Diabetic retinopathy is a diabetes complication that affects the eyes, caused by damage to the blood vessels of the light-sensitive tissue of the retina. At the onset, diabetic retinopathy may cause no symptoms or only mild vision problems, but eventually it can cause blindness. Totally automated segmentation of Eye Fundus Images (EFI) is a necessary step for accurate and early quantification of lesions, useful in the future for better automated diagnosis of degree of diabetic retinopathy and damage caused by the disease. Deep Learning segmentation networks are the state-of-the-art, but quality, limitations and comparison of architectures of segmentation networks is necessary. We build off-theshelf deep learning architectures and evaluate them on a publicly available dataset, to conclude the strengths and limitations of the approaches and to compare architectures. Results show that the segmentation networks score high on important metrics, such as 87.5% weighted IoU on FCN. We also show that network architecture is very important, with DeepLabV3 and FCN outperforming other networks tested by more than 30 pp. We also show that DeepLabV3 outperforms prior related work using deep learning to detect lesions. Finally, we identify and investigate the problem of very low IoU and precision scores, such as 17% IoU of microaneurisms in DeepLabV3, concluding it is due to a large number of false positives. This leads us to discuss the challenges that lie ahead to improve the limitations that we identified
Decellularized tissue is an important source for biological tissue engineering. Evaluation of the quality of decellularized tissue is performed using scanned images of hematoxylin-eosin stained (H&E) tissue sections and is usually dependent on the observer. The first step in creating a tool for the assessment of the quality of the liver scaffold without observer bias is the automatic segmentation of the whole slide image into three classes: the background, intralobular area, and extralobular area. Such segmentation enables to perform the texture analysis in the intralobular area of the liver scaffold, which is crucial part in the recellularization procedure. Existing semi-automatic methods for general segmentation (i.e., thresholding, watershed, etc.) do not meet the quality requirements. Moreover, there are no methods available to solve this task automatically. Given the low amount of training data, we proposed a two-stage method. The first stage is based on classification of simple hand-crafted descriptors of the pixels and their neighborhoods. This method is trained on partially annotated data. Its outputs are used for training of the second-stage approach, which is based on a convolutional neural network (CNN). Our architecture inspired by U-Net reaches very promising results, despite a very low amount of the training data. We provide qualitative and quantitative data for both stages. With the best training setup, we reach 90.70% recognition accuracy.
- MeSH
- Liver * diagnostic imaging MeSH
- Neural Networks, Computer MeSH
- Image Processing, Computer-Assisted * MeSH
- Semantics * MeSH
- Publication type
- Letter MeSH
Living cell segmentation from bright-field light microscopy images is challenging due to the image complexity and temporal changes in the living cells. Recently developed deep learning (DL)-based methods became popular in medical and microscopy image segmentation tasks due to their success and promising outcomes. The main objective of this paper is to develop a deep learning, U-Net-based method to segment the living cells of the HeLa line in bright-field transmitted light microscopy. To find the most suitable architecture for our datasets, a residual attention U-Net was proposed and compared with an attention and a simple U-Net architecture. The attention mechanism highlights the remarkable features and suppresses activations in the irrelevant image regions. The residual mechanism overcomes with vanishing gradient problem. The Mean-IoU score for our datasets reaches 0.9505, 0.9524, and 0.9530 for the simple, attention, and residual attention U-Net, respectively. The most accurate semantic segmentation results was achieved in the Mean-IoU and Dice metrics by applying the residual and attention mechanisms together. The watershed method applied to this best - Residual Attention - semantic segmentation result gave the segmentation with the specific information for each cell.
This article considers customer typology in fitness centres. The main aim of our survey is to state the basic segments of fitness customers and create their typology. A survey was conducted on a sample of 1004 respondents from 48 fitness centres. We used questionnaires and latent class analysis for the assessment and interpretation of data. The results of our research are as follows: we identified 6 segments of typical customers, of which three are male (we called them student, shark, mature) and three are female (manager, hunter, and student). Each segment is influenced primarily by the age of customers, from which we can develop further characteristics, such as education, income, marital status, etc. Male segments use the main workout area above all, whilst female segments use a much wider range of services offered, for example group exercises, personal training, and cardio theatres.
- Keywords
- typologie, zákazník, segmentace,
- MeSH
- Latent Class Analysis MeSH
- Adult MeSH
- Fitness Centers * MeSH
- Data Interpretation, Statistical MeSH
- Middle Aged MeSH
- Humans MeSH
- Adolescent MeSH
- Surveys and Questionnaires MeSH
- Research * statistics & numerical data MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Adolescent MeSH
- Male MeSH
- Female MeSH
- Publication type
- Research Support, Non-U.S. Gov't MeSH
Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.
