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
- algoritmy * MeSH
- počítačové zpracování obrazu * MeSH
- sémantika MeSH
- strojové učení MeSH
- Publikační typ
- časopisecké články MeSH
- přehledy MeSH
Arousing events influence retrieval success, with a number of studies supporting a context-dependent effect of arousal on episodic memory retrieval. An improvement in speed and accuracy of episodic memories is observed when negative arousal is attached to them. In contrast, enhancing effects of negative arousal have not been reported to improve semantic memory retrieval. Episodic and semantic memory are highly interactive and yet differ based on their embedded contextual content. Although differences in brain activity exist between episodic and semantic memory, the two types of memory retrieval are part of a common long-term memory system. Considering the shared processes between episodic and semantic memory, the objectives of the current study were twofold: i) to examine, employing a novel paradigm, whether performance on episodic and semantic memory retrieval would be influenced differently by varying levels of arousal, between negative and neutral valence; and ii) to explore the neural patterns underlying these processes. Forty-seven healthy young adults were recruited and completed the experiment in the MRI scanner. The results demonstrated a negative arousal effect on the brain circuitry subserving both memory conditions as well as on behavioural performance, as indicated by better accuracy and faster reaction times. The study provides an insight into the role of negative arousal in memory processes and contributes to our understanding of the interplay between cognitive and emotional factors in memory modulation. Our work also highlights the highly interactive nature of episodic and semantic memory, and emphasises the importance in understanding how negative arousal interacts with the contextual content of a memory, on a behavioural and neurofunctional level.
- MeSH
- arousal MeSH
- emoce MeSH
- epizodická paměť * MeSH
- lidé MeSH
- mapování mozku MeSH
- mladý dospělý MeSH
- mozek * diagnostické zobrazování MeSH
- rozpomínání MeSH
- sémantika MeSH
- Check Tag
- lidé MeSH
- mladý dospělý MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Artificial intelligence (AI) has advanced substantially in recent years, transforming many industries and improving the way people live and work. In scientific research, AI can enhance the quality and efficiency of data analysis and publication. However, AI has also opened up the possibility of generating high-quality fraudulent papers that are difficult to detect, raising important questions about the integrity of scientific research and the trustworthiness of published papers. OBJECTIVE: The aim of this study was to investigate the capabilities of current AI language models in generating high-quality fraudulent medical articles. We hypothesized that modern AI models can create highly convincing fraudulent papers that can easily deceive readers and even experienced researchers. METHODS: This proof-of-concept study used ChatGPT (Chat Generative Pre-trained Transformer) powered by the GPT-3 (Generative Pre-trained Transformer 3) language model to generate a fraudulent scientific article related to neurosurgery. GPT-3 is a large language model developed by OpenAI that uses deep learning algorithms to generate human-like text in response to prompts given by users. The model was trained on a massive corpus of text from the internet and is capable of generating high-quality text in a variety of languages and on various topics. The authors posed questions and prompts to the model and refined them iteratively as the model generated the responses. The goal was to create a completely fabricated article including the abstract, introduction, material and methods, discussion, references, charts, etc. Once the article was generated, it was reviewed for accuracy and coherence by experts in the fields of neurosurgery, psychiatry, and statistics and compared to existing similar articles. RESULTS: The study found that the AI language model can create a highly convincing fraudulent article that resembled a genuine scientific paper in terms of word usage, sentence structure, and overall composition. The AI-generated article included standard sections such as introduction, material and methods, results, and discussion, as well a data sheet. It consisted of 1992 words and 17 citations, and the whole process of article creation took approximately 1 hour without any special training of the human user. However, there were some concerns and specific mistakes identified in the generated article, specifically in the references. CONCLUSIONS: The study demonstrates the potential of current AI language models to generate completely fabricated scientific articles. Although the papers look sophisticated and seemingly flawless, expert readers may identify semantic inaccuracies and errors upon closer inspection. We highlight the need for increased vigilance and better detection methods to combat the potential misuse of AI in scientific research. At the same time, it is important to recognize the potential benefits of using AI language models in genuine scientific writing and research, such as manuscript preparation and language editing.
- MeSH
- algoritmy * MeSH
- analýza dat MeSH
- jazyk (prostředek komunikace) MeSH
- lidé MeSH
- sémantika MeSH
- umělá inteligence * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem 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.
The study is a follow-up to three published anglophone researches examining the relation between the use of linguistic categories and personality characteristics as outlined in the Big Five model, with the purpose of replicating these and elaborating for the Czech language. The comparative research study in Czech focuses on analysis of both grammatical and semantic variables in six types of text (written and oral), produced by N = 200 participants. Within the study, there were six confirmed relations, however, these appear only in certain types of text. The results show not only an essential role of the text register, but they also allow us to evaluate the universality of findings of studies in English in comparison with other, especially Slavic, languages.
