Vision Transformer for Parkinson's Disease Classification using Multilingual Sustained Vowel Recordings.

Parkinson's disease (PD) is the 2nd most prevalent neurodegenerative disease in the world. Thus, the early detection of PD has recently been the subject of several scientific and commercial studies. In this paper, we propose a pipeline using Vision Transformer applied to mel-spectrograms for PD classification using multilingual sustained vowel recordings. Furthermore, our proposed transformed-based model shows a great potential to use voice as a single modality biomarker for automatic PD detection without language restrictions, a wide range of vowels, with an F1-score equal to 0.78. The results of our study fall within the range of the estimated prevalence of voice and speech disorders in Parkinson's disease, which ranges from 70-90%. Our study demonstrates a high potential for adaptation in clinical decision-making, allowing for increasingly systematic and fast diagnosis of PD with the potential for use in telemedicine.Clinical relevance- There is an urgent need to develop non invasive biomarker of Parkinson's disease effective enough to detect the onset of the disease to introduce neuroprotective treatment at the earliest stage possible and to follow the results of that intervention. Voice disorders in PD are very frequent and are expected to be utilized as an early diagnostic biomarker. The voice analysis using deep neural networks open new opportunities to assess neurodegenerative diseases' symptoms, for fast diagnosis-making, to guide treatment initiation, and risk prediction. The detection accuracy for voice biomarkers according to our method reached close to the maximum achievable value.

Weigh-in-Motion Site for Type Approval of Vehicle Mass Enforcement Systems in Poland.

The need to protect road infrastructure makes it necessary to direct the mass enforcement control of motor vehicles. Such control, in order to fulfil its role, must be continuous and universal. The only tool currently known to achieve these goals are weigh-in-motion (WIM) systems. The implementation of mass enforcement WIM systems is possible only if the requirements for their metrological properties are formulated, followed by the implementation of administrative procedures for the type approval of WIM systems, rules for their metrological examination, and administrative regulations for their practical use. The AGH University of Krakow, in cooperation with the Central Office of Measures (Polish National Metrological Institute), has been conducting research in this direction for many years, and, now, as part of a research project financed by the Ministry of Education and Science. In this paper, we describe a unique WIM system located in the south of Poland and the results of over two years of our research. These studies are intended to lead to the formulation of requirements for metrological legalisation procedures for this type of system. Our efforts are focused on implementing WIM systems in Poland for direct mass enforcement. The tests carried out confirmed that the constructed system is fully functional. Its equipment with quartz and bending plate load sensors allows for the comparison of both technologies and the measurement of many parameters of the weighed vehicle and environmental parameters affecting weighing accuracy. The tests confirmed the stability of its metrological parameters. The GVW maximal measurement error does not exceed 5%, and the single axle load maximal measurement error does not exceed 12%. The sensors of the environmental parameters allow for the search for correlations between weighing accuracy and the intensity of these parameters.

Towards clinical applicability and computational efficiency in automatic cranial implant design: An overview of the AutoImplant 2021 cranial implant design challenge.

Cranial implants are commonly used for surgical repair of craniectomy-induced skull defects. These implants are usually generated offline and may require days to weeks to be available. An automated implant design process combined with onsite manufacturing facilities can guarantee immediate implant availability and avoid secondary intervention. To address this need, the AutoImplant II challenge was organized in conjunction with MICCAI 2021, catering for the unmet clinical and computational requirements of automatic cranial implant design. The first edition of AutoImplant (AutoImplant I, 2020) demonstrated the general capabilities and effectiveness of data-driven approaches, including deep learning, for a skull shape completion task on synthetic defects. The second AutoImplant challenge (i.e., AutoImplant II, 2021) built upon the first by adding real clinical craniectomy cases as well as additional synthetic imaging data. The AutoImplant II challenge consisted of three tracks. Tracks 1 and 3 used skull images with synthetic defects to evaluate the ability of submitted approaches to generate implants that recreate the original skull shape. Track 3 consisted of the data from the first challenge (i.e., 100 cases for training, and 110 for evaluation), and Track 1 provided 570 training and 100 validation cases aimed at evaluating skull shape completion algorithms at diverse defect patterns. Track 2 also made progress over the first challenge by providing 11 clinically defective skulls and evaluating the submitted implant designs on these clinical cases. The submitted designs were evaluated quantitatively against imaging data from post-craniectomy as well as by an experienced neurosurgeon. Submissions to these challenge tasks made substantial progress in addressing issues such as generalizability, computational efficiency, data augmentation, and implant refinement. This paper serves as a comprehensive summary and comparison of the submissions to the AutoImplant II challenge. Codes and models are available at https://github.com/Jianningli/Autoimplant_II.

