Upper gastrointestinal cancers (including oesophageal cancer and gastric cancer) are the most common cancers worldwide. Artificial intelligence platforms using deep learning algorithms have made ...remarkable progress in medical imaging but their application in upper gastrointestinal cancers has been limited. We aimed to develop and validate the Gastrointestinal Artificial Intelligence Diagnostic System (GRAIDS) for the diagnosis of upper gastrointestinal cancers through analysis of imaging data from clinical endoscopies.
This multicentre, case-control, diagnostic study was done in six hospitals of different tiers (ie, municipal, provincial, and national) in China. The images of consecutive participants, aged 18 years or older, who had not had a previous endoscopy were retrieved from all participating hospitals. All patients with upper gastrointestinal cancer lesions (including oesophageal cancer and gastric cancer) that were histologically proven malignancies were eligible for this study. Only images with standard white light were deemed eligible. The images from Sun Yat-sen University Cancer Center were randomly assigned (8:1:1) to the training and intrinsic verification datasets for developing GRAIDS, and the internal validation dataset for evaluating the performance of GRAIDS. Its diagnostic performance was evaluated using an internal and prospective validation set from Sun Yat-sen University Cancer Center (a national hospital) and additional external validation sets from five primary care hospitals. The performance of GRAIDS was also compared with endoscopists with three degrees of expertise: expert, competent, and trainee. The diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of GRAIDS and endoscopists for the identification of cancerous lesions were evaluated by calculating the 95% CIs using the Clopper-Pearson method.
1 036 496 endoscopy images from 84 424 individuals were used to develop and test GRAIDS. The diagnostic accuracy in identifying upper gastrointestinal cancers was 0·955 (95% CI 0·952–0·957) in the internal validation set, 0·927 (0·925–0·929) in the prospective set, and ranged from 0·915 (0·913–0·917) to 0·977 (0·977–0·978) in the five external validation sets. GRAIDS achieved diagnostic sensitivity similar to that of the expert endoscopist (0·942 95% CI 0·924–0·957 vs 0·945 0·927–0·959; p=0·692) and superior sensitivity compared with competent (0·858 0·832–0·880, p<0·0001) and trainee (0·722 0·691–0·752, p<0·0001) endoscopists. The positive predictive value was 0·814 (95% CI 0·788–0·838) for GRAIDS, 0·932 (0·913–0·948) for the expert endoscopist, 0·974 (0·960–0·984) for the competent endoscopist, and 0·824 (0·795–0·850) for the trainee endoscopist. The negative predictive value was 0·978 (95% CI 0·971–0·984) for GRAIDS, 0·980 (0·974–0·985) for the expert endoscopist, 0·951 (0·942–0·959) for the competent endoscopist, and 0·904 (0·893–0·916) for the trainee endoscopist.
GRAIDS achieved high diagnostic accuracy in detecting upper gastrointestinal cancers, with sensitivity similar to that of expert endoscopists and was superior to that of non-expert endoscopists. This system could assist community-based hospitals in improving their effectiveness in upper gastrointestinal cancer diagnoses.
The National Key R&D Program of China, the Natural Science Foundation of Guangdong Province, the Science and Technology Program of Guangdong, the Science and Technology Program of Guangzhou, and the Fundamental Research Funds for the Central Universities.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Background and Aims
Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) is increasingly being used for diagnosing lymphadenopathy. We aim to systematically review the accuracy of EUS-FNA in ...differentiating benign and malignant mediastinal and abdominal lymph nodes (LNs).
Methods
A comprehensive literature search was performed on multiple electronic databases through February 2020. A random or fixed effect model generated the pooled sensitivity, specificity, likelihood ratio (LR), and diagnostic odds ratio (DOR) of EUS-FNA. Subgroup analyses and meta-regression were used to explore sources of heterogeneity.
Results
Twenty-six studies involving 2753 patients with 2833 LNs were included. In the differential diagnosis of benign and malignant LNs, EUS-FNA had a pooled sensitivity, specificity, positive LR, and negative LR of 87% (95% confidence interval CI 86–90%), 100% (95% CI 99–100%), 68.98 (95% CI 42.10–113.02), and 0.14 (95% CI 0.11–0.17), respectively. The pooled rate of adverse events associated with EUS-FNA was 1.57% (95% CI 1.06–2.24%). The summary receiver operating characteristic (SROC) yielded an area under the curve (AUC) of 0.9912. EUS-FNA performed in mediastinal LNs gained a sensitivity of 85% (95% CI 81–88%), while in abdominal LNs, it reached 87% (95% CI 82–91%). The sensitivity of the subgroup with rapid on-site evaluation (ROSE) was 91% (95% CI 89–93%), while non-ROSE was 85% (95% CI 82–87%).
