S postupující digitalizací patologie se do popředí zájmu dostávají i aplikace metod strojového učení a umělé inteligence. Výzkum a vývoj v této oblasti je velmi rychlý, ale aplikace učících systémů v klinické praxi stále zaostávají. Cílem tohoto textu je přiblížit proces tvorby a nasazení učících systémů v digitální patologii. Začneme popisem základních vlastností dat produkovaných v rámci digitální patologie. Konkrétně pojednáme o skenerech a skenování vzorků, o ukládání a přenosu dat, o kontrole jejich kvality a přípravě pro zpracování pomocí učících systémů, zejména o anotacích. Naším cílem je prezentovat aktuální přístupy k řešení technických problémů a zároveň upozornit na úskalí, na která lze narazit při zpracování dat z digitální patologie. V první části také naznačíme, jak vypadají aktuální softwarová řešení pro prohlížení naskenovaných vzorků a implementace diagnostických postupů zahrnujících učící systémy. Ve druhé části textu popíšeme obvyklé úlohy digitální patologie a naznačíme obvyklé přístupy k jejich řešení. V této části zejména vysvětlíme, jak je nutné modifikovat standardní metody strojového učení pro zpracování velkých skenů a pojednáme o konkrétních aplikacích v diagnostice. Na závěr textu poskytneme rychlý náhled dalšího možného vývoje učících systémů v digitální patologii. Zejména ilustrujeme podstatu přechodu na velké základní modely a naznačíme problematiku virtuálního barvení vzorků. Doufáme, že tento text přispěje k lepší orientaci v rapidně se vyvíjející oblasti strojového učení v digitální patologii a tím přispěje k rychlejší adopci učících metod v této oblasti.
With the advancing digitalization of pathology, the application of machine learning and artificial intelligence methods is becoming increasingly important. Research and development in this field are progressing rapidly, but the clinical implementation of learning systems still lags behind. The aim of this text is to provide an overview of the process of developing and deploying learning systems in digital pathology. We begin by describing the fundamental characteristics of data produced in digital pathology. Specifically, we discuss scanners and sample scanning, data storage and transmission, quality control, and preparation for processing by learning systems, with a particular focus on annotations. Our goal is to present current approaches to addressing technical challenges while also highlighting potential pitfalls in processing digital pathology data. In the first part of the text, we also outline existing software solutions for viewing scanned samples and implementing diagnostic procedures that incorporate learning systems. In the second part of the text, we describe common tasks in digital pathology and outline typical approaches to solving them. Here, we explain the necessary modifications to standard machine learning methods for processing large scans and discuss specific diagnostic applications. Finally, we provide a brief overview of the potential future development of learning systems in digital pathology. We illustrate the transition to large foundational models and introduce the topic of virtual staining of samples. We hope that this text will contribute to a better understanding of the rapidly evolving field of machine learning in digital pathology and, in turn, facilitate the faster adoption of learning-based methods in this domain.
Objective.Accurate localization of the epileptogenic zone (EZ) is crucial for epilepsy surgery, but the class imbalance of epileptogenic vs. non-epileptogenic electrode contacts in intracranial electroencephalography (iEEG) data poses significant challenges for automatic localization methods. This review evaluates methodologies for handling the class imbalance in EZ localization studies that use machine learning (ML).Approach.We systematically reviewed studies employing ML to localize the EZ from iEEG data, focusing on strategies for addressing class imbalance in data handling, algorithm design, and evaluation.Results.Out of 2,128 screened studies, 35 fulfilled the inclusion criteria. Across the studies, the iEEG contacts annotated as epileptogenic prior to automatic localization constituted a median of 18.34% of all contacts. However, many of these studies did not adequately address the class imbalance problem. Techniques such as data resampling and cost-sensitive learning were used to mitigate the class imbalance problem, but the chosen evaluation metrics often failed to account for it.Significance.Class imbalance significantly impacts the reliability of EZ localization models. More comprehensive management and innovative approaches are needed to enhance the robustness and clinical utility of these models. Addressing class imbalance in ML models for EZ localization will improve both the predictive performance and reliability of these models.
