Deep Augmented Metric Learning Network for Prostate Cancer Classification in Ultrasound Images.

Prostate cancer screening often relies on cost-intensive MRIs and invasive needle biopsies. Transrectal ultrasound imaging, as a more affordable and non-invasive alternative, faces the challenge of high inter-class similarity and intra-class variability between benign and malignant prostate cancers. This complexity requires more stringent differentiation of subtle features for accurate auxiliary diagnosis. In response, we introduce the novel Deep Augmented Metric Learning (DAML) network, specifically tailored for ultrasound-based prostate cancer classification. The DAML network represents a significant innovation in the metric learning space, introducing the Semantic Differences Mining Strategy (SDMS) to effectively discern and represent subtle differences in prostate ultrasound images, thereby enhancing tumor classification accuracy. Additionally, the DAML network strategically addresses class variability and limited sample sizes by combining the Linear Interpolation Augmentation Strategy (LIAS) and Permutation-Aided Reconstruction Loss (PARL). This approach enriches feature representation and introduces variability with straightforward structures, mirroring the efficacy of advanced sample generation techniques. We carried out comprehensive empirical assessments of the DAML model by testing its key components against a range of models, ensuring its effectiveness. Our results demonstrate the enhanced performance of the DAML model, achieving classification accuracies of 0.857 and 0.888 for benign and malignant cancers, respectively, underscoring its effectiveness in prostate cancer classification via medical imaging.

[A case of neonatal Netherton syndrome]. / 新生儿Netherton综合征1例.

A male infant, aged 6 days, was admitted to the hospital due to respiratory distress and systemic desquamative rash after birth. The infant presented with erythema and desquamative rash, respiratory failure, recurrent infections, chronic diarrhea, hypernatremic dehydration, and growth retardation. Comprehensive treatment, including anti-infection therapy, intravenous immunoglobulin administration, and skin care, resulted in improvement of the rash, but recurrent infections persisted. Second-generation sequencing revealed a homozygous mutation in the SPINK5 gene, consistent with the pathogenic variation of Netherton syndrome. The family opted for palliative care, and the infant died at the age of 2 months after discharge. This report documents a case of Netherton syndrome caused by the SPINK5 gene mutation in the neonatal period, and highlights multidisciplinary diagnosis and therapy for this condition.

The influence of emerging atmospheric organophosphorus flame retardants from land source emissions on the East China Sea.

Organophosphate flame retardants (OPFRs) pose a new challenge to the marine environment due to their toxicity and persistence. This study explores the contributions of OPFR emissions from different land sources and sectors to its contamination of the East China Sea (ECS) using a novel atmospheric transport model（ChnMETOP）for POPs and a marine food web model. The results show that the major land sources causing OPFR pollution in the ECS were situated in Yangtze River Delta (YRD) and middle reach areas of China's Yangtze River, confirming that source proximity made most significant contributions to OPFR pollution in the ECS. Among those OPFR emission sectors, industrial emissions accounted for the highest modeled OPFR levels in the seawaters, followed by the OPFR usage process in textile, plastic, and rubber products. Assessment of bioaccumulation of OPFR in the marine food web of the ECS and the potential risk in commercial fish consumers reveals lower exposure risk via dietary fish ingestion. However, the risk might increase if OPFRs are continuously bioaccumulated in the biotic and released into the abiotic marine environment. This study simultaneously identified both the source locations and emission sectors, thereby providing important policy implications in mitigating OPFR pollution in the ECS marine environment.

Prediction of postoperative recurrence of oral cancer by artificial intelligence model: Multilayer perceptron.

