Patient-Specific 3-Dimensional Model of Smooth Muscle Cell and Extracellular Matrix Dysfunction for the Study of Aortic Aneurysms.

INTRODUCTION: Abdominal aortic aneurysms (AAAs) are associated with overall high mortality in case of rupture. Since the pathophysiology is unclear, no adequate pharmacological therapy exists. Smooth muscle cells (SMCs) dysfunction and extracellular matrix (ECM) degradation have been proposed as underlying causes. We investigated SMC spatial organization and SMC-ECM interactions in our novel 3-dimensional (3D) vascular model. We validated our model for future use by comparing it to existing 2-dimensional (2D) cell culture. Our model can be used for translational studies of SMC and their role in AAA pathophysiology. MATERIALS AND METHODS: SMC isolated from the medial layer of were the aortic wall of controls and AAA patients seeded on electrospun poly-lactide-co-glycolide scaffolds and cultured for 5 weeks, after which endothelial cells (EC) are added. Cell morphology, orientation, mechanical properties and ECM production were quantified for validation and comparison between controls and patients. RESULTS: We show that cultured SMC proliferate into multiple layers after 5 weeks in culture and produce ECM proteins, mimicking their behavior in the medial aortic layer. EC attach to multilayered SMC, mimicking layer interactions. The novel SMC model exhibits viscoelastic properties comparable to biological vessels; cytoskeletal organization increases during the 5 weeks in culture; increased cytoskeletal alignment and decreased ECM production indicate different organization of AAA patients' cells compared with control. CONCLUSION: We present a valuable preclinical model of AAA constructed with patient specific cells with applications in both translational research and therapeutic developments. We observed SMC spatial reorganization in a time course of 5 weeks in our robust, patient-specific model of SMC-EC organization and ECM production.

A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes.

Malignant lateral lymph nodes (LLNs) in low, locally advanced rectal cancer can cause (ipsi-lateral) local recurrences ((L)LR). Accurate identification is, therefore, essential. This study explored LLN features to create an artificial intelligence prediction model, estimating the risk of (L)LR. This retrospective multicentre cohort study examined 196 patients diagnosed with rectal cancer between 2008 and 2020 from three tertiary centres in the Netherlands. Primary and restaging T2W magnetic resonance imaging and clinical features were used. Visible LLNs were segmented and used for a multi-channel convolutional neural network. A deep learning model was developed and trained for the prediction of (L)LR according to malignant LLNs. Combined imaging and clinical features resulted in AUCs of 0.78 and 0.80 for LR and LLR, respectively. The sensitivity and specificity were 85.7% and 67.6%, respectively. Class activation map explainability methods were applied and consistently identified the same high-risk regions with structural similarity indices ranging from 0.772-0.930. This model resulted in good predictive value for (L)LR rates and can form the basis of future auto-segmentation programs to assist in the identification of high-risk patients and the development of risk stratification models.