Tracheal, Lung, and Diaphragmatic Applications of M-Mode Ultrasonography in Anesthesiology and Critical Care

Automatic detection of pleural line and lung sliding in lung ultrasonography using convolutional neural networks

Background

Lung ultrasonography (LUS) is a valuable diagnostic tool, but there is a shortage of LUS experts with extensive knowledge and significant experience in the field. Convolutional neural networks (CNNs) have the potential to mitigate this issue by facilitating computer-aided diagnosis.

Methods

We propose computer-aided system by a CNN-based method for LUS diagnosis. As the first consideration, we investigated pleural line and lung sliding. The pleural line indicates the position of pleura in an ultrasound image, and LUS is performed after first confirming the position of pleural line. Lung sliding defined as the movement of the pleural line, and the absence of this feature is associated with pneumothorax.

Results

Our proposed method accurately detected pleural line and lung sliding, demonstrating its potential to provide valuable diagnostic information on lung lesions.

Setting the Standards: Neonatal Lung Ultrasound in Clinical Practice

The use of lung ultrasonography in neonates is increasing at a very fast rate. Evidence-based guidelines on the use of lung ultrasound (LU) in neonates and children have been published and well received across the world. However, there remains a lack of standardized curriculum for lung ultrasound training and standards for its application at the bedside. This article focuses on providing a standardized approach to the application of lung ultrasonography in neonates for the common neonatal conditions and how it can be integrated into bedside clinical decision-making.

Pleuropulmonary and diaphragmatic ultrasound in intensive care medicine

The usefulness of ultrasound for chest exploration was described in 1968. It was not until the 1990s, when its use became widespread in Intensive Care Units as a diagnostic, monitoring and procedural guide tool. The fact that it is a non-invasive tool, accessible at the bedside, with a sensitivity and specificity close to computerized tomography (CT) and with a short learning curve, have made it a mandatory technique in the management of critically ill patients. It is essential to know that there are different air/fluid ratio generated by different pathologies that gives rise to one echographic pattern or another. The identification of these patterns together with the clinical information will allow to make an accurate diagnosis in most settings of respiratory failure. Likewise, we must not forget the importance of evaluating diaphragmatic function by ultrasound during weaning from mechanical ventilation.

Role of ultrasound in acute respiratory failure and in the weaning of mechanical ventilation

Comprehensive ultrasound assessment has become an essential tool to facilitate the diagnosis and therapeutic management of critically ill patients with acute respiratory failure (ARF). There is evidence supporting the use of ultrasound for the diagnosis of pneumothorax, acute respiratory distress syndrome, cardiogenic pulmonary edema, pneumonia and acute pulmonary thromboembolism, and in patients with COVID-19. In addition, in recent years, the use of ultrasound to evaluate responses to treatment in critically ill patients with ARF has been developed, providing a noninvasive tool for titrating positive end-expiratory pressure, monitoring recruitment maneuvers and response to prone position, as well as for facilitating weaning from mechanical ventilation. The objective of this review is to summarize the basic concepts on the utility of ultrasound in the diagnosis and monitoring of critically ill patients with ARF.

Training Ultrasound Image Classification Deep-Learning Algorithms for Pneumothorax Detection Using a Synthetic Tissue Phantom Apparatus

Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.

Practical considerations for developing a lung transplantation anesthesiology program

The advancement in lung transplantation outcomes has been secondary to ongoing improvements within multiple medical specialties. The recent emergence of literature describing the impact of anesthetic management on perioperative outcomes has led to the beginnings of formalized training fellowships within lung transplantation anesthesiology. Practical considerations for the development of a lung transplantation anesthesiology program, both clinical and educational, are herein described.

Comparison of gastric insufflation using LMA-supreme and I-gel versus tracheal intubation in laparoscopic gynecological surgery by ultrasound: a randomized observational trial

Background

The application of bedside ultrasound to evaluate gastric content and volume can assist in determining aspiration risk. Applying positive pressure ventilation via supraglottic airway devices (SAD) can result in a degree of gastric insufflation. This study assessed and compared the antral cross-sectional area (CSA) in patients undergoing laparoscopic gynecological surgery when managed with different SAD.

Methods

One hundred American Society of Anesthesiologists I or II female patients were assessed for inclusion in this study and divided into three groups of different ventilation devices. Patients were randomly allocated into three groups to receive LMA-Supreme (Group S), I-gel (Group I) or tracheal tube (Group T). The primary outcome was the antral cross-sectional area and secondary outcomes included haemodynamic parameters and postoperative morbidity such as sore throat, hoarseness, dry throat, nausea and vomiting.

Results

The antral CSA was not significantly different among three groups before induction (P = 0.451), after induction (P = 0.456) and at the end of surgery (P = 0.195). The haemodynamic variables were significantly higher in the tracheal tube group than in the LMA-Supreme and I-gel groups after insertion (P < 0.0001) and after removal (P < 0.01). Sore throat was detected in none in the I-gel group compare to two patients (6.7%) in the LMA-Supreme group and fifteen patients (50%) in the tracheal tube group. Hoareness was detected in one (3.3%) in the I-gel group compare to two patients (6.7%) in the LMA-Supreme group and eleven patients (36.7%) in the tracheal tube group.

Conclusions

The SADs do not cause obvious gastric insufflation. Thus, LMA-Supreme and I-gel can be widely used as alternative to endotracheal intubation for the short laparoscopic gynecological surgery.

Trial registration

This trial was registered at the Chinese Clinical Trial Registry (ChiCTR1800018212, data of registration, September 2018).