Seeking a Sufficient Data Volume for Railway Infrastructure Component Detection with Computer Vision Models.

Railway infrastructure monitoring is crucial for transportation reliability and travelers' safety. However, it requires plenty of human resources that generate high costs and is limited to the efficiency of the human eye. Integrating machine learning into the railway monitoring process can overcome these problems. Since advanced algorithms perform equally to humans in many tasks, they can provide a faster, cost-effective, and reproducible evaluation of the infrastructure. The main issue with this approach is that training machine learning models involves acquiring a large amount of labeled data, which is unavailable for rail infrastructure. We trained YOLOv5 and MobileNet architectures to meet this challenge in low-data-volume scenarios. We established that 120 observations are enough to train an accurate model for the object-detection task for railway infrastructure. Moreover, we proposed a novel method for extracting background images from railway images. To test our method, we compared the performance of YOLOv5 and MobileNet on small datasets with and without background extraction. The results of the experiments show that background extraction reduces the sufficient data volume to 90 observations.

3D-printed custom ossicular prosthesis - methodology of design and LDV measurements in a cadaver study.

OBJECTIVE: In tympanoplasty, surgical reconstruction of the tympanic membrane and ossicular chain is well-established; however, its hearing results still require improvement. Custom 3D printing of individualized ossicular prostheses seems to be an attractive solution for optimal prosthesis adjustment and better hearing results. AIM: The aim was to design a custom ossicular prosthesis using a 3D printing method based on Cone-beam Computed Tomography (CBCT) scans and assess the acoustic conduction properties of such prosthesis. MATERIAL AND METHODS: A cadaver fresh frozen temporal bone was used. Based on CBCT images, a new incus prosthesis was designed and 3D printed. Next, canal wall-up tympanoplasty was performed. The intact ossicular chain and reconstructed 3D-printed prosthesis chain movements/vibrations were measured with Laser Doppler Vibrometer (LDV) system and analyzed in detail. RESULTS: The CBCT scans provided enough information about the anatomical structures. For frequencies 500 and 1000 Hz and 80 dB SPL sound intensity, collected velocities were higher for the intact ossicular chain than the 3D-printed ossicular prosthesis. The intensity thresholds for movement at 500 and 1000 Hz were lower in the intact ossicular chain than in the 3D-printed ossicular prosthesis. At 2000 Hz, there was the same intensity threshold value in the two measured circumstances. CONCLUSION: It is possible to design a custom individually fitted ossicular prosthesis using a 3D printing method based on CBCT scans. The acoustic conduction properties of such 3D-printed prosthesis showed differences in movability pattern between the intact and reconstructed ossicular chain. More data are needed to analyze the acoustic properties of such designed prostheses in detail. The results of our experiment showed the 3D-printed prosthesis presents the potential to be an interesting option for conductive hearing loss treatment caused by chronic otitis media and the ossicular chain defects.

Outcomes of the two generations of bioresorbable scaffolds (Magmaris vs. Absorb) in acute coronary syndrome in routine clinical practice.

BACKGROUND: Acute coronary syndrome (ACS) as a clinical manifestation of coronary artery disease (CAD) remains a significant cause of mortality and morbidity, as reported worldwide annually. The second generation of drug-eluting stents (DES) is a gold standard in percutaneous interventions in ACS patients however, permanent caging of the vessel with metallic DES has some drawbacks. Bioresorbable vascular scaffolds (BRS) were designed as a temporal vessel-supporting technology allowing for anatomical and functional restoration. Nevertheless, following the initial encouraging reports, numerous concerns about the safety of BRS occurred. METHODS: In this study, a 1-year performance of 193 patients with magnesium BRS - Magmaris (Biotronik, Berlin, Germany) was evaluated in comparison to 160 patients with polymer BRS - Absorb (Abbott-Vascular, Chicago, USA) in the non-ST-segment elevation-ACS setting. RESULTS: The Magmaris, when compared to Absorb showed a significantly lower rate of primary endpoint (death from cardiac causes, myocardial infarction, stent thrombosis) as well as target lesion failure in 30-day and 1 year follow-up. In the Absorb group, a significantly higher rate of stent thrombosis was observed. CONCLUSIONS: Data from the present study suggests encouraging safety a profile and more favorable clinical outcomes of Magnesium BRS in comparison to the polymer Absorb - BRS.

Sex Differences in the Clinical Features and Outcomes of Patients with Acute Coronary Syndrome Treated with Two Generations (Absorb and Magmaris) of Bioresorbable Vascular Scaffolds.