Deep learning-based framework for automatic cranial defect reconstruction and implant modeling.

BACKGROUND AND OBJECTIVE: This article presents a robust, fast, and fully automatic method for personalized cranial defect reconstruction and implant modeling. METHODS: We propose a two-step deep learning-based method using a modified U-Net architecture to perform the defect reconstruction, and a dedicated iterative procedure to improve the implant geometry, followed by an automatic generation of models ready for 3-D printing. We propose a cross-case augmentation based on imperfect image registration combining cases from different datasets. Additional ablation studies compare different augmentation strategies and other state-of-the-art methods. RESULTS: We evaluate the method on three datasets introduced during the AutoImplant 2021 challenge, organized jointly with the MICCAI conference. We perform the quantitative evaluation using the Dice and boundary Dice coefficients, and the Hausdorff distance. The Dice coefficient, boundary Dice coefficient, and the 95th percentile of Hausdorff distance averaged across all test sets, are 0.91, 0.94, and 1.53 mm respectively. We perform an additional qualitative evaluation by 3-D printing and visualization in mixed reality to confirm the implant's usefulness. CONCLUSION: The article proposes a complete pipeline that enables one to create the cranial implant model ready for 3-D printing. The described method is a greatly extended version of the method that scored 1st place in all AutoImplant 2021 challenge tasks. We freely release the source code, which together with the open datasets, makes the results fully reproducible. The automatic reconstruction of cranial defects may enable manufacturing personalized implants in a significantly shorter time, possibly allowing one to perform the 3-D printing process directly during a given intervention. Moreover, we show the usability of the defect reconstruction in a mixed reality that may further reduce the surgery time.

Sensors in the Autoclave-Modelling and Implementation of the IoT Steam Sterilization Procedure Counter.

Surgical procedures involve major risks, as pathogens can enter the body unhindered. To prevent this, most surgical instruments and implants are sterilized. However, ensuring that this process is carried out safely and according to the normative requirements is not a trivial task. This study aims to develop a sensor system that can automatically detect successful steam sterilization on the basis of the measured temperature profiles. This can be achieved only when the relationship between the temperature on the surface of the tool and the temperature at the measurement point inside the tool is known. To find this relationship, the thermodynamic model of the system has been developed. Simulated results of thermal simulations were compared with the acquired temperature profiles to verify the correctness of the model. Simulated temperature profiles are in accordance with the measured temperature profiles, thus the developed model can be used in the process of further development of the system as well as for the development of algorithms for automated evaluation of the sterilization process. Although the developed sensor system proved that the detection of sterilization cycles can be automated, further studies that address the possibility of optimization of the system in terms of geometrical dimensions, used materials, and processing algorithms will be of significant importance for the potential commercialization of the presented solution.

Modeling and Implementation of TEG-Based Energy Harvesting System for Steam Sterilization Surveillance Sensor Node.

The aim of this work is a proof of concept, that medical Internet of Things (IoT) sterilization surveillance sensors can be powered by using the heat during a steam sterilization procedure. Hereby, the focus was on the use of thermo-electrical generators (TEG) to generate enough power for an ultra-low-power sensor application. Power generation requirement of the sensor was 1.6 mW over the single sterilization cycle. The thermal gradient across the TEG has been achieved using a highly efficient aerogel-foam-based thermal insulation, shielding a heat storage unit (HSU), connected to one side of the TEG. The evaluation of the developed system was carried out with thermal and electrical simulations based on the parameters extracted from the TEG manufacturer's datasheet. The developed model has been validated with a real prototype using the thermal step response method. It was important for the authors to focus on rapid-prototyping and using off-the-shelf devices and materials. Based on comparison with the physical prototype, the SPICE model was adjusted. With a thermal gradient of 12 °C, the simulated model generated over 2 mW of power. The results show that a significant power generation with this system is possible and usable for sensor applications in medial IoT.