Explore the vast range of titles available.

As the banana industry develops, the demand for intelligent banana crown cutting is increasing. To achieve efficient crown cutting of bananas, accurate segmentation of the banana crown is crucial for the operation of a banana crown cutting device. In order to address the existing challenges, this paper proposed a method for segmentation of banana crown based on improved DeepLabv3+. This method replaces the backbone network of the classical DeepLabv3+ model with MobilenetV2, reducing the number of parameters and training time, thereby achieving model lightweightness and enhancing model speed. Additionally, the Atrous Spatial Pyramid Pooling (ASPP) module is enhanced by incorporating the Shuffle Attention Mechanism and replacing the activation function with Meta-ACONC. This enhancement results in the creation of a new feature extraction module, called Banana-ASPP, which effectively handles high-level features. Furthermore, Multi-scale Channel Attention Module (MS-CAM) is introduced to the Decoder to improve the integration of features from multiple semantics and scales. According to experimental data, the proposed method has a Mean Intersection over Union (MIoU) of 85.75%, a Mean Pixel Accuracy (MPA) of 91.41%, parameters of 5.881 M and model speed of 61.05 f/s. Compared to the classical DeepLabv3+ network, the proposed model exhibits an improvement of 1.94% in MIoU and 1.21% in MPA, while reducing the number of parameters by 89.25% and increasing the model speed by 47.07 f/s. The proposed method enhanced banana crown segmentation accuracy while maintaining model lightweightness and speed. It also provided robust technical support for relevant parameters calculation of banana crown and control of banana crown cutting equipment.

Epidermal growth factor receptor (EGFR) exon 20 insertion mutations (ex20ins) account for ≤ 12% of all EGFR‐mutant nonsmall cell lung cancers. We analysed real‐world datasets to determine the frequency of ex20ins variants, and the ability of polymerase chain reaction (PCR) and next‐generation sequencing (NGS) to identify them. Three real‐world United States NGS databases were used: GENIE, FoundationInsights, and GuardantINFORM. Mutation profiles consistent with in‐frame EGFR ex20ins were summarized. GENIE, FoundationInsights, and GuardantINFORM datasets identified 180, 627, and 627 patients with EGFR ex20ins respectively. The most frequent insertion region of exon 20 was the near loop (~ 70%), followed by the far loop (~ 30%) and the helical (~ 3–6%) regions. GENIE, FoundationInsights, and GuardantINFORM datasets identified 41, 102, and 96 unique variants respectively. An analysis of variants projected that ~ 50% of EGFR ex20ins identified by NGS would have been missed by PCR‐based assays. Given the breadth of EGFR ex20ins identified in the real‐world US datasets, the ability of PCR to identify these mutations is limited. NGS platforms are more appropriate to identify patients likely to benefit from EGFR ex20ins‐targeted therapies. Three next‐generation sequencing (NGS) databases (GENIE, FoundationInsights and GuardantINFORM) were analyzed to estimate the frequency of exon 20 insertion (ex20ins) variants in epidermal growth factor receptor (EGFR)–mutant non‐small cell lung cancer (NSCLC). Results indicate ~ 50% of ex20ins identified by NGS would have been missed by PCR and the near loop is the most frequent insertion site.

Early and effective detection of Mycobacterium tuberculosis (MTB), particularly in smear-negative tuberculosis (TB), is a priority for global TB control. Loop-mediated isothermal amplification with a procedure for ultra rapid DNA extraction (PURE-LAMP) can detect TB in sputum samples rapidly and with high sensitivity and specificity. However, the PURE-LAMP test has not been effectively evaluated, especially in resource-limited laboratories. In this study, we evaluated the performance of the PURE-LAMP test for TB detection in TB suspects from two county-level TB dispensaries in China. From April 2011 to February 2012, patients with suspected TB were continuously enrolled from two county-level TB laboratories in China. Three sputum samples (spot, night, and morning sputum) were collected from each recruited patient. Detection of MTB by PURE-LAMP was compared to a reference standard L-J culture. The results showed that the sensitivity of the PURE-LAMP test based on spot sputum for MTB detection was 70.67%, while the sensitivity of the PURE-LAMP test based on spot sputum for MTB detection in smear positive and culture positive patients and smear negative and culture positive patients was 92.12% and 53.81%, respectively. The specificity of PURE-LAMP based on spot sputum for MTB detection was 98.32%. The sensitivity and specificity of the PURE-LAMP test based on three sputa combination for MTB detection was 88.80% and 96.86%, respectively. The results also showed that the PURE-LAMP test had a significantly lower contamination rate than did solid culture. The study suggested that, in peripheral-level TB laboratories in China, the PURE-LAMP test showed high sensitivity and specificity for TB detection in TB suspects, making it a more effective, rapid, and safe method worthy of broader use in the future.