BACKGROUND: Postoperative recurrence of oral cancer is an important factor affecting the prognosis of patients. Artificial intelligence is used to establish a machine learning model to predict the risk of postoperative recurrence of oral cancer. METHODS: The information of 387 patients with postoperative oral cancer were collected to establish the multilayer perceptron (MLP) model. The comprehensive variable model was compared with the characteristic variable model, and the MLP model was compared with other models to evaluate the sensitivity of different models in the prediction of postoperative recurrence of oral cancer. RESULTS: The overall performance of the MLP model under comprehensive variable input was the best. CONCLUSION: The MLP model has good sensitivity to predict postoperative recurrence of oral cancer, and the predictive model with variable input training is better than that with characteristic variable input.

Self-supervised dual-head attentional bootstrap learning network for prostate cancer screening in transrectal ultrasound images.

Current convolutional neural network-based ultrasound automatic classification models for prostate cancer often rely on extensive manual labeling. Although Self-supervised Learning (SSL) have shown promise in addressing this problem, those data that from medical scenarios contains intra-class similarity conflicts, so using loss calculations directly that include positive and negative sample pairs can mislead training. SSL method tends to focus on global consistency at the image level and does not consider the internal informative relationships of the feature map. To improve the efficiency of prostate cancer diagnosis, using SSL method to learn key diagnostic information in ultrasound images, we proposed a self-supervised dual-head attentional bootstrap learning network (SDABL), including Online-Net and Target-Net. Self-Position Attention Module (SPAM) and adaptive maximum channel attention module (CAAM) are inserted in both paths simultaneously. They captures position and inter-channel attention and of the original feature map with a small number of parameters, solve the information optimization problem of feature maps in SSL. In loss calculations, we discard the construction of negative sample pairs, and instead guide the network to learn the consistency of the location space and channel space by drawing closer to the embedding representation of positive samples continuously. We conducted numerous experiments on the prostate Transrectal ultrasound (TRUS) dataset, experiments show that our SDABL pre-training method has significant advantages over both mainstream contrast learning methods and other attention-based methods. Specifically, the SDABL pre-trained backbone achieves 80.46% accuracy on our TRUS dataset after fine-tuning.

Effect of low-temperature stress on the survival of Meloidogyne incognita and its application in greenhouse of northern China.

We examined the effects of low temperature on egg hatching and killing rate of the 2nd instars of Meloi-dogyne incognita (J2) in the laboratory. We further evaluated the effects of two soil treatment methods on the survival rate of M. incognita in northern China in a field experiment. The results of laboratory experiment showed that survival rate of J2 was 0 after being subjected to -7 ℃ for 24 hours, and that egg hatching was completely inhibited 24 hours after being subjected to -9 ℃. The survival rate of J2 was 0 after being subjected to -1, -2, -3, and -4 ℃ for 8, 5, 3, and 1.5 d, respectively. Egg hatching was completely inhibited after being subjected to -2, -3, -4, and -5 ℃ for 9, 6, 4, and 1 d, respectively. Results of the fitting analysis showed that both the relationships between the temperature and the lethal time of J2 as well as the temperature and the non-hatching time of the eggs followed exponential functions. The results of field test showed that death rate of M. incognita in 0-50 cm soil layer after ridging treatment and 0-30 cm soil layer after leveling treatment could reach 100%, while the disease index of the former in 30-40 cm and 40-50 cm was 84.9% and 75.8%, respectively, which was lower than that in the greenhouse. Our results suggest that preventing and controlling M. incognita in greenhouses through low-tempe-rature in winter could achieve a better control effect in Yulin City and the northward region. The proposed technique is convenient and has high potential for popularization.

Ultrasonographic pathological grading of prostate cancer using automatic region-based Gleason grading network.

