Northwest Minzu University

Metastatic lesion segmentation is a crucial task for diagnosis and follow-up assessments of patients with malignancies.Recent advances in Convolutional Neural Networks have introduced promising approaches for bone metastasis lesion segmentation.While previous efforts have focused on enhancing the performance of U-Net-based models, challenges persist regarding clin. interpretability and lesion sensitivity.In this paper, we propose a novel bone scintigraphy segmentation model, BSci-Seg, designed to address these challenges by leveraging domain-specific patterns and improving both performance and interpretability.BSci-Seg is built upon a classical encoder-decoder architecture and incorporates a paired dual-sampling scheme (PDSS), multiple receptive-field attention (MRFA), and a customized loss function.The network employs PDSS to relevant layers during both encoding and decoding, and utilizes MRFA modules in the feature encoding stage to enhance differential representation across regions.Exptl. evaluations on 286 SPECT bone scintigrams show significant improvements, with a 4.53 % increase in Dice Similarity Coefficient (DSC) and a 9.90 % increase in Recall.Addnl., comparisons with existing models for bone metastasis lesion segmentation demonstrate the superior performance of BSci-Seg.Comprehensive ablation studies and detailed case analyses further validate the effectiveness of the model, laying the groundwork for further research.

Chemotherapy for patients with pancreatic cancer typically has a poor prognosis. Immunotherapy is currently a hot therapeutical approach to treat tumors. Various studies have shown that natural products have numerous activities, especially in the anti-tumor field. The triterpenoid class compound Obacunone has been shown to have various bioactivities, including anti-cancer properties. In this study, combining Obacunone with anti-PD-1 to treat pancreatic cancer in mice enhanced the anti-cancer activity of anti-PD-1 and suppressed tumor growth significantly. Proteomic analysis, immunofluorescence, Western blot, and flow cytometry revealed that this combination of compounds modulated the CD36-mediated PPAR signaling pathway to improve the infiltration and number of immune-associated CD4⁺ and CD8⁺ T cells in tumors. This report provides a new strategy for discovering immunotherapy for pancreatic cancer.