Institute of Fundamental Technological Research

Abstract:
Introduction: Hemodialysis patients are at higher risk of developing cognitive impairment, but the pattern of affected cognitive domains is still undetermined. Little is also known about the symptoms of depression and anxiety in hemodialysis patients. Methods: In this cross-sectional study, we included 74 consecutive adult patients undergoing hemodialysis. Cognitive functions were assessed using the Addenbrooke Cognitive Test III. In addition, all patients were screened for symptoms of depression and anxiety using the Hospital Anxiety and Depression Scale. Results: The mean age of hemodialysis patients was 65.69 ± 14 years. Among the patients, there were 27% and 31% of patients with mild cognitive impairment and suspected dementia, respectively. In the group of patients with suspected dementia, all cognitive functions had significantly lower values compared to these functions in incognitively unimpaired and mild cognitive impairment patients. The most impaired domain was verbal fluency, which reflects impairments in executive function. Depression and anxiety symptoms were observed in 28% and 22% of patients, respectively. Patients with anxiety symptoms had higher levels of endogenous creatinine, parathyroid hormone, and hemoglobin, as well as decreased creatinine clearance, being younger and less educated. No factors contributing to the occurrence of depressive symptoms were found. Conclusion: Cognitive dysfunction is a significant problem in hemodialysis patients. Our study showed that the prevalence of cognitive impairment and depression and anxiety symptoms in hemodialysis patients was high. The domain of executive functions was most affected. Furthermore, creatinine, parathyroid hormone, hemoglobin levels, creatinine clearance, and education affected the anxiety scale score.

Keywords:
hemodialysis,cognitive impairment,depression,anxiety

Abstract:
Purpose: BUS-Set is a reproducible benchmark for breast ultrasound (BUS) lesion segmentation, comprising of publicly available images with the aim of improving future comparisons between machine learning models within the field of BUS. Method: Four publicly available datasets were compiled creating an overall set of 1154 BUS images, from five different scanner types. Full dataset details have been provided, which include clinical labels and detailed annotations. Further- more, nine state-of -the-art deep learning architectures were selected to form the initial benchmark segmentation result, tested using five-fold cross-validation and MANOVA/ANOVA with Tukey statistical significance test with a threshold of 0.01. Additional evaluation of these architectures was conducted, exploring possible training bias, and lesion size and type effects. Results: Of the nine state-of -the-art benchmarked architectures, Mask R-CNN obtained the highest overall results, with the following mean metric scores: Dice score of 0.851, intersection over union of 0.786 and pixel accuracy of 0.975. MANOVA/ANOVA and Tukey test results showed Mask R-CNN to be statistically significant better compared to all other benchmarked models with a p-value > 0.01. Moreover, Mask R-CNN achieved the highest mean Dice score of 0.839 on an additional 16 image dataset, that contained multiple lesions per image. Further analysis on regions of interest was conducted, assessing Hamming distance, depth-to-width ratio (DWR), circularity, and elongation, which showed that the Mask R-CNN’s segmentations maintained the most morphological fea-tures with correlation coefficients of 0.888, 0.532, 0.876 for DWR, circularity, and elongation, respectively. Based on the correlation coefficients, statistical test indicated that Mask R-CNN was only significantly different to Sk-U-Net.Conclusions: BUS-Set is a fully reproducible benchmark for BUS lesion seg-mentation obtained through the use of public datasets and GitHub. Of the state-of -the-art convolution neural network (CNN)-based architectures, Mask R-CNN achieved the highest performance overall, further analysis indicated that a training bias may have occurred due to the lesion size variation in the dataset. All dataset and architecture details are available at GitHub: https://github.com/corcor27/BUS-Set, which allows for a fully reproducible benchmark.

Keywords:
breast segmentation,public datasets

Abstract:
Portable, hand-held ultrasound devices capable of 3D imaging in real time are the next generation of the
medical imaging apparatus adapted not only for professional medical stuff but for a wide group of less advanced users. Limited power supply capacity and the relatively small number of channels used for the ultrasound data acquisition are the most important limitations that should be taken into account when designing such devices and when developing the corresponding image reconstruction algorithms. The aim of this study was to develop a new 3D ultrasound imaging method which would take into account the above-mentioned features of the new generation of ultrasonic devices – low-cost portable general access scanners.
It was based on the synthetic transmit aperture (STA) method combined with the Fourier spectrum domain
(SD) acoustic data processing. The STA using a limited number of elements in transmit and receive modes for
ultrasound data acquisition allowed both aforementioned constraints to be obeyed simultaneously. Moreover, the
computational speed of the fast Fourier transform (FFT) algorithm utilized for the ultrasound image synthesis
in the spectrum domain makes the proposed method to be more competitive compared to the conventional time domain (TD) STA method based on the delay-and-sum (DAS) technique, especially in the case of 3D imaging in real time mode.
Performance of the proposed method was verified using numerical 3D acoustic data simulated in the Field II
program for MATLAB and using experimental data from the custom design 3D scattering phantom collected by means of the Verasonics Vantage 256™ research ultrasound system equipped with the dedicated 1024-element 2D matrix transducer.
The method proposed in this paper was about 80 times faster than its counterpart based on the time domain synthetic transmit aperture (TD-STA) approach in the numerical example of a single 3D ultrasound
image synthesized from 4 partial images each containing 64 × 64 × 512 pixels.
It was also shown that the acceleration of the image reconstruction was achieved at the cost of a slight
deterioration in the image quality assessed by the contrast and contrast-to-noise ratio (CNR).

