Search for: All records

Abstract Percutaneous nephrostomy is widely used in kidney access surgeries. Despite its prevalence in urological interventions, it presents two operational challenges: 1) precise needle placement into the renal pelvis; and 2) avoiding hemorrhage from blood vessel rupture. In this study, we developed an endoscopic optical coherence tomography probe for needle navigation. We conducted experiments on thirty-one human kidneys for two aspects: 1) tissue recognition, and 2) blood vessel detection. Experimental results indicated that renal tissues including cortex, medulla, calyx, sinus fat, and pelvis could be effectively distinguished through structural optical coherence tomography imaging, and renal blood flow could be detected through the Doppler function. Deep learning methods were utilized to automate recognition procedures. For tissue classification, an Inception model was used, achieving a recognition accuracy of 99.6%. For blood vessel detection, an nnU-net model was applied, exhibiting an intersection over union value of 0.8917 for blood vessel and 0.9916 for background. 

Bladder cancer (BCa) is the second most common cancer of the genitourinary tract globally. It has limited treatment options, high recurrence rate, and acquires resistance to platinum-based therapy. Therefore, identifying novel therapeutic targets is urgently needed. Analysis of the TCGA data revealed that the enzyme galactokinase-1 (GALK1) is overexpressed (p < 0.0001) in bladder tumors compared to normal tissue. Our data also confirmed GALK1 protein upregulation in multiple human BCa cell lines and rodent bladder tumors. However, the precise role of GALK1 in BCa progression and effects of its specific inhibitor remain unexamined. In this study, we demonstrate that GALK1 gene silencing using shRNA resulted in a significant reduction in BCa cell proliferation, migration, and invasion. Pharmacological inhibition of GALK1 using small molecule Cpd36 resulted in anticancer efficacy against BCa. Cpd36 inhibited proliferation, migration, and invasion of BCa cells. Further, Cpd36 induced G1 phase cell cycle arrest, apoptosis, mitochondrial membrane depolarization, and ROS production in the BCa cells. Mechanistically, Cpd36-induced reduction in cell proliferation was associated with a decrease in expression of GALK1, PCNA proteins. Inhibition of metastatic potential was accompanied by decreased migration, invasion, and MMP-9 expression. Cell cycle arrest was associated with decrease in Cyclin D1 and increased expression of p21 and p27. Induction of apoptosis was linked with increased expression of cleaved caspase-3 and cleaved PARP, while downregulating p-AKT. Additionally, Cpd36 in combination with cisplatin or gemcitabine showed a strong synergistic effect on BCa cells. Taken together, our findings suggest that GALK1 plays a significant role in BCa cell survival and validates its inhibitors as promising therapeutic options for managing this disease. 

Smoke detection is a practical approach for early identification of wildfires and mitigating hazards that affect ecosystems, infrastructure, property, and the community. The existing deep learning (DL) object detection methods (e.g., Detection Transformer (DETR)) have demonstrated significant potential for early awareness of these events. However, their precision is influenced by the low visual salience of smoke and the reliability of the annotation, and collecting real-world and reliable datasets with precise annotations is a labor-intensive and time-consuming process. To address this challenge, we propose a weakly supervised Transformer-based approach with a teacher–student architecture designed explicitly for smoke detection while reducing the need for extensive labeling efforts. In the proposed approach, an expert model serves as the teacher, guiding the student model to learn from a variety of data annotations, including bounding boxes, point labels, and unlabeled images. This adaptability reduces the dependency on exhaustive manual annotation. The proposed approach integrates a Deformable-DETR backbone with a modified loss function to enhance the detection pipeline by improving spatial reasoning, supporting multi-scale feature learning, and facilitating a deeper understanding of the global context. The experimental results demonstrate performance comparable to, and in some cases exceeding, that of fully supervised models, including DETR and YOLOv8. Moreover, this study expands the existing datasets to offer a more comprehensive resource for the research community.