BACKGROUND: Despite the developments in percutaneous coronary interventions (PCI), women are still more likely than men to have unfavorable outcomes after PCI performed in Acute Coronary Syndrome (ACS). The mechanisms of this phenomena are not fully understood. Potential benefits of bioresorbable scaffolds (BRS) may be particularly expressed in the female population. Nevertheless, the data available currently are inconsistent and limited. This study evaluated the gender-related differences in the short-term clinical outcomes in ACS patients treated with implantation of two generations of BRS (first generation, Absorb; second generation, Magmaris). METHODS: The study was divided into two arms. To the first one, we qualified 160 patients with ACS treated with PCI who received 210 Absorb scaffolds. The second arm was composed of 193 patients with ACS who underwent PCI with Magmaris implantation. RESULTS: There were no significant sex-related differences in primary endpoints (cardiovascular-death, myocardial infarction, in-stent thrombosis) or principal secondary endpoints (of target-lesion failure, scaffold restenosis, death from any reason, other cardiovascular events) in either generation of BRS in a 1-year follow-up. CONCLUSIONS: Both genders tended to have a similar outcome in routine clinical practice following BRS implantation due to ACS. The magnesium bioresorbable scaffold (Magmaris) early outcome seemed to be more favorable in comparison to the Absorb scaffold.

The 1-Year Safety and Efficacy Outcomes of Magmaris, Novel Magnesium Bioresorbable Vascular Scaffolds in Diabetes Mellitus Patients with Acute Coronary Syndrome.

BACKGROUND: Diabetes mellitus (DM) is one of the major risk factors contributing to Acute Coronary Syndromes (ACS) and is associated with an increased risk of adverse clinical outcomes following percutaneous coronary intervention (PCI), even when the second generation of drug-eluting stents (DES) is used. In order to overcome the disadvantages of permanent caging of a vessel with metallic DES, bioresorbable scaffold (BRS) technology has been recently developed. However, the prognosis of patients with DM and ACS treated with PCI via subsequent implantation of Magmaris (Biotronik, Berlin, Germany)-a novel magnesium-bioresorbable scaffold-is poorly investigated. METHODS: A total of 193 consecutive subjects with non-ST elevation acute coronary syndrome (NSTE-ACS) who, from October 2016 to March 2020, received one or more Magmaris scaffolds were enrolled in this study. The diabetic group was compared with non-diabetic subjects. RESULTS: There were no significant differences in the occurrence of primary endpoints (cardiovascular death, myocardial infarction, and in-stent thrombosis) and principal secondary endpoints (target-lesion failure, scaffold restenosis, death from any reason, and other cardiovascular events) between the two compared groups in a 1-year follow-up period. CONCLUSIONS: The early 1-year-outcome of magnesium bioresorbable scaffold (Magmaris) seems to be favorable and suggests that this novel BRS is safe and effective in subjects with NSTE-ACS and co-existing DM.

countfitteR: efficient selection of count distributions to assess DNA damage.

BACKGROUND: DNA double-strand breaks can be counted as discrete foci by imaging techniques. In personalized medicine and pharmacology, the analysis of counting data is relevant for numerous applications, e.g., for cancer and aging research and the evaluation of drug efficacy. By default, it is assumed to follow the Poisson distribution. This assumption, however, may lead to biased results and faulty conclusions in datasets with excess zero values (zero-inflation), a variance larger than the mean (overdispersion), or both. In such cases, the assumption of a Poisson distribution would skew the estimation of mean and variance, and other models like the negative binomial (NB), zero-inflated Poisson or zero-inflated NB distributions should be employed. The model chosen has an influence on the parameter estimation (mean value and confidence interval). Yet the choice of the suitable distribution model is not trivial. METHODS: To support, simplify and objectify this process, we have developed the countfitteR software as an R package. We used a Bayesian approach for distribution model selection and the shiny web application framework for interactive data analysis. RESULTS: We show the application of our software based on examples of DNA double-strand break count data from phenotypic imaging by multiplex fluorescence microscopy. In analyzing numerous datasets of molecular pharmacological markers (phosphorylated histone H2AX and p53 binding protein), countfitteR demonstrated an equal or superior statistical performance compared to the usually employed two-step procedure, with an overall power of up to 98%. In addition, it still gave information in cases with no result at all from the two-step procedure. In our data sample we found that the NB distribution was the most frequent, with the Poisson distribution taking second place. CONCLUSIONS: countfitteR can perform an automated distribution model selection and thus support the data analysis and lead to objective statistically verifiable estimated values. Originally designed for the analysis of foci in biomedical image data, countfitteR can be used in a variety of areas where non-Poisson distributed counting data is prevalent.