RESUMO
Acute paediatric leukaemia is diagnosed and monitored via bone marrow aspirate assessment of blasts as a measure of minimal residual disease. Liquid biopsies in the form of blood samples could greatly reduce the need for invasive bone marrow aspirations, but there are currently no blood markers that match the sensitivity of bone marrow diagnostics. Circulating extracellular vesicles (EVs) represent candidate biomarkers that may reflect the blast burden in bone marrow, and several studies have reported on the utility of EVs as biomarkers for adult haematological malignancies. Increased levels of EVs have been reported for several haematological malignancies, and we similarly report here elevated EV concentrations in plasma from paediatric BCP-ALL patients. Plasma EVs are very heterogeneous in terms of their cellular origin, thus identifying a cancer selective EV-marker is challenging. Here, we undertook a reductionistic approach to identify protein markers selectively associated to plasma EVs derived from BCP-ALL patients. The EV proteome of primary BCP-ALL cell-derived EVs were compared against EVs from healthy donor B cells and the BCP-ALL cell line REH, and further against EVs isolated from plasma of healthy paediatric donors and paediatric BCP-ALL patients. With this approach, we identified a signature of 6 proteins (CD317, CD38, IGF2BP1, PCNA, CSDE1, and GPR116) that were specifically identified in BCP-ALL derived EVs only and not in healthy control EVs, and that could be exploited as diagnostic biomarkers.
Assuntos
Vesículas Extracelulares , Neoplasias Hematológicas , Leucemia-Linfoma Linfoblástico de Células Precursoras , Adulto , Humanos , Criança , Linfócitos B , Biomarcadores , Leucemia-Linfoma Linfoblástico de Células Precursoras/diagnóstico , Proteínas de Ligação a DNA , Proteínas de Ligação a RNARESUMO
Defect inspection of existing buildings is receiving increasing attention for digitalization transfer in the construction industry. The development of drone technology and artificial intelligence has provided powerful tools for defect inspection of buildings. However, integrating defect inspection information detected from UAV images into semantically rich building information modeling (BIM) is still challenging work due to the low defect detection accuracy and the coordinate difference between UAV images and BIM models. In this paper, a deep learning-based method coupled with transfer learning is used to detect defects accurately; and a texture mapping-based defect parameter extraction method is proposed to achieve the mapping from the image U-V coordinate system to the BIM project coordinate system. The defects are projected onto the surface of the BIM model to enrich a surface defect-extended BIM (SDE-BIM). The proposed method was validated in a defect information modeling experiment involving the No. 36 teaching building of Nantong University. The results demonstrate that the methods are widely applicable to various building inspection tasks.
RESUMO
Textbook question answering (TQA) task aims to infer answers for given questions from a multimodal context, including text and diagrams. The existing studies have aggregated intramodal semantics extracted from a single modality but have yet to capture the intermodal semantics between different modalities. A major challenge in learning intermodal semantics is maintaining lossless intramodal semantics while bridging the gap of semantics caused by heterogeneity. In this article, we propose an intermodal relation-aware heterogeneous graph network (IMR-HGN) to extract the intermodal semantics for TQA, which aggregates different modalities while learning features rather than representing them independently. First, we design a multidomain consistent representation (MDCR) to eliminate semantic gaps by capturing intermodal features while maintaining lossless intramodal semantics in multidomains. Furthermore, we present neighbor-based relation inpainting (NRI) to reduce semantic ambiguity via repairing fuzzy relations with correlations of relations. Finally, we propose hierarchical multisemantics aggregation (HMSA) to guarantee the completeness of semantics by aggregating features of nodes and relations with a reconstruction network (RN). Experimental results show that IMR-HGN could extract the intermodal semantics of answers, achieving a 2.16% improvement on the validation set of the TQA dataset and a 3.04% increase on the test set of the AI2D dataset.