Achieving a reliable and accurate biomedical image segmentation is a long-standing problem. In order to train or adapt the segmentation methods or measure their performance, reference segmentation masks are required. Usually gold-standard annotations, i.e. human-origin reference annotations, are used as reference although they are very hard to obtain. The increasing size of the acquired image data, large dimensionality such as 3D or 3D + time, limited human expert time, and annotator variability, typically result in sparsely annotated gold-standard datasets. Reliable silver-standard annotations, i.e. computer-origin reference annotations, are needed to provide dense segmentation annotations by fusing multiple computer-origin segmentation results. The produced dense silver-standard annotations can then be either used as reference annotations directly, or converted into gold-standard ones with much lighter manual curation, which saves experts' time significantly. We propose a novel full-resolution multi-rater fusion convolutional neural network (CNN) architecture for biomedical image segmentation masks, called DeepFuse, which lacks any down-sampling layers. Staying everywhere at the full resolution enables DeepFuse to fully benefit from the enormous feature extraction capabilities of CNNs. DeepFuse outperforms the popular and commonly used fusion methods, STAPLE, SIMPLE and other majority-voting-based approaches with statistical significance on a wide range of benchmark datasets as demonstrated on examples of a challenging task of 2D and 3D cell and cell nuclei instance segmentation for a wide range of microscopy modalities, magnifications, cell shapes and densities. A remarkable feature of the proposed method is that it can apply specialized post-processing to the segmentation masks of each rater separately and recover under-segmented object parts during the refinement phase even if the majority of inputs vote otherwise. Thus, DeepFuse takes a big step towards obtaining fast and reliable computer-origin segmentation annotations for biomedical images.
- MeSH
- Humans MeSH
- Neural Networks, Computer * MeSH
- Image Processing, Computer-Assisted * methods MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
IMPORTANCE: Understanding the pathogenic mechanisms of Fuchs endothelial corneal dystrophy (FECD) could contribute to developing gene-targeted therapies. OBJECTIVE: To investigate associations between demographic data and age at first keratoplasty in a genetically refined FECD cohort. DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study recruited 894 individuals with FECD at Moorfields Eye Hospital (London) and General University Hospital (Prague) from September 2009 to July 2023. Ancestry was inferred from genome-wide single nucleotide polymorphism array data. CTG18.1 status was determined by short tandem repeat and/or triplet-primed polymerase chain reaction. One or more expanded alleles (≥50 repeats) were classified as expansion-positive (Exp+). Expansion-negative (Exp-) cases were exome sequenced. MAIN OUTCOMES AND MEASURES: Association between variants in FECD-associated genes, demographic data, and age at first keratoplasty. RESULTS: Within the total cohort (n = 894), 77.3% of patients were Exp+. Most European (668 of 829 [80.6%]) and South Asian (14 of 22 [63.6%]) patients were Exp+. The percentage of female patients was higher (151 [74.4%]) in the Exp- cohort compared to the Exp+ cohort (395 [57.2%]; difference, 17.2%; 95% CI, 10.1%-24.3%; P < .001). The median (IQR) age at first keratoplasty of the Exp + patients (68.2 years [63.2-73.6]) was older than the Exp- patients (61.3 years [52.6-70.4]; difference, 6.5 years; 95% CI, 3.4-9.7; P < .001). The CTG18.1 repeat length of the largest expanded allele within the Exp+ group was inversely correlated with the age at first keratoplasty (β, -0.087; 95% CI, -0.162 to -0.012; P = .02). The ratio of biallelic to monoallelic expanded alleles was higher in the FECD cohort (1:14) compared to an unaffected control group (1:94; P < .001), indicating that 2 Exp+ alleles were associated with increased disease penetrance compared with 1 expansion. Potentially pathogenic variants (minor allele frequency, <0.01; combined annotation dependent depletion, >15) were only identified in FECD-associated genes in 13 Exp- individuals (10.1%). CONCLUSIONS AND RELEVANCE: In this multicenter cohort study among individuals with FECD, CTG18.1 expansions were present in most European and South Asian patients, while CTG18.1 repeat length and zygosity status were associated with modifications in disease severity and penetrance. Known disease-associated genes accounted for only a minority of Exp- cases, with unknown risk factors associated with disease in the rest of this subgroup. These data may have implications for future FECD gene-targeted therapy development.