- MeSH
- jazyk (prostředek komunikace) * MeSH
- lidé MeSH
- lingvistika * MeSH
- osobnost MeSH
- sémantika MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- Geografické názvy
- Česká republika MeSH
BACKGROUND: Ubiquitin ligases (Ub-ligases) are essential intracellular enzymes responsible for the regulation of proteome homeostasis, signaling pathway crosstalk, cell differentiation and stress responses. Individual Ub-ligases exhibit their unique functions based on the nature of their substrates. They create a complex regulatory network with alternative and feedback pathways to maintain cell homeostasis, being thus important players in many physiological and pathological conditions. However, the functional classification of Ub-ligases needs to be revised and extended. METHODS: In the current study, we used a novel semantic biclustering technique for expression profiling of Ub-ligases and ubiquitination-related genes in the murine gastrointestinal tract (GIT). We accommodated a general framework of the algorithm for finding tissue-specific gene expression clusters in GIT. In order to test identified clusters in a biological system, we used a model of epithelial regeneration. For this purpose, a dextran sulfate sodium (DSS) mouse model, following with in situ hybridization, was used to expose genes with possible compensatory features. To determine cell-type specific distribution of Ub-ligases and ubiquitination-related genes, principal component analysis (PCA) and Uniform Manifold Approximation and Projection technique (UMAP) were used to analyze the Tabula Muris scRNA-seq data of murine colon followed by comparison with our clustering results. RESULTS: Our established clustering protocol, that incorporates the semantic biclustering algorithm, demonstrated the potential to reveal interesting expression patterns. In this manner, we statistically defined gene clusters consisting of the same genes involved in distinct regulatory pathways vs distinct genes playing roles in functionally similar signaling pathways. This allowed us to uncover the potentially redundant features of GIT-specific Ub-ligases and ubiquitination-related genes. Testing the statistically obtained results on the mouse model showed that genes clustered to the same ontology group simultaneously alter their expression pattern after induced epithelial damage, illustrating their complementary role during tissue regeneration. CONCLUSIONS: An optimized semantic clustering protocol demonstrates the potential to reveal a readable and unique pattern in the expression profiling of GIT-specific Ub-ligases, exposing ontologically relevant gene clusters with potentially redundant features. This extends our knowledge of ontological relationships among Ub-ligases and ubiquitination-related genes, providing an alternative and more functional gene classification. In a similar way, semantic cluster analysis could be used for studding of other enzyme families, tissues and systems.
- MeSH
- gastrointestinální trakt metabolismus MeSH
- lidé MeSH
- myši MeSH
- sémantika * MeSH
- shluková analýza MeSH
- ubikvitin genetika metabolismus MeSH
- ubikvitinligasy * genetika MeSH
- zvířata MeSH
- Check Tag
- lidé MeSH
- myši MeSH
- zvířata MeSH
- Publikační typ
- časopisecké články MeSH
This paper deals with a developed information system called a Personal Genetic Card (PGC). The system aims to integrate the known clinical knowledge (interpretations and recommendations) linked to genetic information with the analysis results of a patient. Genetic information has an increasing influence on the clinical decision of physicians as well as other medical and health services. All these services need to connect the genetic profile with the phenotypes such as drug metabolization, drug toxicity, drug dosing, or intolerance of some substances. It still applies that the best way to represent data of medical records is a structured form of record. Many approaches can be used to define the structure (syntax) of the record and the content (semantics) of the record and to exchange data in forms of various standards and terminologies. Moreover, the genetic analysis field has its terminology databases for representing genetic information (e.g. HGNC, NCBI). The next step is to connect the genetic analysis results with c clinical knowledge (interpretation, recommendation). This step is crucial because the genetic analysis results have clinical benefits if we can assign them to some valid clinical knowledge. And the best final result is when we can make a better recommendation based on the genetic results and clinical knowledge. Genetic knowledge databases (e.g. PharmGKB, SNPedia, ClinVar) contain many interpretations and even recommendations for genetic analysis results based on different purposes. This situation is appropriate for developing the PGC system that takes inspiration from case-based reasoning in purpose to allow integration of the assumptions and knowledge about phenotypes and the real genetic analysis results in the structured form.
- MeSH
- chorobopisy - počítačové systémy * MeSH
- fenotyp MeSH
- genetické testování * MeSH
- sémantika MeSH
- Publikační typ
- časopisecké články MeSH
Automated sentiment analysis is becoming increasingly recognized due to the growing importance of social media and e-commerce platform review websites. Deep neural networks outperform traditional lexicon-based and machine learning methods by effectively exploiting contextual word embeddings to generate dense document representation. However, this representation model is not fully adequate to capture topical semantics and the sentiment polarity of words. To overcome these problems, a novel sentiment analysis model is proposed that utilizes richer document representations of word-emotion associations and topic models, which is the main computational novelty of this study. The sentiment analysis model integrates word embeddings with lexicon-based sentiment and emotion indicators, including negations and emoticons, and to further improve its performance, a topic modeling component is utilized together with a bag-of-words model based on a supervised term weighting scheme. The effectiveness of the proposed model is evaluated using large datasets of Amazon product reviews and hotel reviews. Experimental results prove that the proposed document representation is valid for the sentiment analysis of product and hotel reviews, irrespective of their class imbalance. The results also show that the proposed model improves on existing machine learning methods.
- MeSH
- algoritmy * MeSH
- emoce MeSH
- lidé MeSH
- neuronové sítě (počítačové) * MeSH
- sémantika MeSH
- strojové učení MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
The wide-spread use of Common Data Models and information models in biomedical informatics encourages assumptions that those models could provide the entirety of what is needed for knowledge representation purposes. Based on the lack of computable semantics in frequently used Common Data Models, there appears to be a gap between knowledge representation requirements and these models. In this use-case oriented approach, we explore how a system-theoretic, architecture-centric, ontology-based methodology can help to better understand this gap. We show how using the Generic Component Model helps to analyze the data management system in a way that allows accounting for data management procedures inside the system and knowledge representation of the real world at the same time.
- MeSH
- bio-ontologie * MeSH
- data management MeSH
- sémantika * MeSH
- Publikační typ
- časopisecké články MeSH
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.