Conclusions
EUS-FNA is a sensitive, highly specific, and safe method for distinguishing benign and malignant mediastinal or abdominal LNs. However, the sensitivity of EUS-FNA still varies significantly among different centers.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Research on optimal sensor placement (OSP) has become very important due to the need to obtain effective testing results with limited testing resources in health monitoring. In this study, a new ...methodology is proposed to select the best sensor locations for large structures. First, a novel fitness function derived from the nearest neighbour index is proposed to overcome the drawbacks of the effective independence method for OSP for large structures. This method maximizes the contribution of each sensor to modal observability and simultaneously avoids the redundancy of information between the selected degrees of freedom. A hybrid algorithm combining the improved discrete particle swarm optimization (DPSO) with the clonal selection algorithm is then implemented to optimize the proposed fitness function effectively. Finally, the proposed method is applied to an arch dam for performance verification. The results show that the proposed hybrid swarm intelligence algorithm outperforms a genetic algorithm with decimal two-dimension array encoding and DPSO in the capability of global optimization. The new fitness function is advantageous in terms of sensor distribution and ensuring a well-conditioned information matrix and orthogonality of modes, indicating that this method may be used to provide guidance for OSP in various large structures.
Refractory high-entropy alloys (RHEAs) exhibit outstanding softening resistance and thermal stability at elevated temperatures. Unfortunately, poor ductility at room temperature has remained the ...critical issue for their processability and practical application. In this study, an original-type fabrication method of RHEA was proposed, using multi-walled carbon nanotubes (MWCNTs) to enhance the alloy prepared via laser melting deposition (LMD) technology. The processing optimization, microstructure evolution and mechanical properties were systematically investigated for LMD processing of CNTs/CoCrMoNbTi0.4 RHEA. The results have shown that CNTs/CoCrMoNbTi0.4 RHEA have a polycrystalline structure (BCC, HCP, and TiC). As the optimal LMD-processing parameters of laser linear energy density of 3.6 J/mm were applied, owing to the formation of high densification and an ultrafine microstructure, the fully dense LMD-processed alloy exhibited high microhardness of 1015 HV0.5, fracture strength of 2110.5 MPa, and fracture strain of 2.39%. The solid solution strengthening and load transfer are considered as the main strengthening mechanisms occurring simultaneously during compressive tests at room temperature, leading to excellent mechanical properties of LMD-processed CNTs/CoCrMoNbTi0.4 RHEA, which explores the potential application of RHEAs.
Nonsurgical therapies have become treatment options for hepatocellular carcinoma (HCC). This study was to evaluate the efficacy and complications of high-intensity focused ultrasound (HIFU) treatment ...for patients with HCC. Between May 2001 and May 2005, 145 patients with HCC were enrolled for treatments using a HIFU tumor therapeutic system. Clinical symptoms, hepatic functions and values of serum α-fetoprotein (AFP) were tested before and after HIFU treatment. The changes in computerized tomography (CT) and magnetic resonance imaging (MRI), complications and survival time after HIFU were also obtained for further analysis. Symptoms improved or pain was relieved in 84.8% of the 145 patients and the rate of serum AFP decrease was 71.7%. The size of the target tumor shrank by various degrees. The 2-year survival rate was 80% in patients with stage Ib HCC, 51.4% in stage IIa and 46.5% in stage IIIa. During HIFU treatment, complications included body temperature increase and abnormal cardiac rhythm. After HIFU procedures, there were skin burns of different grades. In conclusion, HIFU is safe and effective for patients with hepatocellular carcinoma; HIFU can improve the survival quality of patients with HCC.
•AlCoCrFeNi2.1 EHEA was successfully joined by laser beam welding.•The joint exhibited refined eutectic lamellar structure of FCC(L12)/BCC(B2) phases.•Acceptable joint tensile strength via grain ...refinement and dislocation accumulation.
To determine the potential of an AlCoCrFeNi2.1 eutectic high entropy alloy (EHEA) as a structural material, its laser beam welding (LBW) performance was evaluated, and the microstructure and mechanical properties of weld joint were studied. A fully penetrated, defect-free joint was obtained, in which the fusion zone (FZ) exhibited a eutectic lamellar microstructure containing FCC(L12)/BCC(B2) solid solution phases. The FZ contained refined columnar grains, which grown with the preferential 〈111〉 orientation induced by the rapid cooling during LBW. The tensile strength of the FZ was superior than that of the base metal (BM), which was attributed to grain refinement and higher dislocation density. LBW is a suitable process for joining AlCoCrFeNi2.1 EHEAs.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
•An in-situ strengthened dual-phase AlCoCuFeNi HEA is developed via SEBM.•HEA comprised BCC solid solution matrix with FCC precipitates.•Compressive strength and ductility of the SEBM HEA superior to ...SLM HEA.•Electron beam remelting during SEBM could result in superior properties.
