MSCS-DeepLN: Evaluating lung nodule malignancy using multi-scale cost-sensitive neural networks.

The accurate identification of malignant lung nodules using computed tomography (CT) screening images is vital for the early detection of lung cancer. It also offers patients the best chance of cure, because non-invasive CT imaging has the ability to capture intra-tumoral heterogeneity. Deep learning methods have obtained promising results for the malignancy identification problem; however, two substantial challenges still remain. First, small datasets cannot insufficiently train the model and tend to overfit it. Second, category imbalance in the data is a problem. In this paper, we propose a method called MSCS-DeepLN that evaluates lung nodule malignancy and simultaneously solves these two problems. Three light models are trained and combined to evaluate the malignancy of a lung nodule. Three-dimensional convolutional neural networks (CNNs) are employed as the backbone of each light model to extract the lung nodule features from CT images and preserve lung nodule spatial heterogeneity. Multi-scale input cropped from CT images enables the sub-networks to learn the multi-level contextual features and preserve diverse. To tackle the imbalance problem, our proposed method employs an AUC approximation as the penalty term. During training, the error in this penalty term is generated from each major and minor class pair, so that negatives and positives can contribute equally to updating this model. Based on these methods, we obtain state-of-the-art results on the LIDC-IDRI dataset. Furthermore, we constructed a new dataset collected from a grade-A tertiary hospital and annotated using biopsy-based cytological analysis to verify the performance of our method in clinical practice.

[Application and effect of integrated control model of schistosomiasis interruption in mountainous and hilly endemic regions].

OBJECTIVE: To explore the integrated schistosomiasis control model in mountainous and hilly endemic regions, so as to provide insights into the development of the schistosomiasis elimination strategy. METHODS: Five hilly and mountainous areas endemic for schistosomiasis were selected as the integrated control demonstration areas in Sichuan Province from 2011 to 2015. According to the epidemic characteristics, economic levels and overall development planning of the demonstration areas, the goals, strategies and measures were developed, and the effectiveness of schistosomiasis control was evaluated following implementation of the integrated control. RESULTS: The support system of the integrated schistosomiasis control model was built in the integrated control demonstration areas in Sichuan Province from 2011 to 2015, and five ecological, industrialized and sustainable development models of integrated schistosomiasis control were developed, including integration of balancing rural and urban development, systematic ecological improvement, intensified ecological agriculture, scientific management and health education of schistosomiasis control and ecological ethnic circular economy. Since the implementation of the integrated schistosomiasis control model, the snail habitats were completely changed. Until 2015, 92.0% of all historical areas with snails were managed, the coverage of safe drinking water was 100.0%, and more than 95.0% of the livestock were fenced. The coverage of sanitary toilets increased by 93.0%, 96.8%, 78.8%, 87.1% and 82.0% from 2011 to 2015, respectively, and the farmers'mean yearly income increased by 32.7% in the demonstration areas. From 2011 to 2015, the seroprevalence of human Schistosoma japonicum infections reduced from 3.1% in 2011 to 1.6% in 2015 in the demonstration areas, and no egg-positives were identified. In addition, the number of fenced bovines reduced year by year, and no egg-positives were detected. The areas of snail habitats were 398.7, 108.2 hm2 and 52.9 hm2 in the demonstration areas from 2011 to 2013, with no infected snails found, and no snails were detected since 2014. The awareness of schistosomiasis control knowledge and percentage of correct behavior formation increased year by year among residents in the demonstration areas from 2011 to 2015. CONCLUSIONS: The five integrated schistosomiasis control models meet the needs of the current schistosomiasis control activities in mountainous and hilly endemic areas of Sichuan Province, and achieve the goals of controlling the sources of S. japonicum infections, economic development, social progress and improving the ecological environment, which provides new insights into schistosomiasis elimination in the country.

Defense Against Chip Cloning Attacks Based on Fractional Hopfield Neural Networks.

