Yuehan Zhou

Background: Precise retinal vessel segmentation is crucial for the diagnosis of ocular diseases. This meticulous process can promptly capture retinal vessel abnormalities, which in turn can facilitate early diagnosis and timely treatment. However, retinal vessels exhibit complex branching patterns with different diameters and contrasts, making it difficult to segment tiny vessels and low-contrast areas, and identify subtle terminal branches. This study aimed to improve the accuracy of retinal vessel segmentation and ultimately improve the efficiency of clinical diagnosis. Methods: In this study, we proposed the Multi-modal Attention Deformable U-shaped Network (MA-DUNet) to enhance retinal vessel segmentation performance. This model was designed to enhance segmentation accuracy through three key strategies. First, it incorporates atrous multi-scale (AMS) convolutions in the encoding stage to enhance the perception of information across different scales, thereby improving the extraction and representation of image features. Second, a gated channel transformation (GCT) attention mechanism is introduced between the encoder and decoder to improve feature transmission and extract crucial information. This mechanism dynamically adjusts the relationships among feature channels, emphasizing important task-related features while suppressing irrelevant ones. Third, a Multi-Modal Attention Fusion Block (MAFB), which combines the Multi-Modal Fusion Block (MFB) and GCT attention mechanism, is used during the decoding process to optimize information usage and enhance segmentation performance. Results: Images from three public datasets [i.e., digital retinal images for vessel extraction (DRIVE), structured analysis of the retina (STARE), and Child Heart and Health Study in England Database 1 (CHASE-DB1)] were analyzed. In terms of blood vessel segmentation, the model had accuracy values of 95.72%, 96.68%, and 96.38%, and area under the receiver operating characteristic (ROC) curve values of 98.10%, 98.89%, and 98.35% for the three datasets, respectively. Additionally, when validated using data from hospital collaborations, our model outperformed other comparative models in terms of the segmentation results. Conclusions: Our proposed MA-DUNet model provides more accurate segmentation of the fine terminal branches of vessels, effectively eliminating blurred boundaries and fragmentation in the segmentation outcomes, resulting in clearer vascular segmentation results.

Pharmacy Intravenous Admixture Services (PIVAS) are places dedicated to the centralized dispensing of intravenous drugs, usually managed and operated by professional pharmacists and pharmacy technicians, and are an integral part of modern healthcare. However, the workflow of PIVAS has some problems, such as low efficiency and error-prone. This study aims to improve the efficiency of drug dispensing, reduce the rate of manual misjudgment, and minimize drug errors by conducting an in-depth study of the entire workflow of PIVAS and applying image recognition technology to the drug checking and dispensing process. Firstly, through experimental comparison, a target detection model suitable for drug category recognition is selected in the drug-checking process of PIVAS, and it is improved to improve the recognition accuracy and speed of intravenous drug categories. Secondly, a corner detection model for drug dosage recognition was studied in the drug dispensing stage to further increase drug dispensing accuracy. Then the PIVAS drug category recognition system and PIVAS drug dosage recognition system were designed and implemented.

Acute lymphoblastic leukemia (ALL) is one of the most common malignant tumor types of the circulatory system. Dexamethasone (DEX) acts on the glucocorticoid (GC) receptor (GR) and is a first‑line chemotherapy drug for ALL. However, long‑term or high‑dose applications of the drug can not only cause adverse reactions, such as osteoporosis and high blood pressure, but can also cause downregulation of GR and lead to drug resistance. In the present study, reverse transcription‑quantitative PCR, western blotting and LysoTracker Red staining were used to observe the effects of DEX and andrographolide (AND; a botanical with antitumorigenic properties) combined treatment. It was found that AND enhanced the sensitivity of CEM‑C1 cells, a GC‑resistant cell line, to DEX, and synergistically upregulated GR both at the transcriptional and post‑transcriptional level with DEX. The combination of AND with DEX synergistically alkalized lysosomal lumen and downregulated the expression of autophagy‑related genes Beclin1 and microtubule‑associated 1 protein light chain 3 (LC3), thereby inhibiting autophagy. Knocking down LC3 expression enhanced GR expression, suggesting that GR was regulated by autophagy. Furthermore, compared with the monotherapy group (AND or DEX in isolation), AND interacted with DEX to activate the autophagy‑dependent PI3K/AKT/mTOR signaling pathway by enhancing the phosphorylation of PI3K, AKT and mTOR, thereby decreasing GR degradation and increasing the sensitivity of cells to GCs. In conclusion, the present study demonstrated that AND exhibited a synergistic anti‑ALL effect with DEX via upregulation of GR, which was orchestrated by the autophagy‑related PI3K/AKT/mTOR signaling pathway. The results of the present study therefore provided novel research avenues and strategies for the treatment of ALL.

