Efficient Near-Infrared Spectrum Detection in Nondestructive Wood Testing via Transfer Network Redesign.

This study systematically developed a deep transfer network for near-infrared spectrum detection using convolutional neural network modules as key components. Through meticulous evaluation, specific modules and structures suitable for constructing the near-infrared spectrum detection model were identified, ensuring its effectiveness. This study extensively analyzed the basic network components and explored three unsupervised domain adaptation structures, highlighting their applications in the nondestructive testing of wood. Additionally, five transfer networks were strategically redesigned to substantially enhance their performance. The experimental results showed that the Conditional Domain Adversarial Network and Globalized Loss Optimization Transfer network outperformed the Direct Standardization, Piecewise Direct Standardization, and Spectral Space Transformation models. The coefficients of determination for the Conditional Domain Adversarial Network and Globalized Loss Optimization Transfer network are 82.11% and 83.59%, respectively, with root mean square error prediction values of 12.237 and 11.582, respectively. These achievements represent considerable advancements toward the practical implementation of an efficient and reliable near-infrared spectrum detection system using a deep transfer network.

Inhibition of mitochondrial translocase SLC25A5 and histone deacetylation is an effective combination therapy in neuroblastoma.

The mitochondrion is a gatekeeper of apoptotic processes, and mediates drug resistance to several chemotherapy agents used to treat cancer. Neuroblastoma is a common solid cancer in young children with poor clinical outcomes following conventional chemotherapy. We sought druggable mitochondrial protein targets in neuroblastoma cells. Among mitochondria-associated gene targets, we found that high expression of the mitochondrial adenine nucleotide translocase 2 (SLC25A5/ANT2), was a strong predictor of poor neuroblastoma patient prognosis and contributed to a more malignant phenotype in pre-clinical models. Inhibiting this transporter with PENAO reduced cell viability in a panel of neuroblastoma cell lines in a TP53-status-dependant manner. We identified the histone deacetylase inhibitor, suberanilohydroxamic acid (SAHA), as the most effective drug in clinical use against mutant TP53 neuroblastoma cells. SAHA and PENAO synergistically reduced cell viability, and induced apoptosis, in neuroblastoma cells independent of TP53-status. The SAHA and PENAO drug combination significantly delayed tumour progression in pre-clinical neuroblastoma mouse models, suggesting that these clinically advanced inhibitors may be effective in treating the disease.

Integrated clinical genotype-phenotype characteristics of early T-cell precursor acute lymphoblastic leukemia.

BACKGROUND: Early T-cell precursor acute lymphoblastic leukemia (ETP-ALL) is a distinct subtype of T-ALL with a unique immunophenotype and high treatment failure rate. The molecular genetic abnormalities and their prognostic impact in ETP-ALL patients are poorly understood. METHODS: The authors performed systematic analyses of the clinicopathologic features with an emphasis on molecular genetic aspects of 32 patients with ETP-ALL. RESULTS: The median age was 43 years (range, 16-71). The blasts were positive for cytoplasmic CD3 and CD7 and negative for CD1a and CD8. Other markers expressed included CD34 (88%), CD33 (72%), CD117 (68%), CD13 (58%), CD5 (partial, 56%), CD2 (38%), CD10 (25%), CD56 (partial, 19%), and CD4 (6%). Cytogenetic analyses revealed a diploid karyotype in 10 patients, simple (1-2) abnormalities in 10 patients, and complex karyotype in 10 patients. Next-generation sequencing for 21 patients demonstrated that all had gene mutations (median, four mutations per patient). The most frequently mutated genes were WT1 (38%), NOTCH1 (29%), NRAS (29%), PHF6 (25%), TP53 (24%), ASXL1 (19%), FLT3 (19%), and IKZF1 (19%). All patients except one received multi-agent chemotherapy, and 22 patients underwent allogeneic stem cell transplantation. Thrombocytopenia, an abnormal karyotype, and TP53 mutation were associated with markedly shortened overall survival. Stem cell transplantation significantly improved overall survival. CONCLUSIONS: Patients with ETP-ALL often have high mutation burden with increased genomic instability. TP53 mutation was the only molecular prognostic marker and was associated with complex karyotype and greater than or equal to five mutations. These patients may benefit from stem cell transplantation, and recurrent gene mutations may be novel therapeutic markers.

