Diabetic retinopathy identification based on multi-sourcefree domain adaptation

AIM:To address the challenges of data labeling difficulties,data privacy,and necessary large amount of labeled data for deep learning methods in diabetic retinopathy(DR)identification,the aim of this study is to develop a source-free domain adaptation(SFDA)method for efficient and effective DR identification from unlabeled data.METHODS:A multi-SFDA method was proposed for DR identification.This method integrates multiple source models,which are trained from the same source domain,to generate synthetic pseudo labels for the unlabeled target domain.Besides,a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances.Validation is performed using three color fundus photograph datasets(APTOS2019,DDR,and EyePACS).RESULTS:The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks.It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains.CONCLUSION:The multi-SFDA method provides an effective approach to overcome the challenges in DR identification.The method not only addresses difficulties in data labeling and privacy issues,but also reduces the need for large amounts of labeled data required by deep learning methods,making it a practical tool for early detection and preservation of vision in diabetic patients.

血清肿瘤标记物在视网膜母细胞瘤诊断中的研究

目的:探讨血清肿瘤标记物神经元特异性烯醇化酶(NSE)、糖蛋白抗原CA153、CA199在视网膜母细胞瘤(RB)患者血清中的分泌水平。方法:选取2017-10/2019-10在深圳市人民医院进行化疗且临床资料完整的RB患儿42例为研究对象,检测首次化疗前空腹静脉血血清中肿瘤标记物NSE、CA153、CA199水平,比较不同性别、不同临床分期、单双眼受累患者血清肿瘤标记物水平的差异。结果:晚期组患儿血清肿瘤标记物NSE、CA153、CA199水平均高于早中期组(49.69±18.45ng/mL vs 36.18±14.92ng/mL,22.38±12.03U/mL vs 15.10±8.32U/mL,46.44±18.76U/mL vs 30.21±24.03U/mL,P<0.05),但不同性别、单双眼受累患儿血清各肿瘤标记物水平均无明显差异(P>0.05)。结论:血清NSE、CA153、CA199在临床晚期RB患者血清中的分泌水平明显高于早中期患者,其对RB分期诊疗可能具有重要意义。

Analysis of the LIF Spectroscopy of Nickel Hydride in 19000-21400 cm^-1

The laser-induced fluorescence （LIF） excitation spectrum of NiH was recorded in the spectral region from 15000 cm^-1 to 21400 cm^-1, with the NiH molecules produced by the reaction of sputtered nickel atoms with methanol under supersonic jet conditions. The 19000-21400 cm^-1 portion of the spectrum of NiH is reported for the first time. Twenty-four bands were observed and classified into seven electronic transitions. Every band was rotationally analyzed. Higher vibrational levels of many excited states, A, B, D, E, F, and G, were observed and the complete set of spectroscopic parameters, vibrational frequency, unharmonic constant, rotational constant, and equilibrium length of these states were obtained. Some bands were reassigned.

F^2∑^＋-X^2∑^＋ Band System of Cobalt Carbide

The laser-induced fluorescence excitation spectrum of CoC was recorded in the spectral region from 13500 cm^-1 to 22000 cm^-1, in which the CoC molecules were produced by the reaction of sputtered cobalt atoms with methanol under supersonic jet cooled conditions. Much of the visible spectrum was assigned to transitions between the X2∑^＋ ground state and F2∑^＋ state. The 11 bands assigned as （v＇=3-13, 0） transitions of the F^2∑^＋-X^2∑^＋ band system were observed and rotationally analyzed. Equilibrium constants for the F^2∑^＋ state were Te=13628 cm^-1, We=669 cm^-1, ωeХe=4.3 cm^-1, Be=0.546 cm^-1, and Re=1.758A. Some new bands were observed.

Multivariate model for predicting semen ：ryopreservation outcomes in a human sperm ban

Semen cryopreservation is widely used in assisted reproductive technologies, but it reduces sperm quality dramatically. The aim of this study was to develop a model using basal semen quality to predict the outcome of postthaw semen parameters and improve the efficiency of cryopreservation in a human sperm bank. Basal semen parameters of 180 samples were evaluated in the first stage, and a multiple logistic regression analysis involving a backward elimination selection procedure was applied to select independent predictors. After a comprehensive analysis of all results, we developed a new model to assess the freezability of sperm. Progressive motility （PR）, straight-line velocity （VSL） and average path velocity （VAP） were included in our model. A greater area under the receiver operating characteristic curve was obtained in our model when compared with other indicators. In the second stage of our study, samples that satisfied the new model were selected to undergo freeze-thawing. Compared with the first stage, the rate of good freezability was increased significantly （94% vs 67%, P = 0.003）. By determining basal semen quality, we have developed a new model to improve the efficiency of cryopreservation in a human sperm bank.