- MeSH
- Algorithms * MeSH
- Image Processing, Computer-Assisted * MeSH
- Semantics MeSH
- Machine Learning MeSH
- Publication type
- Journal Article MeSH
- Review MeSH
OBJECTIVE: Lithium has been long used in psychiatry as an adjuvant treatment for bipolar disorder. Chronic lithium intoxication is very rare. DESIGN: We present the case of a 72-year-old female, treated with lithium for more than 10 years for bipolar disorder, who was admitted for gait impairment with weakness of limbs, myoclonus, speech impairment and memory disturbances. RESULTS: Diagnosis of lithium intoxication was based on clinical picture and determination of serum lithium levels. EEG showed severe encephalopathy with triphasic wave complexes. Sensory and motor axonal neuropathy was observed by EMG. Discontinuation of the drug leads to clinical improvement, although not to a fully neurological recovery. CONCLUSION: Lithium is still very effective drug, but requires regular monitoring of serum levels to prevent overdose and symptoms of intoxication. Neurophysiological methods, including EEG and EMG, are strongly recommended to determine the level of peripheral and/or central nervous system impairment.
- MeSH
- Antimanic Agents adverse effects blood therapeutic use MeSH
- Bipolar Disorder blood drug therapy physiopathology MeSH
- Electroencephalography MeSH
- Humans MeSH
- Lithium Carbonate adverse effects blood therapeutic use MeSH
- Myoclonus blood chemically induced physiopathology MeSH
- Brain Diseases blood chemically induced physiopathology MeSH
- Memory Disorders blood chemically induced physiopathology MeSH
- Aged MeSH
- Check Tag
- Humans MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Case Reports MeSH
Pathology diagnostics relies on the assessment of morphology by trained experts, which remains subjective and qualitative. Here we developed a framework for large-scale histomorphometry (FLASH) performing deep learning-based semantic segmentation and subsequent large-scale extraction of interpretable, quantitative, morphometric features in non-tumour kidney histology. We use two internal and three external, multi-centre cohorts to analyse over 1000 kidney biopsies and nephrectomies. By associating morphometric features with clinical parameters, we confirm previous concepts and reveal unexpected relations. We show that the extracted features are independent predictors of long-term clinical outcomes in IgA-nephropathy. We introduce single-structure morphometric analysis by applying techniques from single-cell transcriptomics, identifying distinct glomerular populations and morphometric phenotypes along a trajectory of disease progression. Our study provides a concept for Next-generation Morphometry (NGM), enabling comprehensive quantitative pathology data mining, i.e., pathomics.
- MeSH
- Kidney Glomerulus * pathology MeSH
- Kidney * pathology MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
Words like yeah, okay and (al)right are fairly unspecific in their lexical semantics, and not least for this reason there is a general tendency for them to occur with highly varied and expressive prosodic patterns across languages. Here we examine in depth the prosodic forms that express eight pragmatic functions of the Czech discourse marker jasně, including resignation, reassurance, surprise, indifference or impatience. Using a collection of 172 tokens from a corpus of scripted dialogues by 30 native speakers, we performed acoustic analyses, applied classification algorithms and solicited judgments from native listeners in a perceptual experiment. There appeared to be multi-parametric differences between jasně realizations in terms of their F0, timing and intensity patterns, which gave rise to generally consistent form-function mappings. For example, resignation seems to be realized with a falling intonation contour, relatively slow tempo, long wordinitial consonant and a short word-final vowel. Although the most significant prosodic parameters used for clustering analysis involved segment durations, all pragmatic functions were expressed by patterns of multiple features.
- MeSH
- Speech Acoustics * MeSH
- Phonation physiology MeSH
- Language * MeSH
- Communication MeSH
- Humans MeSH
- Speech Perception physiology MeSH
- Semantics * MeSH
- Verbal Behavior physiology MeSH
- Check Tag
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Geographicals
- Czech Republic MeSH
- MeSH
- Aphasia * MeSH
- Akinetic Mutism * MeSH
- Atrophy * MeSH
- Creutzfeldt-Jakob Syndrome * diagnosis complications mortality MeSH
- Dementia * MeSH
- Hemianopsia * MeSH
- Inpatients * MeSH
- Cognition Disorders * diagnosis MeSH
- Middle Aged MeSH
- Humans MeSH
- Cerebellum * physiopathology MeSH
- Brain * MeSH
- Myoclonus * drug therapy MeSH
- Basal Ganglia Diseases * MeSH
- Neurologic Examination * methods nursing utilization MeSH
- Outpatients * MeSH
- Autopsy * standards utilization MeSH
- Prion Diseases * MeSH
- Disease Progression * MeSH
- Cerebrospinal Fluid Proteins * MeSH
- Aged MeSH
- Home Care Services * MeSH
- Death * MeSH
- Rare Diseases * MeSH
- Medical Futility * MeSH
- Check Tag
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Case Reports MeSH