- MeSH
- Genome-Wide Association Study MeSH
- Adult MeSH
- Fuchs' Endothelial Dystrophy * genetics surgery epidemiology diagnosis MeSH
- Genetic Predisposition to Disease * MeSH
- Polymorphism, Single Nucleotide * MeSH
- Middle Aged MeSH
- Humans MeSH
- Retrospective Studies MeSH
- Risk Factors MeSH
- Aged, 80 and over MeSH
- Aged MeSH
- Severity of Illness Index MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged, 80 and over MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Multicenter Study MeSH
- Observational Study MeSH
Antibiotic resistance is one of the biggest threats to global health. Fungal endophytes are important sources of active natural products with antimicrobial potential. The purpose of this study was to characterize the endophytes coexisting with Helichrysum oocephalum, evaluate their antimicrobial activities, and annotate the endophytes metabolites. Six fungal species, including Fusarium avenaceum and Fusarium tricinctum, were identified. Endophytes were cultured, and their metabolites were extracted. The antimicrobial effects of the extracts were tested against Staphylococcus aureus, Bacillus cereus, Staphylococcus epidermidis, Pseudomonas aeruginosa, Escherichia coli, and Candida albicans. In addition, anti-biofilm effects of the extracts were examined against P. aeruginosa and S. epidermidis. The metabolites in the most active extract were annotated on the basis of the LC-ESI-QToF-MS/MS data. In anti-biofilm studies, F. avenaceum extract was effective in destroying and inhibiting the biofilm formation of S. epidermidis. LC-MS analysis showed that most of the identified compounds in the active extracts were enniatins (cyclic hexadepsipeptides). However, apicidin derivatives were also annotated. Our results revealed that these endophytes, especially Fusarium species, have antimicrobial activity against S. aureus, B. cereus, and C. albicans and anti-biofilm activity against S. epidermidis. According to the literature, the observed antimicrobial activity can be attributed to the enniatins. However, further phytochemical and pharmacological studies are necessary in this regard.
- MeSH
- Anti-Bacterial Agents * pharmacology isolation & purification chemistry MeSH
- Antifungal Agents * pharmacology isolation & purification chemistry MeSH
- Anti-Infective Agents * pharmacology isolation & purification chemistry MeSH
- Bacillus cereus drug effects MeSH
- Biofilms drug effects MeSH
- Candida albicans drug effects MeSH
- Endophytes * chemistry metabolism isolation & purification MeSH
- Escherichia coli drug effects MeSH
- Fusarium * chemistry metabolism MeSH
- Microbial Sensitivity Tests MeSH
- Pseudomonas aeruginosa drug effects MeSH
- Staphylococcus aureus drug effects MeSH
- Staphylococcus epidermidis drug effects MeSH
- Tandem Mass Spectrometry MeSH
- Publication type
- Journal Article MeSH
OBJECTIVES: Artificial Intelligence (AI), particularly deep learning, has significantly impacted healthcare, including dentistry, by improving diagnostics, treatment planning, and prognosis prediction. This systematic mapping review explores the current applications of deep learning in dentistry, offering a comprehensive overview of trends, models, and their clinical significance. MATERIALS AND METHODS: Following a structured methodology, relevant studies published from January 2012 to September 2023 were identified through database searches in PubMed, Scopus, and Embase. Key data, including clinical purpose, deep learning tasks, model architectures, and data modalities, were extracted for qualitative synthesis. RESULTS: From 21,242 screened studies, 1,007 were included. Of these, 63.5% targeted diagnostic tasks, primarily with convolutional neural networks (CNNs). Classification (43.7%) and segmentation (22.9%) were the main methods, and imaging data-such as cone-beam computed tomography and orthopantomograms-were used in 84.4% of cases. Most studies (95.2%) applied fully supervised learning, emphasizing the need for annotated data. Pathology (21.5%), radiology (17.5%), and orthodontics (10.2%) were prominent fields, with 24.9% of studies relating to more than one specialty. CONCLUSION: This review explores the advancements in deep learning in dentistry, particulary for diagnostics, and identifies areas for further improvement. While CNNs have been used successfully, it is essential to explore emerging model architectures, learning approaches, and ways to obtain diverse and reliable data. Furthermore, fostering trust among all stakeholders by advancing explainable AI and addressing ethical considerations is crucial for transitioning AI from research to clinical practice. CLINICAL RELEVANCE: This review offers a comprehensive overview of a decade of deep learning in dentistry, showcasing its significant growth in recent years. By mapping its key applications and identifying research trends, it provides a valuable guide for future studies and highlights emerging opportunities for advancing AI-driven dental care.