A combination of genetically engineered oncolytic virus and melittin-CpG for cancer viro-chemo-immunotherapy.

BACKGROUND: Immunotherapy has emerged as an efficient therapeutic approach for cancer management. However, stimulation of host immune system against cancer cells often fails to achieve promising clinical outcomes mainly owing to the immunosuppressive characteristics of the tumor microenvironment (TME). Combination therapeutics that can trigger sustained immunogenic cell death (ICD) have provided new opportunities for cancer treatment. METHODS: In this study, we designed and applied an ICD inducer regimen, including a genetically engineered oncolytic virus (miRNA-modified coxsackieviruses B3, miR-CVB3), a pore-forming lytic peptide (melittin, found in bee venom), and a synthetic toll-like receptor 9 ligand (CpG oligodeoxynucleotides), for breast cancer and melanoma treatment. We compared the anti-tumor efficacy of miR-CVB3 and CpG-melittin (CpGMel) alone and in combination (miR-CVB3 + CpGMel) and investigated possible mechanisms involved. RESULTS: We demonstrated that miR-CVB3 + CpGMel had no major impact on viral growth, while enhancing the cellular uptake of CpGMel in vitro. We further showed that combination therapy led to significant increases in tumor cell death and release of damage-associated molecular patterns compared with individual treatment. In vivo studies in 4T1 tumor-bearing Balb/c mice revealed that both primary and distant tumors were significantly suppressed, and the survival rate was significantly prolonged after administration of miR-CVB3 + CpGMel compared with single treatment. This anti-tumor effect was accompanied by increased ICD and immune cell infiltration into the TME. Safety analysis showed no significant pathological abnormalities in Balb/c mice. Furthermore, the developed therapeutic regimen also demonstrated a great anti-tumor activity in B16F10 melanoma tumor-bearing C57BL/6 J mice. CONCLUSIONS: Overall, our findings indicate that although single treatment using miR-CVB3 or CpGMel can efficiently delay tumor growth, combining oncolytic virus-based therapy can generate even stronger anti-tumor immunity, leading to a greater reduction in tumor size.

Highly sensitive short-range mode resonance sensor with multilayer structured hyperbolic metamaterials.

Hyperbolic metamaterial (HMM) based sensors can achieve superior sensing performance than conventional surface plasmon resonance sensors. In this work, the operator approach to effective medium approximation (OEMA) is used to characterize the HMM dielectric constant properties of metal-dielectric multilayer structures, which are classified into short-range (SR) mode and long-range (LR) mode according to the propagation length of the bulk high K waves in HMM. The dispersion relations of SR modes are derived, and a high-sensitivity refractive index sensor is designed for the near-infrared SR mode resonance. The effects of the number of periods, cell thickness, metal fill rate and incidence angle on the SR mode resonance were analyzed for the multilayer structured HMM. Our designed sensing structure achieves a maximum sensitivity of 330 µm/RIU in the near-infrared band with a quality factor of 492 RIU-1. In addition, the simulations show that the SR mode resonance wavelength is flexible and tunable. We believe that the study of HMM-based SR mode resonance sensors offers potential applications for high-sensitivity biochemical detection.

Knockdown of let-7b in leukemia associated macrophages inhibit acute myeloid leukemia progression.

Macrophages, critical components of bone marrow microenvironment, are reported to be remodeled into leukemia-associated macrophages (LAMs) in leukemic microenvironment where they contribute to leukemia development, characterized as M2 macrophages with pro-tumor effects. However, how leukemic microenvironment transforms macrophages into LAMs remains unknown. Here, we analyzed the clinical relevance of LAMs and profiled their RNA-Seq from acute myeloid leukemia (AML) patients with complete remission (CR) after induction treatment and refractory AML patients. Our results showed that the proportion and number of LAMs in refractory AML patients was higher than that in CR patients and LAM was a poor prognostic factor of AML patients. Furthermore, let-7b was a potentially aberrant gene in LAMs contributed to M2-subtype characteristics. Knockdown of let-7b in LAMs could inhibit the development of AML by repolarizing LAMs toward M1-subtype characteristics through the activation of Toll-like receptor and NF-κB pathway. Our study provides insight for future LAM-based immunotherapy strategies for AML.

