this method, activation maps are reinterpreted as arrays of one-dimensional vectors that represent channel-specific pixel activations. We show that, as compared to other approaches such as Grad-CAM, Pixel Ablation-CAM offers better resolution and accuracy in class-discriminative localisation maps by methodically ablating these vectors and monitoring changes in class activation scores. Our extensive testing demonstrates that Pixel Ablation-CAM improves model trust and interpretability, providing fresh perspectives on CNN behavior and propelling the field of explainable AI forward.

关键词： accuracy   analogic   computer-aided design   computer-assisted surgery   dental implants  

摘要： Objectives: To compare the accuracy of CAD-CAM and conventional guides in the static computer-assisted implant surgery (sCAIS) placement of distal free-end implants. Material and Methods: A prospective, controlled, and blinded quasi-experimental study was done involving 27 patients (76 implants) distributed into two groups according to the surgical guide manufacturing approach used: conventional (control group [CG or CAD-CAM (test group [TG]). The implants were planned in the software and the surgical guides were manufactured. Fully guided implant placement was carried out and the deviations were measured along with secondary variables as potential confounding factors. Descriptive analyses were performed on mean, standard deviation (SD and interquartile range (IQR). In the comparative/inferential analysis hypothesis, contrasts were made of the quantitative and qualitative variables and multiple linear models were generated to adjust for the different confounding variables recorded. Results: Coronal horizontal deviation (CHD) was significantly greater in CG (1.52 mm) versus TG (1.04 mm p = 0.004). Apical horizontal deviation (AHD) in turn was 1.67 versus 1.46 mm, respectively;angular deviation was 2.87 versus 3.64;and vertical deviation was -0.1 versus -0.05 mm, with no significant differences between the groups (p > 0.05). A greater sleeve height, positioning in premolars versus molars, and the use of shorter implants, were associated with greater accuracy in relation to CHD and/or AHD (p < 0.05). The implant success rate at 1 year was 92.1%, 90.7% in TG, and 100% in CG, being statistically significant (p = 0.026) at the implant level, but not significant at the patient level. Conclusions: The CAD-CAM surgical guides proved to be more accurate than the conventional guides in the sCAIS placement of distal free-end implants, with statistically significant differences being observed in terms of CHD. All implant failures occurred in TG (6 implants/3 patients). Trial Reg

关键词： CAD   Hepatocellular carcinoma (HCC)   TCGA   Prognosis   Immune therapy  

摘要： Hepatocellular carcinoma (HCC) is a common type of cancer that ranks first in cancer-associated death worldwide. Carbamoyl-phosphate synthetase 2, aspartate transcarbamylase, and dihydroorotase (CAD) are the key components of the pyrimidine pathway, which promotes cancer development. However, the function of CAD in HCC needs to be clarified. In this study, the clinical and transcriptome data of 424 TCGA-derived HCC cases were analyzed. The results demonstrated that high CAD expression was associated with poor prognosis in HCC patients. The effect of CAD on HCC was then investigated comprehensively using GO annotation analysis, KEGG enrichment analysis, Gene Set Enrichment Analysis (GSEA and CIBERSORT algorithm. The results showed that CAD expression was correlated with immune checkpoint inhibitors and immune cell infiltration. In addition, low CAD levels in HCC patients predicted increased sensitivity to anti-CTLA4 and PD1, while HCC patients with high CAD expression exhibited high sensitivity to chemotherapeutic and molecular-targeted agents, including gemcitabine, paclitaxel, and sorafenib. Finally, the results from clinical sample suggested that CAD expression increased remarkably in HCC compared with non-cancerous tissues. Loss of function experiments demonstrated that CAD knockdown could significantly inhibit HCC cell growth and migration both in vitro and in vivo. Collectively, the results indicated that CAD is a potential oncogene during HCC metastasis and progression. Therefore, CAD is recommended as a candidate marker and target for HCC prediction and treatment.

摘要： Background: The ScreenTrustCAD trial was a prospective study that evaluated the cancer detection rates for combinations of artificial intelligence (AI) computer-aided detection (CAD) and two radiologists. The results raised concerns about the tendency of radiologists to agree with AI CAD too much (when AI CAD made an erroneous flagging) or too little (when AI CAD made a correct flagging). Purpose: To evaluate differences in recall proportion and positive predictive value (PPV) related to which reader flagged the mammogram for consensus discussion: AI CAD and/or radiologists. Materials and Methods: Participants were enrolled from April 2021 to June 2022, and each examination was interpreted by three independent readers: two radiologists and AI CAD, after which positive findings were forwarded to the consensus discussion. For each combination of readers flagging an examination, the proportion recalled and the PPV were calculated by dividing the number of pathologic evaluation-verified cancers by the number of positive examinations. Results: The study included 54 991 women (median age, 55 years [IQR, 46-65 years among whom 5489 were flagged for consensus discussion and 1348 were recalled. For examinations flagged by one reader, the proportion recalled after flagging by one radiologist was larger (14.2% [263 of 1858 compared with flagging byAI CAD (4.6% [86 of 1886 P < .001 whereas the PPV of breast cancer was lower (3.4% [nine of 263] vs 22% [19 of 86 P < .001). For examinations flagged by two readers, the proportion recalled after flagging by two radiologists was larger (57.2% [360 of 629 compared with flagging by AI CAD and one radiologist (38.6% [244 of 632 P < .001 whereas the PPV was lower (2.5% [nine of 360] vs 25.0% [61 of 244 P < .001). For examinations flagged by all three readers, the proportion recalled was 82.6% (400 of 484) and the PPV was 34.2 (137 of 400). Conclusion: A larger proportion of participants were recalled after initial flagging by radiologist

摘要： We developed an endothelial cell-specific polygenic risk score for coronary artery disease (CAD), which quantifies a currently immeasurable axis of CAD risk. This tool identifies patients who are more susceptible to LDL-C entering the cell wall and will benefit from aggressive lipid-lowering therapy, providing an opportunity to guide earlier and more-personalized preventive therapies.