- MeSH
- Deep Learning * MeSH
- Humans MeSH
- Dentistry * MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Review MeSH
- Systematic Review MeSH
OBJECTIVE: Idiopathic inflammatory myopathies (IIMs, myositis) are rare systemic autoimmune disorders that lead to muscle inflammation, weakness, and extramuscular manifestations, with a strong genetic component influencing disease development and progression. Previous genome-wide association studies identified loci associated with IIMs. In this study, we imputed data from two prior genome-wide myositis studies and analyzed the largest myositis data set to date to identify novel risk loci and susceptibility genes associated with IIMs and its clinical subtypes. METHODS: We performed association analyses on 14,903 individuals (3,206 patients and 11,697 controls) with genotypes and imputed data from the Trans-Omics for Precision Medicine reference panel. Fine-mapping and expression quantitative trait locus colocalization analyses in myositis-relevant tissues indicated potential causal variants. Functional annotation and network analyses using the random walk with restart (RWR) algorithm explored underlying genetic networks and drug repurposing opportunities. RESULTS: Our analyses identified novel risk loci and susceptibility genes, such as FCRLA, NFKB1, IRF4, DCAKD, and ATXN2 in overall IIMs; NEMP2 in polymyositis; ACBC11 in dermatomyositis; and PSD3 in myositis with anti-histidyl-transfer RNA synthetase autoantibodies (anti-Jo-1). We also characterized effects of HLA region variants and the role of C4. Colocalization analyses suggested putative causal variants in DCAKD in skin and muscle, HCP5 in lung, and IRF4 in Epstein-Barr virus (EBV)-transformed lymphocytes, lung, and whole blood. RWR further prioritized additional candidate genes, including APP, CD74, CIITA, NR1H4, and TXNIP, for future investigation. CONCLUSION: Our study uncovers novel genetic regions contributing to IIMs, advancing our understanding of myositis pathogenesis and offering new insights for future research.
BACKGROUND: Ticks, hematophagous Acari, pose a significant threat by transmitting various pathogens to their vertebrate hosts during feeding. Despite advances in tick genomics, high-quality genomes were lacking until recently, particularly in the genus Ixodes, which includes the main vectors of Lyme disease. RESULTS: Here, we present the genome sequences of four tick species, derived from a single female individual, with a particular focus on the European species Ixodes ricinus, achieving a chromosome-level assembly. Additionally, draft assemblies were generated for the three other Ixodes species, I. persulcatus, I. pacificus, and I. hexagonus. The quality of the four genomes and extensive annotation of several important gene families have allowed us to study the evolution of gene repertoires at the level of the genus Ixodes and of the tick group. We have determined gene families that have undergone major amplifications during the evolution of ticks, while an expression atlas obtained for I. ricinus reveals striking patterns of specialization both between and within gene families. Notably, several gene family amplifications are associated with a proliferation of single-exon genes-most strikingly for fatty acid elongases and sulfotransferases. CONCLUSIONS: The integration of our data with existing genomes establishes a solid framework for the study of gene evolution, improving our understanding of tick biology. In addition, our work lays the foundations for applied research and innovative control targeting these organisms.
Rare diseases may affect the quality of life of patients and be life-threatening. Therapeutic opportunities are often limited, in part because of the lack of understanding of the molecular mechanisms underlying these diseases. This can be ascribed to the low prevalence of rare diseases and therefore the lower sample sizes available for research. A way to overcome this is to integrate experimental rare disease data with prior knowledge using network-based methods. Taking this one step further, we hypothesized that combining and analyzing the results from multiple network-based methods could provide data-driven hypotheses of pathogenic mechanisms from multiple perspectives.We analyzed a Huntington's disease transcriptomics dataset using six network-based methods in a collaborative way. These methods either inherently reported enriched annotation terms or their results were fed into enrichment analyses. The resulting significantly enriched Reactome pathways were then summarized using the ontological hierarchy which allowed the integration and interpretation of outputs from multiple methods. Among the resulting enriched pathways, there are pathways that have been shown previously to be involved in Huntington's disease and pathways whose direct contribution to disease pathogenesis remains unclear and requires further investigation.In summary, our study shows that collaborative network analysis approaches are well-suited to study rare diseases, as they provide hypotheses for pathogenic mechanisms from multiple perspectives. Applying different methods to the same case study can uncover different disease mechanisms that would not be apparent with the application of a single method.
Specialized or secondary metabolites are small molecules of biological origin, often showing potent biological activities with applications in agriculture, engineering and medicine. Usually, the biosynthesis of these natural products is governed by sets of co-regulated and physically clustered genes known as biosynthetic gene clusters (BGCs). To share information about BGCs in a standardized and machine-readable way, the Minimum Information about a Biosynthetic Gene cluster (MIBiG) data standard and repository was initiated in 2015. Since its conception, MIBiG has been regularly updated to expand data coverage and remain up to date with innovations in natural product research. Here, we describe MIBiG version 4.0, an extensive update to the data repository and the underlying data standard. In a massive community annotation effort, 267 contributors performed 8304 edits, creating 557 new entries and modifying 590 existing entries, resulting in a new total of 3059 curated entries in MIBiG. Particular attention was paid to ensuring high data quality, with automated data validation using a newly developed custom submission portal prototype, paired with a novel peer-reviewing model. MIBiG 4.0 also takes steps towards a rolling release model and a broader involvement of the scientific community. MIBiG 4.0 is accessible online at https://mibig.secondarymetabolites.org/.
