Magnetic resonance imaging-based deep learning model to predict multiple firings in double-stapled colorectal anastomosis

Figure 1 Examples of three-dimensional model of the target regions. A: Models from patients with the use of ≥ 3 linear stapler cartridges; B: Models from patients with the use of ≤ 2 cartridges. The regions of pelvis, mesorectum, and tumor body were represented by drab, yellow, and green, respectively.

Figure 2 Flow chart of the design of pre-warning models. BMI: Body mass index; CEA: Carcinoembryonic antigen; CRM: Circumferential resection margin; MR: Magnetic resonance; Mask R-CNN: Mask region-based convolutional neural network.

Figure 3 Receiver operating characteristic curves of the pre-warning models. A: Clinical model; B: Image model; C: Integrated model.