Crosstalk between RNA viruses and DNA sensors: Role of the cGAS-STING signalling pathway.

Despite only comprising half of all known viral species, RNA viruses are disproportionately responsible for many of the worst epidemics in human history, including outbreaks of influenza, poliomyelitis, Ebola, and most recently, the coronavirus disease-2019 (COVID-19) pandemic. The propensity for RNA viruses to replicate in cytosolic compartments has led to an evolutionary arms race and the emergence of cytosolic sensors to recognise and initiate the host innate immune response. Although significant progress has been made in identifying and characterising cytosolic RNA sensors as anti-viral innate immune factors, the potential role for cytosolic DNA sensors in RNA viral infection is only recently being appreciated. Among these, the cyclic GMP-AMP synthase (cGAS)-stimulator of interferon genes (STING) pathway has attracted increasing attention. The cGAS-STING signalling pathway has emerged as a key innate immune signalling axis that is implicated in diverse human diseases from infectious diseases to neurodegeneration and cancer. Here we review the existing literature on RNA viruses and their reciprocal interactions with the cGAS-STING pathway and share insights into RNA virus diversity by touching on the similarities and differences of RNA viral strategies.

Self-referenced refractive index sensor based on double-dips method with bimetal-dielectric and double-groove grating.

Self-referenced refractive index sensors allow more accurate measurements and reduce the influence of extraneous factors. This work proposed a high-sensitivity, self-referenced surface plasmon resonance sensor with Na grating and Au-ZnS composite grating. When Transverse Magnetic-polarized light is incident into the prism, three surface plasmon resonances are excited at the interface of Na-MgF2 grating and Au-ZnS grating. The first one is treated as the reference angle, the second and third are forward and backward surface plasmon resonance, respectively. Using the angular modulation, the single-dip sensitivities are 329.41 deg/RIU and 788.24 deg/RIU in the range of 1.330-1.347. To further improve the performance of the sensor, the double-dips method is adopted, and the average sensitivity in the range of 1.330-1.347 is 1117.65 deg/RIU, while the maximum reaches 4390 deg/RIU. Due to high sensitivity, a good figure of merit can be obtained even with a larger full width at half maximum of 3.30°. This proposed sensor provides potential application in the research of biomolecular detection and chemical testing.

Theoretical modeling and investigations of lossy mode resonance prism sensor based on TiO2 film.

The optical sensor based on lossy mode resonance can overcome the limitations of traditional surface plasmon resonance sensors and work under TE and TM polarized light. In this paper, an LMR sensor theoretical model with the configuration of prism/matching layer/lossy layer/sensing layer is proposed, which is based on the principle of attenuated total reflection. By using TiO2 film as the lossy layer and LiF film as the matching layer, the resonance signal under angle interrogation is effectively improved. One of the advantages of the proposed sensor is that the detection range and detection accuracy are dynamically adjustable, which provides additional degrees of freedom in the design and use of the device. The structural parameters (film thickness, layer refractive index) affecting the resonance signal have been investigated based on the electric field distribution at resonance and the coupled mode theory. The LMR signal under TE and TM polarization can be switched by changing the thickness ratio of the matching layer and the lossy layer. All possible combinations of film thicknesses are given as a reference for the design of the LMR prism sensor based on TiO2 film. Under proper thickness combination, the proposed sensor is capable of detecting the medium with refractive index ranging from 1.32 ∼ 1.47, with a sensitivity range of 34 ∼ 148 °/RIU under angle interrogation and a maximum value of 192 RIU-1 for FOM under TM polarization. We hope these investigations can prove the advantages of LMR prism sensors and provide guidance for the experimental implementation of LMR prism sensors in the future.

Evaluation of pediatric malignancies using total-body PET/CT with half-dose [18F]-FDG.