Breast cancer (BRCA) has an undesirable prognosis and is the second most common cancer among women after lung cancer. A novel mechanism of programmed cell death called cuproptosis is linked to the development and spread of tumor cells. However, the function of cuproptosis in BRCA remains unknown. To this date, no studies have used machine learning methods to screen for characteristic genes to explore the role of cuproptosis-related genes (CRGs) in breast cancer. Therefore, 14 cuproptosis-related characteristic genes (CRCGs) were discovered by the feature selection of 39 differentially expressed CRGs using the three machine learning methods LASSO, SVM-RFE, and random forest. Through the PPI network and immune infiltration analysis, we found that PRNP was the key CRCG. The miRTarBase, TargetScan, and miRDB databases were then used to identify hsa-miR-192-5p and hsa-miR-215-5p as the upstream miRNA of PRNP, and the upstream lncRNA, CARMN, was identified by the StarBase database. Thus, the mRNA PRNP/miRNA hsa-miR-192-5p and hsa-miR-215-5p/lncRNA CARMN ceRNA network was constructed. This ceRNA network, which has not been studied before, is extremely innovative. Furthermore, four cuproptosis-related lncRNAs (CRLs) were screened in TCGA-BRCA by univariate Cox, LASSO, and multivariate Cox regression analysis. The risk model was constructed by using these four CRLs, and the risk score = C9orf163 * (1.8365) + PHC2-AS1 * (−2.2985) + AC087741.1 * (−0.9504) + AL109824.1 * (0.6016). The ROC curve and C-index demonstrated the superior predictive capacity of the risk model, and the ROC curve demonstrated that the AUC of 1-, 3-, and 5-year OS in all samples was 0.721, 0.695, and 0.633, respectively. Finally, 50 prospective sensitive medicines were screened with the pRRophetic R package, among which 17-AAG may be a therapeutic agent for high-risk patients, while the other 49 medicines may be suitable for the treatment of low-risk patients. In conclusion, our study constructs a new ceRNA network and a novel risk model, which offer a theoretical foundation for the treatment of BRCA and will aid in improving the prognosis of BRCA.

Colorectal cancer (CRC) is the most common gastrointestinal tumor with poor prognosis. Ferroptosis is a pivotal form of programmed iron-dependent cell death different from autophagy and apoptosis, and long noncoding RNA (lncRNA) can influence the prognosis of CRC via regulating ferroptosis. To explore the role and prognostic value of the constructed ferroptosis-related lncRNA model in CRC, a prognostic model was constructed and validated by screening ferroptosis-related lncRNAs associated with prognosis based on the transcriptome data and survival data of CRC patients in The Cancer Genome Atlas database. Regarding the established prognostic models, differences in signaling pathways and immune infiltration, as well as differences in immune function, immune checkpoints, and N6-methyladenosine-related genes were also analyzed. A total of 6 prognostic ferroptosis-related lncRNAs were obtained, including AP003555.1, AC010973.2, LINC01857, AP001469.3, ITGB1-DT and AC129492.1. Univariate independent prognostic analysis, multivariate independent prognostic analysis and receiver operating characteristic curves showed that ferroptosis-related lncRNAs could be recognized as independent prognostic factors. The Kaplan–Meier survival curves and the risk curves showed that the survival time of the high-risk group was shorter. Gene set enrichment analysis enrichment analysis showed that ATP-binding cassette transporters, taste transduction and VEGF signaling pathway were more active in high-risk groups that than in low-risk groups. However, the citrate cycle tricarboxylic acid cycle, fatty acid metabolism and peroxisome were significantly more active in the low-risk group than in the high-risk group. In addition, there were also differences in immune infiltration in the high-low-risk groups based on different methods, including antigen-presenting cell co-stimulation, chemokine receptor, parainflammation, and Type II IFN Response. Further analysis of Immune checkpoints showed that most of the Immune checkpoints such as TNFRSF18, LGALS9 and CTLA4 in the high-risk group were significantly higher than those in the low-risk group, and the expressions of N6-methyladenosine related genes METTL3, YTHDH2 and YTHDC1 were also significantly different in the high-risk group. Ferroptosis-related lncRNAs are closely related to the survival of colorectal cancer patients, which can be used as new biomarkers and potential therapeutic targets for the prognosis of colorectal cancer.

