Feet Segmentation for Regional Analgesia Monitoring Using Convolutional RFF and Layer-Wise Weighted CAM Interpretability

Regional neuraxial analgesia for pain relief during labor is a universally accepted, safe, and effective procedure involving administering medication into the epidural. Still, an adequate assessment requires continuous patient monitoring after catheter placement. This research introduces cutting-edge semantic thermal image segmentation method emphasizing superior interpretability regional monitoring. Namely, we propose novel Convolutional Random Fourier Features-based approach, termed CRFFg, custom-designed layer-wise weighted class-activation maps created explicitly foot segmentation. Our aims to enhance three well-known (FCN, UNet, ResUNet). We have rigorously evaluated our methodology on challenging dataset of images from pregnant women who underwent epidural anesthesia. Its limited size significant variability distinguish this dataset. Furthermore, validation results indicate that proposed not only delivers competitive in but also significantly improves explainability process.