Institute of Fundamental Technological Research

Background: Immersive technologies like Mixed Reality (MR), Virtual Reality (VR) and Augmented Reality (AR) are becoming increasingly popular and gain user trust across various fields, particularly in medicine. In this paper we will use the general term Mixed Reality (MR) to refer to the various virtual reality methods, namely VR and AR. These new immersive technologies require varying degrees of instruction, both in their practice use, as well as in how to adjust to interacting with 3D virtual spaces. This study assesses the pedagogical value of these immersive technologies in medical education. Method: We surveyed a group of 211 students and 47 academic faculty at a medical college regarding potential applications of MR in the medical curriculum by using a questionnaire comprised of eight questions. Results were analyzed accounting for user age and professional position, i.e., student vs faculty. Results: 70% of students and 60% of the academic faculty think that MR-supplemented education is advantageous over a classical instruction. Most highly valued were the 3D visualization capabilities of MR, especially in anatomy classes. There was no significant statistical difference between students and faculty responders. Moreover, screensharing between faculty and students contributed to better, longer lasting absorption of knowledge. Surprisingly, the main issue was related to availability, i.e., only 5% of students had access to MR, while 17% of faculty use MR regularly, and 36% occasionally. Conclusions: MR technology can be a valuable resource that supports traditional medical education, especially via 3D anatomy classes, however MR availability needs to be increased. Moreover, MR expands the capabilities and effectiveness of remote learning, which was normalized during the COVID-19 pandemic, to ensure effective student and patient education. MR-based lessons, or even select modules, provide a unique opportunity to ex-change experiences inside and outside the medical community.

mixed reality, e-learning, remote learning, real-time rendering, 3D visualization, medical education

Background and objective: People suffer from sleep disorders caused by work-related stress, irregular lifestyle or mental health problems. Therefore, development of effective tools to diagnose sleep disorders is important. Recently, to analyze biomedical signals Information Theory is exploited. We propose efficient classification method of sleep anomalies by applying entropy estimating algorithms to encoded ECGs signals coming from patients suffering from Sleep-Related Breathing Disorders (SRBD). Methods: First, ECGs were discretized using the encoding method which captures the biosignals variability. It takes into account oscillations of ECG measurements around signals averages. Next, to estimate entropy of encoded signals Lempel–Ziv complexity algorithm (LZ) which measures patterns generation rate was applied. Then, optimal encoding parameters, which allow distinguishing normal versus abnormal events during sleep with high sensitivity and specificity were determined numerically. Simultaneously, subjects' states were identified using acoustic signal of breathing recorded in the same period during sleep. Results: Random sequences show normalized LZ close to 1 while for more regular sequences it is closer to 0. Our calculations show that SRBDs have normalized LZ around 0.32 (on average), while control group has complexity around 0.85. The results obtained to public database are similar, i.e. LZ for SRBDs around 0.48 and for control group 0.7. These show that signals within the control group are more random whereas for the SRBD group ECGs are more deterministic. This finding remained valid for both signals acquired during the whole duration of experiment, and when shorter time intervals were considered. Proposed classifier provided sleep disorders diagnostics with a sensitivity of 93.75 and specificity of 73.00%. To validate our method we have considered also different variants as a training and as testing sets. In all cases, the optimal encoding parameter, sensitivity and specificity values were similar to our results above. Conclusions: Our pilot study suggests that LZ based algorithm could be used as a clinical tool to classify sleep disorders since the LZ complexities for SRBD positives versus healthy individuals show a significant difference. Moreover, normalized LZ complexity changes are related to the snoring level. This study also indicates that LZ technique is able to detect sleep abnormalities in early disorders stage.

information theory, Lempel-Ziv complexity, entropy, ECG, sleep-related breathing disorders, randomness

Early pancreatic cancer diagnosis and therapy drastically increase the chances of survival. Tumor visualization using CT scan images is an important part of these processes. In this paper, we apply Mixed Reality (MR) and Artificial Intelligence, in particular, Machine Learning (ML) to prepare image-guided 3D models of pancreatic cancer in a population of oncology patients. Object detection was based on the convolution neural network, i.e. the You Only Look Once (YOLO) version 7 algorithm, while the semantic segmentation has been done with the 3D-UNET algorithm. Next, the 3D holographic visualization of this model as an interactive, MR object was performed using the Microsoft HoloLens2. The results indicated that the proposed MR and ML-based approach can precisely segment the pancreas along with suspected lesions, thus providing a reliable tool for diagnostics and surgical planning, especially when considering organ reconstruction during pancreaticoduodenectomy.

Extended Reality, Mixed Reality, Augmented Reality, Head-Mounted Displays, Artificial Intelligence, Image-guided surgery