Automated surgery planning for an obstructed nose by combining computational fluid dynamics with reinforcement learning.

Septoplasty and turbinectomy are among the most common interventions in the field of rhinology. Their constantly debated success rates and the lack of quantitative flow data of the entire nasal airway for planning the surgery necessitate methodological improvement. Thus, physics-based surgery planning is highly desirable. In this work, a novel and accurate method is developed to enhance surgery planning by physical aspects of respiration, i.e., to plan anti-obstructive surgery, for the first time a reinforcement learning algorithm is combined with large-scale computational fluid dynamics simulations. The method is integrated into an automated pipeline based on computed tomography imaging. The proposed surgical intervention is compared to a surgeon's initial plan, or the maximum possible intervention, which allows the quantitative evaluation of the intended surgery. Two criteria are considered: (i) the capability to supply the nasal airway with air expressed by the pressure loss and (ii) the capability to heat incoming air represented by the temperature increase. For a test patient suffering from a deviated septum near the nostrils and a bony spur further downstream, the method recommends surgical interventions exactly at these locations. For equal weights on the two criteria (i) and (ii), the algorithm proposes a slightly weaker correction of the deviated septum at the first location, compared to the surgeon's plan. At the second location, the algorithm proposes to keep the bony spur. For a larger weight on criterion (i), the algorithm tends to widen the nasal passage by removing the bony spur. For a larger weight on criterion (ii), the algorithm's suggestion approaches the pre-surgical state with narrowed channels that favor heat transfer. A second patient is investigated that suffers from enlarged turbinates in the left nasal passage. For equal weights on the two criteria (i) and (ii), the algorithm proposes a nearly complete removal of the inferior turbinate, and a moderate reduction of the middle turbinate. An increased weight on criterion (i) leads to an additional reduction of the middle turbinate, and a larger weight on criterion (ii) yields a solution with only slight reductions of both turbinates, i.e., focusing on a sufficient heat exchange between incoming air and the air-nose interface. The proposed method has the potential to improve the success rates of the aforementioned surgeries and can be extended to further biomedical flows.

Effects of the Nasal Cavity Complexity on the Pharyngeal Airway Fluid Mechanics: A Computational Study.

The impact of the human nasal airway complexity on the pharyngeal airway fluid mechanics is investigated at inspiration. It is the aim to find a suitable degree of geometrical reduction that allows for an efficient segmentation of the human airways from cone-beam computed tomography images. The flow physics is simulated by a lattice Boltzmann method on high-performance computers. For two patients, the flow field through the complete upper airway is compared to results obtained from three surface variants with continuously decreasing complexity. The most complex reduced airway model includes the middle and inferior turbinates, while the moderate model only features the inferior turbinates. In the simplest model, a pipe-like artificial structure is attached to the airway. For each model, the averaged pressure is computed at different cross sections. Furthermore, the flow fields are investigated by means of averaged velocity magnitudes, in-plane velocity vectors, and streamlines. By analyzing the averaged pressure loss from the nostrils to each cross section, it is found that only the most complex reduced models are capable of approximating the pressure distribution from the original geometries. In the moderate models, the geometry reductions lead to overpredictions of the pressure loss in the pharynx. Attaching a pipe-like structure leads to a higher deceleration of the incoming flow and underpredicted pressure losses and velocities, especially in the upper part of the pharynx. Dean-like vortices are observed in the moderate and pipe-like models, since their shape comes close to a [Formula: see text]-bend elbow pipe.

Prediction of a typhoon track using a generative adversarial network and satellite images.

Tracks of typhoons are predicted using a generative adversarial network (GAN) with satellite images as inputs. Time series of satellite images of typhoons which occurred in the Korea Peninsula in the past are used to train the neural network. The trained GAN is employed to produce a 6-hour-advance track of a typhoon for which the GAN was not trained. The predicted track image of a typhoon favorably identifies the future location of the typhoon center as well as the deformed cloud structures. Errors between predicted and real typhoon centers are measured quantitatively in kilometers. An averaged error of 95.6 km is achieved for tested 10 typhoons. Predicting sudden changes of the track in westward or northward directions is identified as a challenging task, while the prediction is significantly improved, when velocity fields are employed along with satellite images.