Application of artificial intelligence for automatic cataract staging based on anterior segment images: comparing automatic segmentation approaches to manual segmentation.

Purpose: Cataract is one of the leading causes of blindness worldwide, accounting for >50% of cases of blindness in low- and middle-income countries. In this study, two artificial intelligence (AI) diagnosis platforms are proposed for cortical cataract staging to achieve a precise diagnosis. Methods: A total of 647 high quality anterior segment images, which included the four stages of cataracts, were collected into the dataset. They were divided randomly into a training set and a test set using a stratified random-allocation technique at a ratio of 8:2. Then, after automatic or manual segmentation of the lens area of the cataract, the deep transform-learning (DTL) features extraction, PCA dimensionality reduction, multi-features fusion, fusion features selection, and classification models establishment, the automatic and manual segmentation DTL platforms were developed. Finally, the accuracy, confusion matrix, and area under the receiver operating characteristic (ROC) curve (AUC) were used to evaluate the performance of the two platforms. Results: In the automatic segmentation DTL platform, the accuracy of the model in the training and test sets was 94.59 and 84.50%, respectively. In the manual segmentation DTL platform, the accuracy of the model in the training and test sets was 97.48 and 90.00%, respectively. In the test set, the micro and macro average AUCs of the two platforms reached >95% and the AUC for each classification was >90%. The results of a confusion matrix showed that all stages, except for mature, had a high recognition rate. Conclusion: Two AI diagnosis platforms were proposed for cortical cataract staging. The resulting automatic segmentation platform can stage cataracts more quickly, whereas the resulting manual segmentation platform can stage cataracts more accurately.

Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images.

Purpose: A common ocular manifestation, macular edema (ME) is the primary cause of visual deterioration. In this study, an artificial intelligence method based on multi-feature fusion was introduced to enable automatic ME classification on spectral-domain optical coherence tomography (SD-OCT) images, to provide a convenient method of clinical diagnosis. Methods: First, 1,213 two-dimensional (2D) cross-sectional OCT images of ME were collected from the Jiangxi Provincial People's Hospital between 2016 and 2021. According to OCT reports of senior ophthalmologists, there were 300 images with diabetic (DME), 303 images with age-related macular degeneration (AMD), 304 images with retinal-vein occlusion (RVO), and 306 images with central serous chorioretinopathy (CSC). Then, traditional omics features of the images were extracted based on the first-order statistics, shape, size, and texture. After extraction by the alexnet, inception_v3, resnet34, and vgg13 models and selected by dimensionality reduction using principal components analysis (PCA), the deep-learning features were fused. Next, the gradient-weighted class-activation map (Grad-CAM) was used to visualize the-deep-learning process. Finally, the fusion features set, which was fused from the traditional omics features and the deep-fusion features, was used to establish the final classification models. The performance of the final models was evaluated by accuracy, confusion matrix, and the receiver operating characteristic (ROC) curve. Results: Compared with other classification models, the performance of the support vector machine (SVM) model was best, with an accuracy of 93.8%. The area under curves AUC of micro- and macro-averages were 99%, and the AUC of the AMD, DME, RVO, and CSC groups were 100, 99, 98, and 100%, respectively. Conclusion: The artificial intelligence model in this study could be used to classify DME, AME, RVO, and CSC accurately from SD-OCT images.

Altered synchronous neural activities in retinal vein occlusion patients: A resting-state fMRI study.

Objective: Retinal vein occlusion (RVO) is the second most common retinal vascular disorder after diabetic retinopathy, which is the main cause of vision loss. Retinal vein occlusion might lead to macular edema, causing severe vision loss. Previous neuroimaging studies of patients with RVO demonstrated that RVO was accompanied by cerebral changes, and was related to stroke. The purpose of the study is to investigate synchronous neural activity changes in patients with RVO. Methods: A total of 50 patients with RVO and 48 healthy subjects with matched sex, age, and education were enrolled in the study. The ReHo method was applied to investigate synchronous neural activity changes in patients with RVO. Results: Compared with HC, patients with RVO showed increased ReHo values in the bilateral cerebellum_4_5. On the contrary, patients with RVO had decreased ReHo values in the bilateral middle occipital gyrus, right cerebelum_crus1, and right inferior temporal gyrus. Conclusion: Our study demonstrated that patients with RVO were associated with abnormal synchronous neural activities in the cerebellum, middle occipital gyrus, and inferior temporal gyrus. These findings shed new insight into neural mechanisms of vision loss in patients with RVO.

Application of artificial intelligence models for detecting the pterygium that requires surgical treatment based on anterior segment images.