Colorectal cancer (CRC) is the most common gastrointestinal tumor with poor prognosis. Ferroptosis is a pivotal form of programmed iron-dependent cell death different from autophagy and apoptosis, and long non-coding RNA (lncRNA) can influence the prognosis of CRC via regulating ferroptosis. Nowadays, artificial intelligence (AI) driven solutions, especially machine learning (ML) methodologies, are becoming effective tools in increasing the likelihood of the development of new prognostic and predictive biomarkers of diseases. In this study, with ML-associated tools, a prognostic model was constructed and validated by screening ferroptosis-related lncRNAs associated with prognosis based on the transcriptome data and survival data of CRC patients in TCGA database. Regarding the established prognostic models, differences in signaling pathways and immune infiltration, as well as differences in immune function, immune checkpoints, and m6A-related genes were also analyzed. We obtained a total of 6 ferroptosis-related lncRNAs, and found that the prognostic model could accurately predict the prognosis of CRC patients. Significant differences were found in multiple signaling pathways, as well as immune infiltration, immune function, immune checkpoints, and m6A-related genes between high and low risk groups. Our study provides an efficient prediction tool for CRC patients and contributes to guide the personalized treatment.

Glioblastoma is the most common malignancy of the central nervous system, and patients typically have a poor prognosis. Previous studies indicate a gender bias in the development of glioblastoma; women are at a lower risk compared with men, suggesting that estrogen may confer protective effects. Icaritin, a prenylflavonoid derivative from a Chinese herb of the Epimedium genus, selectively regulates the estrogen receptor (ER) and possesses anti‑cancer properties. The aim of the present study was to investigate the protective effects of icaritin on glioblastoma and its underlying mechanisms, with a particular focus on its association with the ER. The results demonstrated that icaritin inhibited the growth of C6 and U87‑MG glioblastoma cells in a dose‑ and time‑dependent manner. At a concentration of 12.5 µM, icaritin induced apoptosis, which was characterized by the increased expression of the cleaved forms of caspases 3, 7, 8 and 9 and poly (ADP‑ribose) polymerase, downregulation of BCL2 apoptosis regulator and upregulation of BCL2‑associated X, apoptosis regulator expression. Additionally, icaritin inhibited the migration of C6 and U87‑MG cells. The protein expression levels of matrix metalloproteinase (MMP)‑2 and MMP‑9 were also downregulated following icaritin treatment. Furthermore, icaritin treatment increased the expression of estrogen receptor (ER)β and the phosphatase and tensin (PTEN) homolog oncoprotein, thus reducing the expression of downstream targets of PTEN; protein kinase B (Akt) and phosphorylated Akt. Subsequent experiments demonstrated that icaritin cooperates with 17β‑estradiol to inhibit the growth of glioblastoma cells, and the inhibition of ERβ with the ERβ‑specific antagonist ICI 182,780, attenuated the anti‑glioblastoma effects of icaritin. In conclusion, the results of the present study demonstrate that the anti‑glioblastoma effects of icaritin may be mediated by its modulation of ERβ.