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.

基于注意力机制和Pix2Pix网络的术后角膜地形图生成

目的:探索使用注意力机制和Pix2Pix生成对抗网络预测年龄相关性白内障患者术中行飞秒激光弧形角膜切开术后角膜地形图。方法:回顾性病例系列研究。选取2018-03/2020-03山西省眼科医院年龄相关性白内障患者术中行飞秒激光弧形角膜切开术患者87例105眼。收集患者术前及术后角膜地形图210张分为训练集(180张)、测试集(30张)用于模型训练和测试。采用峰值信噪比(PSNR)、结构相似性(SSIM)、Alpins散光矢量分析,比较不同注意力机制下术后角膜地形图预测结果的准确性。结果:基于注意力机制和Pix2Pix网络可以预测术后角膜地形图,其中基于Self-Attention注意力机制的模型预测效果最好,PSNR和SSIM达到了16.048、0.7661。真实的和生成的角膜地形图在3mm和5mm环上的误差矢量,误差矢量轴位,术源性散光和矫正比比较差异均无统计学意义(均P>0.05)。结论:基于Self-Attention注意力机制和Pix2Pix网络可以对术后角膜地形图做到良好的预测,可以为眼科临床医生的手术规划和术后效果提供参考。

Hydroxyl-terminated Polyethylenes Bearing Functional Side Groups:Facile Synthesis and Their Properties

A series of hydroxyl-terminated polyethylenes(HTPE)bearing various functional side groups(e.g.carboxyl,ester and butane groups)were synthesized by the combination of ring opening metathesis polymerization(ROMP)and visible light photocatalytic thiol-ene reaction.The products are named as a,w-dihydroxyl-polyllpropionyloxythio)methinetrimethylene](HTPECarboxy),a,w dihydroxy-poly(methylpropionatethio)methinetrimethylene](HTPEeser)and a,wdihydroxyl-poly[(butylthio)methinetrimethylene](HTPEbutane)respectively.The investigation of ROMP indicated that the molecular weight of resultant hydroxy-terminated polybutadiene(HTPB)can be tailored by varying the feed ratios of monomer to chain transfer agent(CTA).The exploration of the photocatalytic thiol-ene reaction between HTPB precursor and methyl-3-mercaptopropionate revealed that blue light as well as oxygen accelerated the reaction.1H-NMR and 13C-NMR results verified all the double bonds in HTPB can be modified,and the main chain of resultant polymer can be considered as polyethylene.Subsequently,relationship between the structure of side groups and the thermal properties of functional PEs was studied.And the results suggested that the Tg was in the order of HTPEbuane<HTPEester<HTPEarboxy+.Greater interaction between side groups resulted in higher Tg.Moreover,all the functional PE samples exhibited poor thermostability as compared to HTPB.Finally,the promising applications for functional PEs were explored.HTPEcarboxy1 can be utilized as a smart material with pH-responsive properties due to its pH-dependent ionization of carboxyl side groups.HTPEbutane can be employed as a macro-initiator for building the triblock copolymer due to the presence of active hydroxyl end groups.HTPEester can serve as a plasticizer for PVC which can enhance the ductilityt of PVC without obviously sacrificing strength.

MCSTransWnet:A new deep learning process for postoperative corneal topography prediction based on raw multimodal data from the Pentacam HR system

This work provides a new multimodal fusion generative adversarial net(GAN)model,Multiple Conditions Transform W-net(MCSTransWnet),which primarily uses femtosecond laser arcuate keratotomy surgical parameters and preoperative corneal topography to predict postoperative corneal topography in astigmatism-corrected patients.The MCSTransWnet model comprises a generator and a discriminator,and the generator is composed of two sub-generators.The first sub-generator extracts features using the U-net model,vision transform(ViT)and a multi-parameter conditional module branch.​The second sub-generator uses a U-net network for further image denoising.The discriminator uses the pixel discriminator in Pix2Pix.Currently,most GAN models are convolutional neural networks;however,due to their feature extraction locality,it is difficult to comprehend the relationships among global features.Thus,we added a vision Transform network as the model branch to extract the global features.It is normally difficult to train the transformer,and image noise and geometric information loss are likely.Hence,we adopted the standard U-net fusion scheme and transform network as the generator,so that global features,local features,and rich image details could be obtained simultaneously.Our experimental results clearly demonstrate that MCSTransWnet successfully predicts postoperative corneal topographies(structural similarity​=​0.765,peak signal-to-noise ratio​=​16.012,and Fréchet inception distance​=​9.264).Using this technique to obtain the rough shape of the postoperative corneal topography in advance gives clinicians more references and guides changes to surgical planning and improves the success rate of surgery.