ABSTRACT
Peripheral blood oxygen saturation (SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula>) is an essential indicator of respiratory functionality and received increasing attention during the COVID-19 pandemic. Clinical findings show that COVID-19 patients can have significantly low SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula> before any obvious symptoms. Measuring an individual's SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula> without having to come into contact with the person can lower the risk of cross contamination and blood circulation problems. The prevalence of smartphones has motivated researchers to investigate methods for monitoring SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula> using smartphone cameras. Most prior schemes involving smartphones are contact-based: They require using a fingertip to cover the phone's camera and the nearby light source to capture reemitted light from the illuminated tissue. In this paper, we propose the first convolutional neural network based noncontact SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula> estimation scheme using smartphone cameras. The scheme analyzes the videos of an individual's hand for physiological sensing, which is convenient and comfortable for users and can protect their privacy and allow for keeping face masks on. We design explainable neural network architectures inspired by the optophysiological models for SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula> measurement and demonstrate the explainability by visualizing the weights for channel combination. Our proposed models outperform the state-of-the-art model that is designed for contact-based SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula> measurement, showing the potential of the proposed method to contribute to public health. We also analyze the impact of skin type and the side of a hand on SpO<inline-formula><tex-math notation="LaTeX">$_{2}$</tex-math></inline-formula> estimation performance. Author
ABSTRACT
Percutaneous image guided thermal ablation has become a cornerstone of therapy for patients with oligometastatic disease and primary liver malignancies. Evolving from percutaneous ethanol injection (PEI), thermal ablation utilizing radiofrequency ablation (RFA) and microwave ablation (MWA) have become the standard approach in the treatment of isolated lesions that fit within the size criteria for curative intent therapy (typically 3-4cm). With the evolution of more intense thermal ablation, such as MWA, the dramatic increase in both the size of ablation zone and intensity of heat generation have extended the limits of this technique. As a result of these innovations, intra-procedural and post-procedural pain have also significantly increased, requiring either higher levels of intravenous sedation or, in some institutions, general anesthesia. In addition to the increase in therapeutic intensity, the use of intravenous sedation during aggressive ablation procedures carries the risk of over-sedation when the noxious insult (i.e. the ablation) is removed, adding further difficulty to post-procedural recovery and management. Furthermore, high subdiaphragmatic lesions become challenging in this setting due to issues relating to sedation and compliance with breath hold/breathing instructions. Although general anesthesia may mitigate these complications, the added resources associated with providing general anesthesia during ablation is not cost effective and may result in substantial delays in treatment. The reduction of Aerosol Generating Medical Procedures (AGMP), such as intubation due to the COVID-19 Pandemic, must also be taken into consideration. Due to the potential increased risk of infection transmission, alternatives to general anesthesia should be considered when safe and possible. Upper abdominal regional nerve block techniques have been used to manage pain related to trauma, surgery, and cancer; however, blocks of this nature are not well described in the interventional radiology literature. The McGill University group has developed experience in using such blocks as splanchnic, celiac and hepatic hilar nerve blocks to provide peri-procedural pain control [1]. Since incorporating these techniques (along with hydrodissection with tumescent anesthesia), we have also observed in our high volume ablation center a dramatic decrease in the amount of sedatives administered during the procedure, a decrease in patient discomfort during localization and ablation, as well as decreased pain post-procedure. Faster time to discharge and overall reduction in room procedural time serve as added benefits. The purpose of this publication is to outline and illustrate the practical application and use of nerve block/regional anesthesia techniques with respect to percutaneous hepatic thermal ablation.