The application scope and market demand for additive-manufactured high-entropy alloys (AM HEAs) have broadened of late. However, a long-standing problem associated with AM HEAs is their limited ductility. In this study, a dual-phase AlCoCuFeNi HEA, consisting of body-centered cubic (BCC) solid solution matrix with uniformly dispersed face-centered cubic (FCC) structured precipitates, was fabricated by selective electron beam melting (SEBM). SEBM involved a preheating process can enable the formation of Cu-rich FCC phases with needle-like and spherical morphologies, as well as nanotwins that in-situ precipitated from the metastable BCC(B2) matrix. The compressive strength and ductility of the SEBM HEA were superior to those of the HEAs processed by selective laser melting (SLM) AM technique. Furthermore, using selective electron beam remelting (SEB-RM) during SEBM could result in a higher relative density, finer microstructure, and enhanced compressive properties. Particularly, the SEB-RM sample exhibited a better compressive strength of 2572 MPa, a yield strength of 870 MPa, and a strain of 18.3%. The improved mechanical properties of SEB-RM samples could be ascribed to the refined grains and the formation of FCC precipitates, mostly along the grain boundaries. This provides new insights into the dual-phase HEAs—fabricated via a combination of the SEBM additive manufacturing process and selective electron beam remelting—that exhibit in-situ strengthening.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
In this study, CoCrMoNbTi, CoCrMoNbTi(B4C)0.2 and CoCrMoNbTi(SiC)0.2 high-entropy alloy coatings are prepared by laser cladding. These three coatings show significant differences in terms of ...microstructure and mechanical properties. In terms of microstructure, the Pure-HEA exhibits a uniform microstructure distribution, and the coating consists of two BCC phase-solid solution structures (BCC1 and BCC2) with different lattice constants. SiC-HEA exhibits a denser microstructure than Pure-HEA, and both coatings exhibit a typical dendritic structure. In contrast, the microstructure of B4C-HEA transformed from dendritic crystals to fully equiaxed crystals, and the grain refining effect can even up to two orders of magnitude. Both B4C-HEA and SiC-HEA are composed of BCC1, BCC2 and TiC phases, where TiC is obtained by the in-situ reaction. The effects of B4C and SiC on the mechanical properties of the high-entropy alloy are evaluated in terms of microhardness and wear resistance. The results show that B4C has the best strengthening effect on the alloy properties, the microhardness of the coating increases from 666.2 HV0.5 to 886.9 HV0.5. The room temperature wear resistance of the alloy is enhanced, and the frictional coefficient and wear rate are significantly reduced. Moreover, the wear mechanism is transformed from adhesive wear to abrasive wear due to the addition of B4C. This work provides insight into the application of ceramic particle-reinforced high-entropy alloys.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
•Microstructure and phase of laser-cladded AlCrFeMnNi HEA coating were analyzed.•The wear behaviour of the coatings at different temperatures was investigated in detail.•The elevated temperature wear ...mechanisms of the HEA coating were dominated by oxidation wear and adhesive wear.
The AlCrFeMnNi high-entropy alloy (HEA) coatings were deposited on 316L stainless steel through laser cladding technology that employs pre-alloyed HEA powders. The microstructure, phase composition and hardness of the laser-cladded coatings prepared at different laser scanning speeds were investigated. The wear behavior and properties of the HEA coatings at different temperatures (from room temperature to 600 °C) was comprehensively evaluated using a pin-on-disc test. It was demonstrated that the laser-cladded AlCrFeMnNi HEA coatings exhibited dense and uniform microstructures consisting of a single BCC solid solution phase. A columnar-to-equiaxed transition structure feature was observed in the molten pool of the laser-cladded coating. The coatings possessed better high-temperature wear performance due to the protective effect of oxide films on the wear track. The coating at 400 °C exhibited the best wear resistance, which had the lowest friction coefficient and wear rate of 0.48 and 1.246 × 10−4 mm3/N · m, respectively. At room temperature, the main wear mechanism of the coating was abrasive wear. However, the predominant wear mechanism at high temperatures was oxidation and adhesive wear.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Three-dimensional post-processing operations on the volume data generated by a series of CT or MR images had important significance on image reading and diagnosis. As a part of the DIOCM standard, ...WADO service defined how to access DICOM objects on the Web, but it didn’t involve three-dimensional post-processing operations on the series images. This paper analyzed the technical features of three-dimensional post-processing operations on the volume data, and then designed and implemented a web service system for three-dimensional post-processing operations of medical images based on the WADO protocol. In order to improve the scalability of the proposed system, the business tasks and calculation operations were separated into two modules. As results, it was proved that the proposed system could support three-dimensional post-processing service of medical images for multiple clients at the same moment, which met the demand of accessing three-dimensional post-processing operations on the volume data on the web.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, VSZLJ, ZAGLJ