The Gleason scoring system is a reliable method for quantifying the aggressiveness of prostate cancer, which provides an important reference value for clinical assessment on therapeutic strategies. However, to the best of our knowledge, no study has been done on the pathological grading of prostate cancer from single ultrasound images. In this work, a novel Automatic Region-based Gleason Grading (ARGG) network for prostate cancer based on deep learning is proposed. ARGG consists of two stages: (1) a region labeling object detection (RLOD) network is designed to label the prostate cancer lesion region; (2) a Gleason grading network (GNet) is proposed for pathological grading of prostate ultrasound images. In RLOD, a new feature fusion structure Skip-connected Feature Pyramid Network (CFPN) is proposed as an auxiliary branch for extracting features and enhancing the fusion of high-level features and low-level features, which helps to detect the small lesion and extract the image detail information. In GNet, we designed a synchronized pulse enhancement module (SPEM) based on pulse-coupled neural networks for enhancing the results of RLOD detection and used as training samples, and then fed the enhanced results and the original ones into the channel attention classification network (CACN), which introduces an attention mechanism to benefit the prediction of cancer grading. Experimental performance on the dataset of prostate ultrasound images collected from hospitals shows that the proposed Gleason grading model outperforms the manual diagnosis by physicians with a precision of 0.830. In addition, we have evaluated the lesions detection performance of RLOD, which achieves a mean Dice metric of 0.815.

The Clinical Characteristics and Serological Outcomes of Infants With Confirmed or Suspected Congenital Syphilis in Shanghai, China: A Hospital-Based Study.

Background: Congenital syphilis (CS) is the infection of an infant or fetus with Treponema pallidum. The aim of this study was to investigate the clinical features and outcomes of serology reversion in infants diagnosed with confirmed or suspected congenital syphilis (CS). Methods: Infants admitted to the neonatal department of Children's Hospital of Fudan University from 2013 to 2016 who met the case definition of CS or suspected CS were included in this study. Follow-up was performed in an outpatient clinic until reversion to non-reactivity of both toluidine red unheated serum test (TRUST) and Treponemal pallidum particle agglutination (TPPA). Follow-up data were collected until up to the end of 2019, when the last infant with CS reached 3 years of age. Results: In total, 682 infants were enrolled in this study, including 63 in the CS group and 619 in the suspected CS group. Forty-seven infants (74.6%) in the CS group had symptoms, and 57 (90.5%) had abnormal laboratory and/or long bone X-ray findings. By 6 months of age, TRUST results were negative in 53.3% of the infants with CS and in 100% of the infants with suspected CS. All the infants in the CS group returned to TRUST non-reactivity by 18 months of age. The TPPA results at 18 months of age showed that only 10.0% (3/30) of the patients in the CS group returned to non-reactivity, while a 99.6% (548/550) non-reactivity rate was observed in the suspected CS group. All the infants in the CS group returned to 19S-IgM-TPPA non-reactivity by 6 months of age. Conclusions: Although CS is an burdensome disease that may cause fetal and neonatal death, CS responds well to treatment when diagnosed and treated promptly, even when symptoms or lab/X-ray findings are present at birth.

Incidence of retinopathy of prematurity treatment in extremely preterm infants in China.

BACKGROUND: Retinopathy of prematurity (ROP) continues to be a major cause of visual impairment and blindness in premature infants and children. OBJECTIVES: To investigate the incidence of severe ROP receiving treatment in extremely preterm (EP) infants in China over time. The risk factors for ROP treatment were also assessed. METHODS: This was a multicentre retrospective study and a subanalysis of baseline data from the "Outcomes of EP infants in China 2010-2019" study. This study was conducted in 68 tertiary neonatal care centres from 31 provinces of China. Infants with a gestational age of 230 -276  weeks and admitted to a neonatal unit within the first 72 h of life between 2010 and 2019 were enrolled. Incidence of ROP was analysed in infants who survived to 32 weeks postmenstrual age and screened for ROP. Multivariable modified Poisson regression models were used to identify risk factors for ROP treatment. RESULTS: Among 7295 eligible infants, 4701 (64.5%) survived to 32 weeks postmenstrual age and met ROP screening criteria. Of the 3756 infants who screened and with ROP data, 2320 (61.8%) developed ROP of any stage. The overall incidence of ROP treatment was 12.6%, decreasing from 45.5% at 23 weeks to 8.3% at 27 weeks. During the 10-year period, the incidence of ROP treatment did not change, although the incidence of any ROP increased over time. Independent risk factors associated with ROP treatment included lower gestational age, small for gestational age, multiple birth, severe intraventricular haemorrhage, patent ductus arteriosus and supplemental oxygen duration. CONCLUSIONS: The incidence of EP infants receiving ROP treatment showed no change during this 10-year period in China. Prevention of prematurity and foetal growth restriction, judicious use of oxygen and reducing comorbidities are promising factors that may reduce the incidence of ROP needing treatment in these high-risk infants.