Keywords:
ultrasound imaging, matrix transducer, delay-and-sum, Fourier transform

Abstract:
Introduction. Cognitive impairment (CI) is common in end-stage kidney disease (ESKD), including kidney transplant recipients. Patients with cognitive problems may find it difficult to comply with medical recommendations after kidney transplantation (KT), which can be the cause of many complications, poorer prognosis, and increased
hospitalization rates after transplantation. Additionally, some patients after KT may experience depression and anxiety, which are prevalent comorbidities in patients with ESKD. Methods. In this single–center, cross-sectional study, we included 56 consecutive adult patients after KT. Cognitive function were assessed using the Addenbrooke Cognitive Test III (ACE III). In addition, all patients were screened for
depression and anxiety using the Hospital Anxiety and Depression Scale (HADS). The impact of immunosuppressive therapy and other disease-related variables on cognitive function were also assessed. Results. A total of 56 KT patients, with a mean age of 50.3 ± 11.7 years, transplanted ≤ 35 months ago were included
in the study. The prevalence of CI was 30%. Compared with cognitively unimpaired patients, patients with CI scored significantly lower in all cognitive domains. Furthermore, better cognitive functioning after KT was significantly
associated with more years of schooling. We found no significant correlation between CI and age at assessment, duration of dialysis before KT, creatinine levels, creatinine clearance, uric acid levels, hemoglobin levels, comorbid
cardiovascular diseases as well as immunosuppressive therapy. In addition, the prevalence of depression and anxiety in screening tests was 12.5% and 27%, respectively, and patients receiving higher daily dose of prednisone had higher
HADS scores on both the depression and anxiety subscales (not statistically significant). Downloaded from http://karger.com/kbr/article-pdf/doi/10.1159/000533755/3991154/000533755.pdf by guest on 05 September 2023
Discussion/Conclusion. Cognitive disorders is a relevant issue in kidney transplant recipients. There might be many factors, both before and after KT, that have a negative impact on cognition. Therefore, further research is needed to
increase knowledge about the course and profile of cognitive function after KT

Keywords:
cognitive impairment,kidney transplantation,immunosuppressive therapy,ACE III test,HADS

Abstract:
Background: Cognitive impairment (CI) in patients with chronic kidney disease, including those treated with renal replacement therapy, is a growing problem worldwide. Objectives: The study aimed to assess the prevalence of CI and associated factors in patients undergoing peritoneal dialysis (PD). Methods: In this cross-sectional study, 18 consecutive patients with PD therapy and 15 controls were evaluated for CI using the Addenbrooke’s Cognitive Examination III (ACE III) test. Results: The prevalence of CI was 33% in patients and 27% in the control group and was not statistically significant. A higher prevalence of CI was found in subjects aged ≥65 years old than in those <65 years old (p = 0.02), but only in the control group. The prevalence of CI in PD patients over and under 65 years of age did not differ statistically significantly (p = 0.12). Memory and verbal fluency were the most affected cognitive domain in PD patients with CI (p = 0.00, p = 0.04, respectively). There was a significant correlation between higher educated PD patients and the ACE III test results. The duration of dialysis did not affect the results of the cognitive screening test. Conclusions: CI is a growing problem in the course of chronic kidney disease and dialysis therapy. It seems that cognitive problems may occur in patients undergoing PD at a younger age than in the general population with particularly affected memory and verbal fluency. Higher educated patients score better on the cognitive screening test.

Keywords:
Cognitive impairment,Chronic kidney disease,Peritoneal dialysis,Addenbrooke’s Cognitive Examination III test,Screening test

Abstract:
In an interesting article previously published in Data in Brief [Dataset of breast ultrasound images" by W. Al-Dhabyani, M. Gomaa, H. Khaled & A. Fahmy, Data in Brief, 2020, 28, 104863], the authors presented a dataset of breast ultrasound images containing lesions. As of April 22, 2023, this study has garnered significant attention from researchers, as evident by its 298 citations in Scopus data. This is unsurprising considering that the study presents one of the few publicly available datasets on breast ultrasound images, as well as binary masks highlighting the lesions. When implementing various aspects of explainable AI, we verify the correctness of the input data at every stage, especially when using various data sources. In an attempt to use this dataset for research, we did some exploration and identified some inconsistencies that could have a significant impact on the results of the studies utilizing them. As the role of tumor detection is indisputable we feel obliged to point attention to some aspects that need to be kept in mind while using this database in order to receive reliable and good quality results.