New diagnostic methods have provided a promising solution for rapid and reliable detection of drug-resistant TB strains. The aim of this study was to evaluate the performance of the MeltPro TB assay in identifying multidrug-resistant (MDR-) and extensively drug-resistant tuberculosis (XDR-TB) patients from sputum samples. The MeltPro TB assay was evaluated using sputum samples from 2057 smear-positive TB patients. Phenotypic Mycobacterial Growth Indicator Tube (MGIT) 960 drug susceptibility testing served as a reference standard. The sensitivity of the MeltPro TB assay was 94.2% for detecting resistance to rifampicin and 84.9% for detecting resistance to isoniazid. For second-line drugs, the assay showed a sensitivity of 83.3% for ofloxacin resistance, 75.0% for amikacin resistance, and 63.5% for kanamycin resistance. However, there was a significant difference for detecting kanamycin resistance between the two pilot sites in sensitivity, which was 53.2% in Guangdong and 81.5% in Shandong ( P  = 0.015). Overall, the MeltPro TB assay demonstrated good performance for the detection of MDR- and XDR-TB, with a sensitivity of 86.7% and 71.4%, respectively. The MeltPro TB assay is an excellent alternative for the detection of MDR- and XDR-TB cases in China, with high accuracy, short testing turn-around time, and low unit price compared with other tests.

Psoriatic arthritis (PsA) is associated with psoriasis, featured by its irreversible joint symptoms. Despite the significant impact on the healthcare system, it is still challenging to leverage machine learning or statistical models to predict PsA and its progression, or analyze drug efficacy. With 3961 patients’ clinical records, we developed a machine learning model for PsA diagnosis and analysis of PsA progression risk, respectively. Furthermore, general additive models (GAMs) and the Kaplan–Meier (KM) method were applied to analyze the efficacy of various drugs on psoriasis treatment and inhibiting PsA progression. The independent experiment on the PsA prediction model demonstrates outstanding prediction performance with an AUC score of 0.87 and an AUPR score of 0.89, and the Jackknife validation test on the PsA progression prediction model also suggests the superior performance with an AUC score of 0.80 and an AUPR score of 0.83, respectively. We also identified that interleukin-17 inhibitors were the more effective drug for severe psoriasis compared to other drugs, and methotrexate had a lower effect in inhibiting PsA progression. The results demonstrate that machine learning and statistical approaches enable accurate early prediction of PsA and its progression, and analysis of drug efficacy.

Genechip (CapitalBio, Beijing, China) is a system for diagnosing resistance to rifampin and isoniazid, which shows high efficiency in detecting drug-resistant tuberculosis. Here, we firstly evaluated the costs of Genechip for detecting the drug susceptibility of Mycobacterium tuberculosis, compared to conventional drug susceptibility test (DST) in laboratories in China. Data on the costs of the two tests were collected at four hospitals. Costs were calculated using the essential factor cost calculation method. The costs of diagnosing a single case of multidrug-resistant tuberculosis (MDR-TB) using Genechip and DST were US$22.38 and $53.03, respectively. Taking into account the effect on costs from failure of a certain number of tests to accurately diagnose MDR-TB, the costs of Genechip and DST increased by 17.65% and 5.22%, respectively. The cost of both tests decreased with the increasing prevalence of MDR-TB disease, and the cost of Genechip at a sensitivity of more than 50% was lower than that of DST. When price of Genechip was varied to 50%, 80%, 150%, and 200% of the original price, the cost of Genechip at sensitivities of more than 30%, 40%, 60%, and 70%, respectively, was also lower than that of DST. This study showed that Genechip was a more cost-effective method of diagnosing MDR-TB compared to conventional DST.

This paper aims to improve video streaming by leveraging a simple observation: users are more sensitive to low quality in certain parts of a video than in others. For instance, rebuffering during key moments of a sports video (e.g., before a goal is scored) is more annoying than rebuffering during normal gameplay. Such dynamic quality sensitivity, however, is rarely captured by current approaches, which predict QoE (quality-of-experience) using one-size-fits-all heuristics that are too simplistic to understand the nuances of video content. Instead of proposing yet another heuristic, we take a different approach: we run a separate crowdsourcing experiment for each video to derive users' quality sensitivity at different parts of the video. Of course, the cost of doing this at scale can be prohibitive, but we show that careful experiment design combined with a suite of pruning techniques can make the cost negligible compared to how much content providers invest in content generation and distribution. Our ability to accurately profile time-varying user sensitivity inspires a new approach: dynamically aligning higher (lower) quality with higher (lower) sensitivity periods. We present a new video streaming system called SENSEI that incorporates dynamic quality sensitivity into existing quality adaptation algorithms. We apply SENSEI to two state-of-the-art adaptation algorithms. SENSEI can take seemingly unusual actions: e.g., lowering bitrate (or initiating a rebuffering event) even when bandwidth is sufficient so that it can maintain a higher bitrate without rebuffering when quality sensitivity becomes higher in the near future. Compared to state-of-the-art approaches, SENSEI improves QoE by 15.1% or achieves the same QoE with 26.8% less bandwidth on average.