Radiomics and anaesthetic planning: Quantitative imaging as a new frontier in preoperative risk assessment

Figure 1 The radiomics pipeline for perioperative anaesthetic assessment. CT: Computed tomography; MRI: Magnetic resonance imaging; PET: Positron emission tomography; ROI: Region of interest; IBSI: Image biomarker standardisation initiative; GLCM/GLRLM/GLSZM/GLDM/NGTDM: Texture feature matrices; PACS: Picture archiving and communication system; EHR: Electronic health record; PPCs: Postoperative pulmonary complications; AKI: Acute kidney injury; AUC: Area under the curve; CV: Coefficient of variation; LoG: Laplacian of Gaussian; LASSO: Least absolute shrinkage and selection operator; mRMR: Minimum redundancy maximum relevance; PCA: Principal component analysis; SVM: Support vector machine; CNN: Convolutional neural network; SHAP: SHapley Additive exPlanations.

Figure 2 Multi-organ radiomics integration framework for precision anaesthesia. CT: Computed tomography; ASA-PS: American Society of Anesthesiologists Physical Status; SMI: Skeletal Muscle Index; SMD: Skeletal muscle density; VAT: Visceral adipose tissue; SAT: Subcutaneous adipose tissue; Vd: Volume of distribution; EAT: Epicardial adipose tissue; PVAT: Perivascular adipose tissue; POAF: Postoperative atrial fibrillation; COPD: Chronic obstructive pulmonary disease; PPCs: Postoperative pulmonary complications; AUC: Area under the curve; NMB: Neuromuscular blocker; HDU: High-dependency unit; ICU: Intensive care unit; SHAP: SHapley Additive exPlanations; LIME: Local Interpretable model-agnostic explanations; GLCM/GLRLM/GLSZM: Texture feature matrices; LightGBM: Light gradient boosting machine; XGBoost: Extreme Gradient Boosting.