PURPOSE: To explore the impact of a true half dose of [18F]-FDG on image quality in pediatric oncological patients undergoing total-body PET/CT and investigate short acquisition times with half-dose injected activity. METHODS: One hundred pediatric oncological patients who underwent total-body PET/CT using the uEXPLORER scanner after receiving a true half dose of [18F]-FDG (1.85 MBq/kg) were retrospectively enrolled. The PET images were first reconstructed using complete 600-s data and then split into 300-s, 180-s, 60-s, 40-s, and 20-s duration groups (G600 to G20). The subjective analysis was performed using 5-point Likert scales. Objective quantitative metrics included the maximum standard uptake value (SUVmax), SUVmean, standard deviation (SD), signal-to-noise ratio (SNR), and SNRnorm of the background. The variabilities in lesion SUVmean, SUVmax, and tumor-to-background ratio (TBR) were also calculated. RESULTS: The overall image quality scores in the G600, G300, G180, and G60 groups were 4.9 ± 0.2, 4.9 ± 0.3, 4.4 ± 0.5, and 3.5 ± 0.5 points, respectively. All the lesions identified in the half-dose images were localized in the G60 images, while 56% of the lesions could be clearly identified in the G20 images. With reduced acquisition time, the SUVmax and SD of the backgrounds were gradually increased, while the TBR values showed no statistically significant differences among the groups (all p > 0.1). Using the half-dose images as a reference, the variability in the lesion SUVmax gradually increased from the G180 to G20 images, while the lesion SUVmean remained stable across all age groups. SNRnorm was highly negatively correlated with age. CONCLUSION: Total-body PET/CT with a half dose of [18F]-FDG (1.85 MBq/kg, estimated whole-body effective dose: 1.76-2.57 mSv) achieved good performance in pediatric patients, with sufficient image quality and good lesion conspicuity. Sufficient image quality and lesion conspicuity could be maintained at a fast scanning time of 60 s with half-dose activity.

Efficacy and safety comparison between R-CHOP and modified NHL-BFM-90 regimens in children and adolescents with diffuse large B-cell lymphoma.

Studies comparing the efficacy and safety of R-CHOP and modified non-Hodgkin lymphoma Berlin-Frankfurt-Münster-90 (NHL-BFM-90) regimens in children and adolescents with diffuse large B-cell lymphoma (DLBCL) are lacking. Thus, we retrospectively analyzed 85 DLBCL patients aged ≤18 years from 2000 to 2020; 74 patients received the modified NHL-BFM-90 regimen, and 11 received the R-CHOP regimen. The 5-year OS and event-free survival (EFS) rates between the modified NHL-BFM-90 and R-CHOP regimens were 91.0% vs. 90.9% (P = 0.466) and 89.8% vs. 68.6% (P = 0.055), respectively. In the stratified analysis, the survival outcome of pediatric patients treated with the modified NHL-BFM-90 regimen was not significantly different from that of adolescent patients. The OS and EFS rates of patients with early-stage disease were both 100%. Patients in the advanced-stage group who were treated with the modified NHL-BFM-90 regimen had superior EFS rates (P < 0.05). The frequency of severe adverse events from the two regimens was similar. There were no treatment-related deaths. We concluded that the modified NHL-BFM-90 regimen has better efficacy than R-CHOP in DLBCL patients with advanced-stage disease. However, the R-CHOP regimen might be an option for early-stage DLBCL. Further prospective studies are needed to guide clinical decisions about treatment.

Gene rppA co-regulated by LRR, SigA, and CcpA mediates antibiotic resistance in Bacillus thuringiensis.

Antibiotic resistance genes are usually tightly controlled by transcription factors and RNA regulatory elements including sRNAs, riboswitches, and attenuators, and their expression is activated to respond to antibiotic exposure. In previous work, we revealed that the rppA gene is regulated by attenuator LRR and two mistranslation products in Bacillus thuringiensis BMB171. However, its function and promoter regulation is still not precise. In this study, we demonstrated that the encoding product of the rppA gene acts as an ARE1 ABC-F protein and confers resistance to antibiotics virginiamycin M1 and lincomycin when overexpressed. Besides the reported attenuator LRR, the expression of the rppA gene is controlled by the sigma factor SigA and a global transcription factor CcpA. Consequently, its promoter activity is mainly maintained at the stationary phase of cell growth and inhibited in the presence of glucose. Our study revealed the function and regulation of the rppA gene in detail. KEY POINTS: • The RppA protein acts as an ARE1 ABC-F protein • The rppA gene confers resistance to antibiotics virginiamycin M1 and lincomycin when overexpressed • The expression of the rppA gene is regulated by the sigma factor SigA and the pleiotropic regulator CcpA.