Background and aim: A pterygium is a common ocular surface disease, which not only affects facial appearance but can also grow into the tissue layer, causing astigmatism and vision loss. In this study, an artificial intelligence model was developed for detecting the pterygium that requires surgical treatment. The model was designed using ensemble deep learning (DL). Methods: A total of 172 anterior segment images of pterygia were obtained from the Jiangxi Provincial People's Hospital (China) between 2017 and 2022. They were divided by a senior ophthalmologist into the non-surgery group and the surgery group. An artificial intelligence model was then developed based on ensemble DL, which was integrated with four benchmark models: the Resnet18, Alexnet, Googlenet, and Vgg11 model, for detecting the pterygium that requires surgical treatment, and Grad-CAM was used to visualize the DL process. Finally, the performance of the ensemble DL model was compared with the classical Resnet18 model, Alexnet model, Googlenet model, and Vgg11 model. Results: The accuracy and area under the curve (AUC) of the ensemble DL model was higher than all of the other models. In the training set, the accuracy and AUC of the ensemble model was 94.20% and 0.978, respectively. In the testing set, the accuracy and AUC of the ensemble model was 94.12% and 0.980, respectively. Conclusion: This study indicates that this ensemble DL model, coupled with the anterior segment images in our study, might be an automated and cost-saving alternative for detection of the pterygia that require surgery.

Impact of thymosin α1 as an immunomodulatory therapy on long-term survival of non-small cell lung cancer patients after R0 resection: a propensity score-matched analysis.

BACKGROUND: There is limited information about thymosin α1 (Tα1) as adjuvant immunomodulatory therapy, either used alone or combined with other treatments, in patients with non-small cell lung cancer (NSCLC). This study aimed to evaluate the effect of adjuvant Tα1 treatment on long-term survival in margin-free (R0)-resected stage IA-IIIA NSCLC patients. METHODS: A total of 5746 patients with pathologic stage IA-IIIA NSCLC who underwent R0 resection were included. The patients were divided into the Tα1 group and the control group according to whether they received Tα1 or not. A propensity score matching (PSM) analysis was performed to reduce bias, resulting in 1027 pairs of patients. RESULTS: After PSM, the baseline clinicopathological characteristics were similar between the two groups. The 5-year disease-free survival (DFS) and overall survival (OS) rates were significantly higher in the Tα1 group compared with the control group. The multivariable analysis showed that Tα1 treatment was independently associated with an improved prognosis. A longer duration of Tα1 treatment was associated with improved OS and DFS. The subgroup analyses showed that Tα1 therapy could improve the DFS and/or OS in all subgroups of age, sex, Charlson Comorbidity Index (CCI), smoking status, and pathological tumor-node-metastasis (TNM) stage, especially for patients with non-squamous cell NSCLC and without targeted therapy. CONCLUSION: Tα1 as adjuvant immunomodulatory therapy can significantly improve DFS and OS in patients with NSCLC after R0 resection, except for patients with squamous cell carcinoma and those receiving targeted therapy. The duration of Tα1 treatment is recommended to be >24 months.

Donor-acceptor type blends composed of black phosphorus and C60 for solid-state optical limiters.

Novel donor-acceptor blends composed of black phosphorus (BP) as an electron donor and C60 as an electron acceptor have been prepared and successfully embedded into a non-optically active poly(methylmethacrylate) (PMMA) matrix producing a BP:C60/PMMA film. In contrast to C60, BP and non-annealed BP:C60 blends, annealed BP:C60 blends show a significantly enhanced optical limiting response due to the thermal-induced intermolecular charge transfer effect between BP and C60.

Optimization on Extraction Technology of Polysaccharide from Rhizoma Coptidis by Box-Behnken Design-Response Surface Methodology / 世界科学技术-中医药现代化

This study was aimed to optimize the extraction conditions of polysaccharides from Rhizoma Coptidis.With the R.Coptidis of extraction yield,polysaccharide yield and uronic acid yield as evaluation indexes,the impact of extraction temperature,extraction times,extraction duration and liquid-to-solid ratio on the process of R.Coptidis polysaccharides reflux extraction were investigated by the Box-Behnken design-response surface methodology.The results showed that the optimal extraction conditions were achieved and listed as follows:extraction temperature at 100℃,extracted 3 times with 3.8 h per each time,liquid-to-solid ratio of 1:15.7.It was concluded that the Box-Behnken design-response surface methodology was accurate,rational and feasible to optimize the extraction method of polysaccharides fromR.Coptidis.