Ten-Year Trend of Retinopathy of Prematurity Among Extremely Preterm Infants in One Neonatal Intensive Care Unit in China.

Background: Extremely preterm (EP) infants are at the highest risk of retinopathy of prematurity (ROP). With more EP infants survived in China, recent data of ROP is lacking. The aim of the study is to report the trend of incidence of ROP among EP infants in a large neonatal intensive care unit in China over the past 10-year period, in relation with the overall survival rate and the change of oxygen saturation targets. Methods: This retrospective cohort study enrolled all EP infants born before 28 weeks' gestation and admitted to one of the largest tertiary neonatal intensive care units in China from 2010 to 2019. Data were compared between two time periods according to different oxygen saturation targets: 2010-2014 (P1) with low saturation target and 2015-2019 (P2) with higher target. Results: Of 630 EP infants admitted during the 10 years, 447 (71.0%) infants survived to discharge. The survival rate increased significantly from 61.6% in P1 to 75.8% in P2 (P < 0.05). Of the 472 infants who had ROP data, 318 (67.4%) developed ROP of any stage, 67 (14.2%) developed severe ROP, and 44 (9.3%) received treatment. The incidence of any ROP increased significantly from 51.7% in P1 to 74.3% in P2 (P < 0.05). The incidence of severe ROP increased from 11.0% in P1 to 15.6% in P2, and ROP treatment increased from 6.9% in P1 to 10.4% in P2, but neither reached statistical significance (both P > 0.05). Conclusions: We observed an increasing trend in the incidence of ROP across the 10-year period in one of the largest neonatal care units in China. The increased survival rate and the use of high-target oxygen saturation in the later period may partly explain this trend. Further investigations are needed to improve the care practices and to reduce the incidence of severe ROP.

Different Types of Minor Blood Group Incompatibility Causing Haemolytic Disease of Neonates in one of the National Children's Medical Centre in China.

PURPOSE: To review the neonatal cases with different types of minor blood group incompatible haemolytic diseases in China, and to improve the clinical understanding and management. MATERIALS AND METHODS: Seven cases from January, 1st, 2013 to December 31st, 2019 were searched out and reviewed retrospectively. All clinical data and laboratory findings were collected. RESULTS: There were totally seven cases enrolled including three cases of MNS, three of Diego, and one of Kidd combined with Rh, anti-RhE incompatibility. Among the seven cases, two had intrauterine transfusion, two underwent exchange transfusion, five received intravenous immune globulin, five cases developed anaemia, and three of them had transfusion. But among them, only four were found to have positive antibody screening and three were confirmed HDN with antibody types antenatally. CONCLUSION: The clinical presentation is diverse. Antibody screening followed by the technique of peak systolic velocity in the fetal middle cerebral artery (MCA-PSV) helps to filter out the severe cases.

Microchip Nd:YAG dual-frequency laser interferometer for displacement measurement.