Modified conditioning regimen with chidamide and high-dose rituximab for triple-hit lymphoma.

Triple-hit lymphoma (THL), which is classified into high-grade B-cell lymphoma with rearrangements of MYC, BCL2 and BCL6, presents aggressive biological behaviour. High-dose chemotherapy followed by autologous hematopoietic stem cell transplantation (auto-HSCT) is considered to be one of the recommended treatment options. Here, we reported 3 THL patients received carmustine, etoposide, cytarabine and cyclophosphamide (BEAC) combined with chidamide and high-dose rituximab conditioning regimen and found that this conditioning showed good efficacy and tolerance without increase of adverse events.

Novel fully human anti-CD47 antibodies stimulate phagocytosis and promote elimination of AML cells.

Although most patients with acute myeloid leukemia (AML) enter remission after induction chemotherapy, the risk of relapse remains considerable. Therefore, some novel therapeutic strategies are still required. This study found that the overexpression of CD47 on AML cells was at least twofold more than that on normal bone marrow (NBM) cells in 81% (17/21) of the investigated patients; no patients had lower expression level of CD47 compared with healthy donors. The study also demonstrated that blocking the CD47/SIRPα (signal regulatory protein α) signal with the established novel fully human anti-CD47 monoclonal antibodies increased the phagocytosis of AML cells by macrophages in vitro. Furthermore, in vivo experiments showed that the novel fully human anti-CD47 monoclonal antibodies could significantly prolong the survival time of mice. Overall, the novel fully human anti-CD47 antibodies could block CD47/SIRPα interaction, increase macrophage-mediated phagocytosis, and enhance the elimination of AML cells.

Multimodal Treatment of Children With Sacrococcygeal Yolk Sac Tumor: Retrospective Analysis of Clinicopathology Characteristics and Relapse-free Survival.

The aim of the study was to explore the clinicopathologic characteristics of sacrococcygeal yolk sac tumor (SYST) associated with relapse and the role of sensitivity to neoadjuvant chemotherapy in predicting outcome. The authors investigated prognostic factors of age, stage, initial tumor size, pathologic response to neoadjuvant chemotherapy, and alfa fetoprotein. A total of 26 patients with SYST were enrolled. Neoadjuvant chemotherapy was administered to 20 cases. Six patients underwent resection as initial therapy. Recurrence occurred in 12 patients. Nine patients with specimens exhibiting no malignant component after chemotherapy did not experience recurrence. By contrast, relapses occurred in 7 of 11 patients with viable residual tumor after neoadjuvant chemotherapy. All relapsed patients still achieved partial remission or complete remission after salvage therapy. Five-year relapse-free survival and overall survival rates were 55.2% and 100%, respectively (median follow-up, 59.5 mo; range, 16 to 155). Patients with complete necrosis after neoadjuvant chemotherapy had a better outcome compared with children with viable residual tumor. Relapse-free survival of pediatric SYSTs in this cohort were still low and warrants the multidisciplinary effort.

Application of a modified biological flocculant in total nitrogen treatment of leather wastewater.

Leather wastewater harms the ecological environment and human health. In this study, a modified bio-flocculant was prepared to facilitate treatment of leather wastewater. A bio-flocculant produced by Bacillus cereus was combined with amphoteric starch and modified using a cerium ammonium nitrate initiator. Single factor optimization and orthogonal optimization were used to determine the optimal preparation conditions as follows: amphoteric starch-to-flocculant ratio = 22:30; reaction temperature = 64 °C; initiator dosage = 2.00%; reaction time = 15 min; stirring speed = 600 rpm; and flocculation system pH = 8.0. At a dosage of 1 g/L added to simulated leather industry wastewater, the flocculation efficiency (98.17%) and the total nitrogen removal efficiency (100.00%) of modified bio-flocculant was superior to that achieved by 1 g/L of unmodified bio-flocculant (72.16% and 50.00%, respectively), amphoteric starch (8.50% and 0.00%) and polyacrylamide (95.55% and 75.00%). Analysis of natural and flocculated precipitates in the wastewater showed that the modified bio-flocculant significantly changed several characteristics of the flocculated particles; in addition, it promoted the removal of nitrogenous substances in the process of denitrification. These changes helped explain the material's flocculating ability. The results confirmed that the modified bio-flocculant was an effective additive for treating leather wastewater.

