A weak edge estimation based multi-task neural network for OCT segmentation.

Optical Coherence Tomography (OCT) offers high-resolution images of the eye's fundus. This enables thorough analysis of retinal health by doctors, providing a solid basis for diagnosis and treatment. With the development of deep learning, deep learning-based methods are becoming more popular for fundus OCT image segmentation.

Bola-Amphiphilic Dendrimer Enhances Imatinib to Target Metastatic Ovarian Cancer via β-Catenin-HRP2 Signaling Axis.

Ovarian cancer is the leading cause of death among all gynecological malignancies, and drug resistance renders the current chemotherapy agents ineffective for patients with advanced metastatic tumors. We report an effective treatment strategy for targeting metastatic ovarian cancer involving a nanoformulation (Bola/IM)─bola-amphiphilic dendrimer (Bola)-encapsulated imatinib (IM)─to target the critical mediator of ovarian cancer stem cells (CSCs) CD117 (c-Kit). Bola/IM offered significantly more effective targeting of CSCs compared to IM alone, through a novel and tumor-specific β-catenin/HRP2 axis, allowing potent inhibition of cancer cell survival, stemness, and metastasis in metastatic and drug-resistant ovarian cancer cells.

Towards effective functionalization of nanopores/nanochannels: the role of amidation reactions.

In recent years, researchers have drawn inspiration from natural ion channels to develop various artificial nanopores/nanochannels, including solid-state and biological. Through imitating the precise selectivity and single molecule sensing exhibited by natural ion channels, nanopores/nanochannels have been widely used in many fields, such as analyte detection, gene sequencing and so on. In these applications, the surface functionalization of nanopores/nanochannels directly determines the effectiveness in quantitative analysis and single molecule detection.

OrchidBase 6.0: increasing the number of Cymbidium (Orchidaceae) genomes and new bioinformatic tools for orchid genome analysis.

Background: Orchids are well-known for their rich diversity of species as well as wide range habitats. Their floral structures are so unique in angiosperms that many of orchids are economically and culturally important in human society. Orchids pollination strategy and evolutionary trajectory are also fantastic human for centuries.

A robust and interpretable ensemble machine learning model for predicting healthcare insurance fraud.

Healthcare insurance fraud imposes a significant financial burden on healthcare systems worldwide, with annual losses reaching billions of dollars. This study aims to improve fraud detection accuracy using machine learning techniques. Our approach consists of three key stages: data preprocessing, model training and integration, and result analysis with feature interpretation.