The dual-frequency laser interferometer is an indispensable instrument to measure length, position, deformation and other parameters with high precision and long measurement distance in the advanced manufacturing industry and scientific research. In general, the light source of interferometer is the dual-frequency He-Ne laser. The disadvantages of He-Ne laser include generally large size, more heat radiation to the environment, and limited service life, which limits its application. In this paper, we study a microchip Nd:YAG dual-frequency laser interferometer with a 17.4 MHz frequency difference, which is formed by the stress-induced birefringence in the microchip itself. The down-conversion mixer is designed to decrease the beat frequency to about 5 MHz in heterodyne signal preprocessing modular to meet the bandwidth of phase meter. The experimental results show that the microchip Nd:YAG dual-frequency laser interferometer has a displacement resolution of 10 nm and a measuring range of 500 mm. Due to the advantages of the microchip dual-frequency laser, such as small size (40×40×35 mm), good portability, less power consumption and almost infinite service life, the microchip Nd:YAG dual-frequency laser interferometer has broad application prospects.

Ultrasound-modulated laser feedback tomography in the reflective mode.

A novel method of ultrasound-modulated optical tomography (UOT) detection based on the laser feedback technology is proposed in this Letter. The system has advantages such as a simple structure, high sensitivity, and reflective configuration. Effective penetration depths of up to 9 cm and 5 cm in phantom and biological tissues, respectively, have been demonstrated experimentally. The detection capability is comparable with the state of the art in the transmission mode but with a much lower photon consumption. Although a lot remains to be improved, the proposed method is promising for further development toward practical applications.

Assessment of the performance of blood glucose monitoring systems for monitoring dysglycaemia in neonatal patients.

OBJECTIVE: To validate a three-step protocol that assesses the clinical risk associated with using blood glucose monitoring systems (BGMS) in neonates for the management of dysglycaemia. METHOD: The three-step validation approach included confirmation of the accuracy of the reference method using National Institute of Standards and Technology (NIST) glucose standards, assessment of analytical risk performed on whole blood collected from paediatric patients routinely tested for glucose and a clinical risk assessment performed using heel stick capillary samples collected from 147 new-born babies and neonates admitted to intensive care. BGMS glucose measurements were compared with the NIST aligned laboratory reference method. RESULTS: The accuracy of the laboratory reference method was confirmed with the NIST standards. Specificity studies demonstrated that the accuracy of one of the BGMS was affected, particularly, in the hypoglycaemic range, by known interference factors including haematocrit, ascorbic acid, lactose, galactose, N-acetylcysteine and glutathione. The accuracy of the other BGMS was unaffected. The clinical performance of this BGMS in neonates met the system accuracy criteria of Clinical and Laboratory Standards Institute (CLSI) POCT 12-A3 standard for evaluating hospital BGMS with 95.1% of glucose measurements within±0.67 mmol/L for samples ≤5.55 mmol/L and 95.6% within±12.5% for samples>5.55 mmol/L. CONCLUSIONS: This three-step validation protocol provides a challenging approach for determining the accuracy and reliability of BGMS for managing dysglycaemia in neonates. StatStrip BGMS achieved analytical and clinical performance criteria confirming its suitability for use in neonates. We advocate that this validation approach should be considered for performance evaluations of both BGMS and continuous glucose monitoring systems going forward.

Depth of focus extension by filtering in the frequency domain in laser frequency-shifted feedback imaging.

The depth of focus extension in optical imaging is of considerable interest. In this paper, a laser frequency-shifted feedback scanning imaging configuration is demonstrated whose depth of focus is greatly extended through numerical filtering. The transmission characteristics of the system are studied. The original image is acquired through a two-dimensional scanning point by point with the target placed on a defocused plane. Filtered in the frequency domain, images on any oriented plane can be refocused. The superior performances are presented by imaging a three-dimensional target, and the process of gradual refocusing is demonstrated. To obtain the maximum extension in the depth of defocus, a series of numerical experiments has been carried out, which reveals its depth of focus is capable of being extended to four times the length of the objective focus length. The fabulous performances can motivate three-dimensional surface profile measurement.

Full path compensation laser feedback interferometry for remote sensing with recovered nanometer resolutions.