This paper presents a state-of-the-art application of fractional hopfield neural networks (FHNNs) to defend against chip cloning attacks, and provides insight into the reason that the proposed method is superior to physically unclonable functions (PUFs). In the past decade, PUFs have been evolving as one of the best types of hardware security. However, the development of the PUFs has been somewhat limited by its implementation cost, its temperature variation effect, its electromagnetic interference effect, the amount of entropy in it, etc. Therefore, it is imperative to discover, through promising mathematical methods and physical modules, some novel mechanisms to overcome the aforementioned weaknesses of the PUFs. Motivated by this need, in this paper, we propose applying the FHNNs to defend against chip cloning attacks. At first, we implement the arbitrary-order fractor of a FHNN. Secondly, we describe the implementation cost of the FHNNs. Thirdly, we propose the achievement of the constant-order performance of a FHNN when ambient temperature varies. Fourthly, we analyze the electrical performance stability of the FHNNs under electromagnetic disturbance conditions. Fifthly, we study the amount of entropy of the FHNNs. Lastly, we perform experiments to analyze the pass-band width of the fractor of an arbitrary-order FHNN and the defense against chip cloning attacks capability of the FHNNs. In particular, the capabilities of defense against chip cloning attacks, anti-electromagnetic interference, and anti-temperature variation of a FHNN are illustrated experimentally in detail. Some significant advantages of the FHNNs are that their implementation cost is considerably lower than that of the PUFs, their electrical performance is much more stable than that of the PUFs under different temperature conditions, their electrical performance stability of the FHNNs under electromagnetic disturbance conditions is much more robust than that of the PUFs, and their amount of entropy is significantly higher than that of the PUFs with the same rank circuit scale.

[Spatial distribution and risk assessment of atrazine in Taizi River basin, China].

Atrazine (AT) has been detected in surface water and groundwater in many countries and regions around the world. Concentrations of AT in surface water, suspended particulate matter (SPM) and groundwater samples collected from the Taizi River basin, in northeast China, were analyzed using a gas chromatograph-mass spectrometer (GC-MS) in order to clarify their spatial distribution and environmental behavior, and to assess their potential ecological risk. Concentrations of AT varied from 0-734.0 ng x L(-1) for surface water, 0-1 493.6 ng x g(-1) for SPM and 30.0-245.0 ng x L(-1) for groundwater, with averages of 335.3 ng x L(-1), 382.9 ng x L(-1), and 104.4 ng x L(-1), respectively. The logarithm in situ SPM-water partition coefficients (lg k(oc)) of AT were in the range of 3.50-4.14 indicating that adsorption of AT from the aqueous phase to SPM plays an important role in dissipating AT in surface water. Fluxes of AT in surface water ranged from 1.5-184.7 mg x s(-1) in the basin, calculated based on the measured flow velocity and concentrations in surface water and SPM. The maximum value of AT flux was found in the middle stream of the Taizi River (S7). The risk assessment suggested that the ecological risk of AT in surface water was low, with more than 95% of the species protected from risk in the Taizi River basin. However, the residue levels of AT in surface water of the Taizi River basin may cause potential environmental risks.

A pilot assessment of relapse prevention for heroin addicts in a Chinese rehabilitation center.

OBJECTIVES: To conduct a pilot assessment of relapse prevention (RP) group therapy for heroin-dependent patients in a drug rehabilitation center in China. METHODS: A randomized case-control study was conducted to assess the efficacy of RP delivered over a 2-month period to male heroin addicts (n = 50, RP group) in the Shanghai Labor Drug Rehabilitation Center (LDRC) compared with an equal number of participants (n = 50, labor rehabilitation (LR) group) in the LDRC program receiving standard-of-care treatment. Outcomes were assessed by the Beck Depression Inventory (BDI), the Self-Rating Anxiety Scale (SAS), the Self-Efficacy Scale (SE), and the Self-Esteem Scale (SES) after completion of RP, and by the Addiction Severity Index (ASI) and abstinence rates of heroin use at 3-month follow-up post release from the LDRC for both groups. RESULTS: Significant improvements in scores on SAS, SE, and SES were found in the RP group after completion of the 2-month RP group therapy compared with the LR group (SAS 7.85 ± 6.20 vs 1.07 ± 5.42, SE 3.88 ± 3.60 vs .08 ± 2.89, and SES 3.83 ± 3.31 vs .78 ± 2.55). At 3-month follow-up, the RP group participants had more improvements on ASI scores in most domains and had higher abstinence rates than that in the LR group (37.2% vs 16.7%). CONCLUSIONS: An RP component can be effective in increasing abstinence rates among post-program heroin-dependent individuals and may help reduce anxiety and improve self-esteem and self-efficacy during and following treatment. SCIENTIFIC SIGNIFICANCE: This study suggests RP as a potentially effective component of treatment for heroin addicts.