The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carlo dropout to regression tasks and show that predictive uncertainty is systematically underestimated. We apply sigma scaling with a single scalar value; a simple, yet effective calibration method for both types of uncertainty. The performance of our approach is evaluated on a variety of common medical regression data sets using different state-of-the-art convolutional network architectures. In our experiments, sigma scaling is able to reliably recalibrate predictive uncertainty. It is easy to implement and maintains the accuracy. Well-calibrated uncertainty in regression allows robust rejection of unreliable predictions or detection of out-of-distribution samples. Our source code is available at: https://github.com/mlaves/well-calibrated-regression-uncertainty

In order to deliver an aerosolized drug in a breath-triggered manner, the initiation of the patient’s inspiration needs to be detected. The best-known systems monitoring breathing patterns are based on flow sensors. However, due to their large dead space volume, flow sensors are not advisable for monitoring the breathing of (preterm) neonates. Newly-developed respiratory sensors, especially when contact-based (invasive), can be tested on (preterm) neonates only with great effort due to clinical and ethical hurdles. Therefore, a physiological model is highly desirable to validate these sensors. For developing such a system, abdominal movement data of (preterm) neonates are required. We recorded time sequences of five preterm neonates’ abdominal movements with a time-of-flight camera and successfully extracted various breathing patterns and respiratory parameters. Several characteristic breathing patterns, such as forced breathing, sighing, apnea and crying, were identified from the movement data. Respiratory parameters, such as duration of inspiration and expiration, as well as respiratory rate and breathing movement over time, were also extracted. This work demonstrated that respiratory parameters of preterm neonates can be determined without contact. Therefore, such a system can be used for breathing detection to provide a trigger signal for breath-triggered drug release systems. Furthermore, based on the recorded data, a physiological abdominal movement model of preterm neonates can now be developed.

Objective: The laryngeal adductor reflex (LAR) is an important mechanism to secure the airways from potential foreign body aspiration. An involvement of the upper esophageal sphincter (UES) in terms of a laryngo‐UES contractile reflex has been identified after laryngeal mucosa stimulation. However, the LAR–UES relationship has not yet been fully explained. This study aimed to determine the magnitude, latency, and occurrence rate of the UES pressure response when the LAR is triggered in order to elucidate the functional relationship between the larynx and the UES.Methods: This prospective study included seven healthy volunteers (5 female, 2 male, age 22–34 years). Laryngeal penetration was simulated by eliciting the LAR 20 times in each individual by applying water‐based microdroplets onto the laryngeal mucosa. UES pressures were measured simultaneously using high‐resolution manometry.Results: Two distinct pressure phases (P1, P2) associated with the LAR were identified. P1 corresponded with a short‐term UES pressure decrease in two subjects and a pressure increase in five subjects occurring 200 to 500 ms after the stimulus. In P2, all subjects experienced an increase in UES pressure with a latency time of approximately 800 to 1700 ms and an average of 40 to 90 mmHg above the UES resting tone.Conclusion: Foreign bodies penetrating the laryngeal inlet lead to a reflex contraction of the UES. Phase P1 could be a result of vocal fold activity caused by the LAR, leading to pressure changes in the UES. The constriction during P2 could strengthen the barrier function of the UES in preparation to a subsequent cough that may be triggered to clear the airways.Level of Evidence: 4 Laryngoscope, 131:E1778–E1784, 2021

The so-called Laryngeal Adductor Reflex (LAR) protects the respiratory tract from particle intrusion by quickly approximating the vocal folds to close the free glottal space. An impaired LAR may be associated with an increased risk of aspiration and other adverse conditions. To evaluate the integrity of the LAR, we recently developed an endoscopic prototype for LAR triggering by shooting accelerated droplets onto a predefined laryngeal target region. We now modified the existing droplet-dispensing system to adapt the fluid system pressure as well as the valve opening time to user-chosen values autonomously. This has been accomplished using a microcontroller board connected to a pressure sensor and a mechatronic syringe pump. For performance validation, we designed a measurement setup capable of tracking the droplet along a vertical trajectory. In addition to the experimental setup, the influence of parameters such as system pressure and valve opening time on the micro-droplet formation is presented. Further development will enable the physician to adjust the droplet momentum by setting a single input value on the microcontroller-based setup, thus further increasing usability of the diagnostic device.

Pathologies of protective laryngeal reflexes such as the laryngeal adductor reflex (LAR) can increase the risk of aspiration pneumonia, a potentially life-threatening inflammation of the lungs caused by the intrusion of foreign particles into the lower airways. To estimate this risk, a standardized and non-invasive LAR screening method is highly desirable. In previous work, a commercially available high-speed laryngoscope has been equipped with a pressurized fluid system to shoot droplets onto the laryngeal structures for LAR stimulation and subsequent reflex latency evaluation. This Micro-droplet Impulse Testing of the LAR (MIT-LAR) lacks droplet impact site prediction for an unbiased and stimulation site-dependent reflex latency assessment. In this work, a two- phase algorithm leveraging stereoscopic image data for droplet impact site prediction and visualization of this prediction in the laryngoscopic image is proposed. A high-speed stereolaryngoscope requiring only a single camera was designed from scratch by combining two rod lens optics in one common shaft. This setup was used for stereoscopic high-speed image data acquisition of droplets shot at different muzzle energies and endoscope roll angles. Surface reconstruction of the target region is performed using a phantom of the human larynx. The point of intersection between the reconstructed surface and the droplet trajectory approximation recorded previously at known droplet formation parameters is calculated. The proposed approach allows stimulation site prediction for an enhanced MIT-LAR procedure. Quantitative evaluation of impact site prediction accuracy for different droplet muzzle energies and nozzle inclinations yields an average prediction error of 2.9 mm (n = 20).