The accuracy of the existing laser feedback interferometry for measuring the remote target is limited to several microns due to environmental disturbances. A novel approach is presented in this paper based on the double-beam frequency-shift feedback of the laser, which can completely eliminate the dead path errors and measure the displacement or vibration with accuracy at nanometer scale even at a far measurement distance. The two beams emitted from one Nd:YVO4 crystal are incident on the measurement target and its adjacent reference surface, respectively. The reference surface could be taken from the nearby stationary object, without the need to put a reference mirror. The feedback paths and shift frequencies of the two beams are the same, so the air disturbances and the thermal effects in the way could be fully compensated. Under common room conditions, the displacement of a steel block at a distance of 10 m is measured, which proved that the system's stability is ±12 nm in 100 s and ±50 nm in 1000 s, the short-term resolution is better than 3 nm, and the linearity within the 300 mm range is 5 × 10-6 and within the 100 µm range is 1 × 10-4.

Ultrasound modulated laser confocal feedback imaging inside turbid media.

Ultrasound modulated laser confocal feedback technology is proposed in the imaging inside turbid media. By selecting the detectable signal photons and rejecting the background noise photons in the frequency domain based on the ultrasound modulation, the signal-to-noise ratio (SNR) can be much improved, especially in the turbid media, compared with the traditional imaging without ultrasound modulation. This is a promising method to reach both a larger penetration depth and a better SNR than other optical methods.

The complete mitochondrial genome of Scythropus yasumatsui (Coleoptera: Curculionidae).

The complete mitochondrial genome sequence of Scythropus yasumatsui (Coleoptera: Curculionidae) was determined by using an Illumina platform. The circular genome was 16,472 bp in length and contained 22 transfer RNA genes (tRNAs), two ribosomal RNA genes (rRNAs), 13 protein-coding genes (PCGs), and one control region. The nucleotide composition was significantly biased (A, G, C, and T was 39.74%, 10.11%, 15.41%, and 34.74%, respectively) with A + T contents of 74.49%. All PCGs were initiated with standard ATN (ATG/ATT) codons. While 10 PCGs were terminated with TAA, two PCGs were terminated with TAG (cytb and nad1), and nad5 was terminated with an incomplete stop codon TA. All tRNAs were predicted to contain typical cloverleaf secondary structures except trnS1. The phylogenetic analysis of the concatenated nucleotide sequences of 13 PCGs from 12 Curculionidae species was performed by using MrBayes 3.1.2. The results indicated that S. yasumatsui was more closely related to Naupactus xanthographus than to other species.

Common-path heterodyne self-mixing interferometry with polarization and frequency multiplexing.

A heterodyne Nd:YVO4 microchip laser self-mixing interferometry based on frequency and polarization multiplexing has been demonstrated. By using two orthogonally polarized lights to measure the measurement and reference target, the effect of the acousto-optic crystal thermal creep and air disturbance in interference light path is eliminated. In addition, the measurement error caused by the difference between two identical microchip lasers is compensated for by shifted frequency multiplexing technique. A rate equations model with multi-channel frequency-shifted feedback is established for interpreting the principle of the interferometry. Due to the ultrahigh sensitivity of the microchip laser, the target used in the experiment is a non-cooperative object which is different from the targets in conventional Michelson interferometers. Under typical room conditions, the short-term resolution is better than 2.5 nm, and the long-term zero drift is less than 60 nm within 7 h. The result shows that this self-mixing interferometry system is feasible and robust in the field of displacement measurement.

Fiber self-mixing interferometer with orthogonally polarized light compensation.

A fiber heterodyne self-mixing interferometer with orthogonally polarized light compensation is achieved. This system can adapt to various complex scenes while still keeping ultra-high sensitivity and anti-disturbance capability. Ultra-high sensitivity microchip laser is used as the laser source and polarization maintaining(PM) fiber makes the light path easy to accommodate to complex spaces, such as remote or narrow and small space. Besides, orthogonally polarized light inside PM fiber can eliminate the measurement error on account of environment disturbance. At present, the displacement resolution could be less than 10nm, which shows a great potential in nano-metrology.