ABSTRACT
PURPOSE: Decision support systems and context-aware assistance in the operating room have emerged as the key clinical applications supporting surgeons in their daily work and are generally based on single modalities. The model- and knowledge-based integration of multimodal data as a basis for decision support systems that can dynamically adapt to the surgical workflow has not yet been established. Therefore, we propose a knowledge-enhanced method for fusing multimodal data for anticipation tasks. METHODS: We developed a holistic, multimodal graph-based approach combining imaging and non-imaging information in a knowledge graph representing the intraoperative scene of a surgery. Node and edge features of the knowledge graph are extracted from suitable data sources in the operating room using machine learning. A spatiotemporal graph neural network architecture subsequently allows for interpretation of relational and temporal patterns within the knowledge graph. We apply our approach to the downstream task of instrument anticipation while presenting a suitable modeling and evaluation strategy for this task. RESULTS: Our approach achieves an F1 score of 66.86% in terms of instrument anticipation, allowing for a seamless surgical workflow and adding a valuable impact for surgical decision support systems. A resting recall of 63.33% indicates the non-prematurity of the anticipations. CONCLUSION: This work shows how multimodal data can be combined with the topological properties of an operating room in a graph-based approach. Our multimodal graph architecture serves as a basis for context-sensitive decision support systems in laparoscopic surgery considering a comprehensive intraoperative operating scene.
ABSTRACT
Homicide, suicide, or accident - elemental intoxication may be a cause in each of these types of deaths. Inductively coupled plasma mass spectrometry (ICP-MS) has emerged as the gold standard analytical method for toxic metal analysis in both clinical and forensic settings. An ICP-MS method was developed using a modified acidic workup for the quantitative determination of arsenic, lead, and thallium. Method validation focused on the assessment of linearity, between- and within-day precisions, limits of detection (LoD) and lower limits of quantification (LLoQ), and carryover. The method was applied to analysis of postmortem peripheral blood samples from 279 forensic cases for which orders for chemical-toxicological examination had been received from the public prosecutor's office. Using six-point and one-point calibrations (latter for rapid screening purposes), precisions and accuracies ranged from -4.8 to 5.8% and -6.4 to 7.5%. Analytical sensitivities for As, Pb, and Tl were 0.08, 0.18, and 0.01 µg/l (LoD) and 0.23, 0.66, and 0.03 µg/l (LLoQ), respectively. Observed postmortem peripheral blood concentrations were As, 1.31 ± 3.42 µg/L; Pb, 17.4 ± 13.1 µg/L; and Tl, 0.11 ± 0.07 µg/L (mean ± standard deviation [SD]). Elemental concentrations, determined in additional quality control samples, were in good agreement to those obtained with an external ICP-MS method based on alkaline sample processing. The current method is practicable and compatible with an ICP-MS system used for trace element analysis in an accredited medical laboratory. It allows for implementation of low-threshold investigations when metal intoxications are suspected in forensic routine.
ABSTRACT
Dynamic Nuclear Polarization solid-state NMR holds the potential to enable a dramatic increase in sensitivity by exploiting the large magnetic moment of the electron. However, applications to biological solids are hampered in uniformly isotopically enriched biomacromolecules due to line broadening which yields a limited spectral resolution at cryogenic temperatures. We show here that high magnetic fields allow to overcome the broadening of resonance lines often experienced at liquid nitrogen temperatures. For a fibril sample of the Alzheimer's disease ß-amyloid peptide, we find similar line widths at low temperature and at room temperature. The presented results open new perspectives for structural investigations in the solid-state.