Quality of life and related demographic factors in long-term survivors of childhood non-Hodgkin's lymphoma. / å„¿ç«¥éžéœå¥‡é‡‘æ·‹å·´ç˜¤é•¿æœŸç”Ÿå­˜è€ ç”Ÿæ´»è´¨é‡åŠç›¸å ³äººå£å­¦å› ç´ ç ”ç©¶.

OBJECTIVES: To evaluate the quality of life and related demographic factors in long-term survivors of childhood non-Hodgkin's lymphoma (NHL). METHODS: A retrospective analysis was performed on the medical and demographic data of the NHL patients who received treatment in the Sun Yat-sen University Cancer Center and achieved long-term survival at follow-up, with an age of <18 years at initial diagnosis and a present age of ≥18 years. A questionnaire survey was performed using 36-Item Short-Form Health Survey (SF-36) and the symptom subscale of the Chinese version of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-Core 30 (QLQ-C30). The health status of long-term survivors of NHL was evaluated by comparing the scores of various dimensions of the SF-36 scale of general adult population in the United States (American norm) and those of the SF-36 scale of general adult population in Hong Kong, China (Hong Kong norm). The correlation between the score of each dimension of the scale and demographic characteristics was evaluated. The symptoms of long-term NHL survivors were evaluated according to the score of QLQ-C30 scale. RESULTS: A total of 23 patients with NHL with complete follow-up data were enrolled. The pathological types included diffuse large B-cell lymphoma in 10 patients, Burkitt lymphoma in 4 patients, T-cell lymphoblastoma in 5 patients, B-cell lymphoblastoma in 3 patients, and natural killer/T cell lymphoma in 1 patient. All patients received the chemotherapy regimen containing anthracyclines and alkylating agents. The median present age was 26.2 years (range: 16.9-55.8 years), and the median age at initial diagnosis was 10.4 years (range: 2.4-17.6 years). Among the 23 patients, 6 were married and had children and 2 had chronic diseases. There was no significant difference between the long-term survivors and the US norm in role physical, general health, role-emotional, and mental health (P>0.05), while the long-term survivors had significantly better scores of the other dimensions than the US norm (P<0.05). Similar results were obtained for the comparison between the long-term survivors and the China Hong Kong norm. Age at initial diagnosis was negatively correlated with the scores of social functioning, role physical, and general health in the SF-36 scale (P<0.05), and the present age of patients was positively correlated with the score of physical functioning and was negatively correlated with the score of general health (P<0.05). The urban and rural distribution of patients was related to the general health status (P<0.05). In addition, the long-term survivors of childhood NHL had relatively low scores of the symptom domain of QLQ-C30, and few moderate or severe symptoms were found. CONCLUSIONS: Long-term survivors of childhood NHL tend to have a good overall health status, with no significant differences compared with the general population. Age at initial diagnosis is the main demographic factor that affects patients' quality of life. Citation.

The prognosis of prechemotherapy blastemal predominant histology subtype in Wilms tumor: A retrospective study in China.

PURPOSE: This study aimed to retrospectively analyze survival outcomes for Chinese patients with prechemotherapy blastemal predominant histology type Wilms tumors (WTs). METHODS: We collected and analyzed clinical data concerning patients aged <15 years with favorable histology (FH) WTs treated at the Sun Yat-Sen University Cancer Center from December 2005 to May 2016, based on the Children's Oncology Group protocol. Pathological specimens were collected through biopsy or surgical resection before initiation of chemotherapy. We analyzed survival outcomes involving different prechemotherapy histology subtypes. RESULTS: We enrolled 97 patients with FH WTs (median follow-up, 71.5 months; range, 22.2-170.7). The total recurrence rate was 17.5%, and the subtype recurrence rates were as follows: blastemal predominant (45.5%), mixed (7.5%), epithelial (14.3%), and mesenchymal (9.5%) (P = .010). Five-year event-free survival (EFS) and overall survival (OS) rates were 84.9% and 81.4%, respectively. Respective 5-year EFS and OS rates for subtypes were as follows: blastemal predominant (54.5% and 68.2%), mixed (90.0% and 88.9%), epithelial (85.7% and 85.1%), and mesenchymal (90.5% and 94.7%). Multivariate survival analyses showed that the blastemal predominant subtype was an independent prognostic factor of EFS (P = .001) and OS (P = .017). CONCLUSIONS: Our findings showed that prechemotherapy blastemal predominant WTs had higher recurrence and lower EFS and OS rates. Our findings suggested that, albeit with some deficiencies, blastemal predominant histology WT-diagnosed prechemotherapy may have prognostic relevance. Further research into other potential confounding variables are required to determine whether such patients warrant altered risk-stratified therapy.

Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model.

The real-time detection of pine cones in Korean pine forests is not only the data basis for the mechanized picking of pine cones, but also one of the important methods for evaluating the yield of Korean pine forests. In recent years, there has been a certain number of detection accuracy for image processing of fruits in trees using deep-learning methods, but the overall performance of these methods has not been satisfactory, and they have never been used in the detection of pine cones. In this paper, a pine cone detection method based on Boundary Equilibrium Generative Adversarial Networks (BEGAN) and You Only Look Once (YOLO) v3 mode is proposed to solve the problems of insufficient data set, inaccurate detection result and slow detection speed. First, we use traditional image augmentation technology and generative adversarial network BEGAN to implement data augmentation. Second, we introduced a densely connected network (DenseNet) structure in the backbone network of YOLOv3. Third, we expanded the detection scale of YOLOv3, and optimized the loss function of YOLOv3 using the Distance-IoU (DIoU) algorithm. Finally, we conducted a comparative experiment. The experimental results show that the performance of the model can be effectively improved by using BEGAN for data augmentation. Under same conditions, the improved YOLOv3 model is better than the Single Shot MultiBox Detector (SSD), the faster-regions with convolutional neural network (Faster R-CNN) and the original YOLOv3 model. The detection accuracy reaches 95.3%, and the detection efficiency is 37.8% higher than that of the original YOLOv3.

Fusion of Hyperspectral CASI and Airborne LiDAR Data for Ground Object Classification through Residual Network.

Modern satellite and aerial imagery outcomes exhibit increasingly complex types of ground objects with continuous developments and changes in land resources. Single remote-sensing modality is not sufficient for the accurate and satisfactory extraction and classification of ground objects. Hyperspectral imaging has been widely used in the classification of ground objects because of its high resolution, multiple bands, and abundant spatial and spectral information. Moreover, the airborne light detection and ranging (LiDAR) point-cloud data contains unique high-precision three-dimensional (3D) spatial information, which can enrich ground object classifiers with height features that hyperspectral images do not have. Therefore, the fusion of hyperspectral image data with airborne LiDAR point-cloud data is an effective approach for ground object classification. In this paper, the effectiveness of such a fusion scheme is investigated and confirmed on an observation area in the middle parts of the Heihe River in China. By combining the characteristics of hyperspectral compact airborne spectrographic imager (CASI) data and airborne LiDAR data, we extracted a variety of features for data fusion and ground object classification. Firstly, we used the minimum noise fraction transform to reduce the dimensionality of hyperspectral CASI images. Then, spatio-spectral and textural features of these images were extracted based on the normalized vegetation index and the gray-level co-occurrence matrices. Further, canopy height features were extracted from airborne LiDAR data. Finally, a hierarchical fusion scheme was applied to the hyperspectral CASI and airborne LiDAR features, and the fused features were used to train a residual network for high-accuracy ground object classification. The experimental results showed that the overall classification accuracy was based on the proposed hierarchical-fusion multiscale dilated residual network (M-DRN), which reached an accuracy of 97.89%. This result was found to be 10.13% and 5.68% higher than those of the convolutional neural network (CNN) and the dilated residual network (DRN), respectively. Spatio-spectral and textural features of hyperspectral CASI images can complement the canopy height features of airborne LiDAR data. These complementary features can provide richer and more accurate information than individual features for ground object classification and can thus outperform features based on a single remote-sensing modality.