The chemical composition of scaffolds is similar to the extracellular matrix of the target tissue, but sometimes scaffolds cannot meet the special functional requirements for the initial stage of engineering tissue, such as mechanical and optical properties. Bionic scaffolds require certain levels of supramolecular structure, textile structure and liquid crystal structure. Here, we will focus our attention on animal tissues with a similar high-level structure to that of the target organization and we hope to achieve the desired results through new technical means. In this study, we have developed a method to obtain a fish scale lamellar matrix from grass carp scales. The fine structure of the scale matrix has been studied, and it was found that the grass carp scale matrix is a textured structure consisting of multiple collagen sheets, which have a double-twisted spiral structure similar to a liquid crystal, thus correcting the literature reports of a single twisted spiral structure. Interestingly, this structure has many similarities with the cornea, cementum and tibial matrix. At the same time, the correlation between the etching time and the optical properties of the scaffold was also studied, and the scale matrix can reach light transmission and refraction levels similar to those of the corneal stroma. Moreover, the matrix has good mechanical properties, in vitro anti-enzymatic abilities and compatibility with human corneal epithelial cells. Therefore, this kind of scaffold material and preparation method, with a lamellar structure and special physical parameters, may provide new hope for corneal prosthesis.

Along with the increasing knowledge of long noncoding RNA, the interaction between the long noncoding RNA (lncRNA) and tumor immune infiltration is increasingly valued. However, there is a lack of understanding of correlation between regulation of specific lncRNAs and tumor-infiltrating macrophages within melanoma. In this research, a macrophage associated lncRNA signature was identified by multiple machine learning algorithms and the robust and effectiveness of signature also validated in other independent datasets. The signature contained six specific lncRNAs (PART1, LINC00968, LINC00954, LINC00944, LINC00518 and C20orf197) was constructed, which could diagnose melanoma and predict the prognosis of patients. Moreover, our signature achieves higher accuracy than the previous well-established markers and regarded as an independent prognostic indicator. The pathway enrichment revealed that these lncRNAs were closely correlated with many immune processes. In addition, the signature was associated with different immune microenvironment and applied to predict response of immune checkpoint inhibitor therapy (low risk of patients well respond to anti-PD-1 therapy and high risk is insensitive to anti-CTLA-4 therapy). Therefore, our finding supplies a more accuracy and effective lncRNA signature for tumor-infiltrating macrophages targeting treatment approaches and affords a new clinical application for predicting the response of immunotherapies in melanomas.

Background: Deep learning has been extensively used in digital histopathology. The purpose of this study was to test deep learning (DL) algorithms for predicting the vital status of whole-slide image (WSI) of uveal melanoma (UM). Methods: We developed a deep learning model (Google-net) to predict the vital status of UM patients from histopathological images in TCGA-UVM cohort and validated it in an internal cohort. The histopathological DL features extracted from the model and then were applied to classify UM patients into two subtypes. The differences between two subtypes in clinical outcomes, tumor mutation, and microenvironment, and probability of drug therapeutic response were investigated further. Results: We observed that the developed DL model can achieve a high accuracy of > = 90% for patches and WSIs prediction. Using 14 histopathological DL features, we successfully classified UM patients into Cluster1 and Cluster2 subtypes. Compared to Cluster2, patients in the Cluster1 subtype have a poor survival outcome, increased expression levels of immune-checkpoint genes, higher immune-infiltration of CD8 + T cell and CD4 + T cells, and more sensitivity to anti-PD-1 therapy. Besides, we established and verified prognostic histopathological DL-signature and gene-signature which outperformed the traditional clinical features. Finally, a well-performed nomogram combining the DL-signature and gene-signature was constructed to predict the mortality of UM patients. Conclusions: Our findings suggest that DL model can accurately predict vital status in UM patents just using histopathological images. We found out two subgroups based on histopathological DL features, which may in favor of immunotherapy and chemotherapy. Finally, a well-performing nomogram that combines DL-signature and gene-signature was constructed to give a more straightforward and reliable prognosis for UM patients in treatment and management.

Introduction Deep learning (DL) has been widely used to estimate clinical images. The objective of this project was to create DL models to predict the early postoperative visual acuity after small-incision lenticule extraction (SMILE) surgery. Methods We enrolled three independent patient cohorts (a retrospective cohort and two prospective SMILE cohorts) who underwent the SMILE refractive correction procedure at two different refractive surgery centers from July to September 2022. The medical records and surgical videos were collected for further analysis. Based on the uncorrected visual acuity (UCVA) at 24 h postsurgery, the eyes were divided into two groups: those showing good recovery and those showing poor recovery. We then trained a DL model (Resnet50) to predict eyes with early postoperative visual acuity of patients in the retrospective cohort who had undergone SMILE surgery from surgical videos and subsequently validated the model’s performance in the two prospective cohorts. Finally, Gradient-weighted Class Activation Mapping (Grad-CAM) was performed for interpretation of the model. Results Among the 318 eyes (159 patients) enrolled in the study, 10,176 good quality femtosecond laser scanning images were obtained from the surgical videos. We observed that the developed DL model achieved a high accuracy of 96% for image prediction. The area under the curve (AUC) value of the DL model in the retrospective cohort was 0.962 and 0.998 in the training and validation datasets, respectively. The AUC values in two prospective cohorts were 0.959 and 0.936. At the video level, the trained machine learning (ML) model (XGBoost) also accurately distinguished patients with good or poor recovery. The AUC value of the ML model was 0.998 and 0.889 in the retrospective cohort (training and test datasets, respectively) and 1.000 and 0.984 in the two prospective cohorts. We also trained a DL model which can accurately distinguish suction loss (100%), black spots (85%), and opaque bubble layer (96%). The Grad-CAM heatmap indicated that our models can recognize the area of scanning and precisely identify intraoperative complications. Conclusions Our findings suggest that artificial intelligence (DL and ML model) can accurately predict the early postoperative visual acuity and intraoperative complications after SMILE surgery just using surgical videos or images, which may display a great importance for artificial intelligence in application of refractive surgeries.