TzanckNet: a convolutional neural network to identify cells in the cytology of erosive-vesiculobullous diseases

Noyan, Mehmet Alican; Durdu, Murat; Eskiocak, Ali Haydar

doi:10.1038/s41598-020-75546-z

Cited by 17 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thirdly, two images from the same patient might look very different [ 16 ]. Since molecular testing is rarely used for HHV1–3 infections, even in immunocompromised patients, availability is limited [ 14 ].…”

Section: Discussionmentioning

confidence: 99%

“…Since molecular testing is rarely used for HHV1–3 infections, even in immunocompromised patients, availability is limited [ 14 ]. Here, VZVHHV1–3 reactivation was firstly used in the diagnosis of exclusion, secondly, it was indicated by the acantholytic and multinucleated giant cells in the image (Tzanck test) [ 13 , 16 ]. Due to the rapid turnaround time and correlation with clinical symptoms, serologic methods are preferable for VZV1-3 in contrast to viral isolation [ 17 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Two Waves of Specific B Cell Memory Immunoreconstruction Observed in Anti-HHV1–3 IgG Kinetics after Hematopoietic Stem Cell Transplantation

Zdziarski,

Gamian

2024

Biomedicines

View full text Add to dashboard Cite

Background: Humoral memory and specific antibody levels depend on the kind of antigen and individual immunofactors. The presence of IgM antibodies or a fourfold rise in specific IgG levels are generally accepted as diagnostic factors in the serology of acute viral infections. This basic model is not adequate for the herpes virome, especially after hematopoietic stem cell transplantation (HSCT), due to continuous, usually multifocal antigenic stimulation, various donor serostatuses, immunosuppression, and individual immunoreconstitution. Methods: A case–control study was conducted to identify active infection cases of human herpesvirus (HHV) (from 300 diagnosed immunocompromised patients) and to evaluate historically associated humoral factors to look at outcomes. We considered only the data of patients with meticulous differential diagnosis to exclude other causes, and thereby to observe pathways and temporal relationships, not the statistical ones usually collected in cohorts. Despite the small number, such data collection and analysis methods avoid a number of biases and indicate cause and effect. Results: In this observational study, a retrospective analysis of data from 300 patients with clinical diagnosis of herpes simplex virus (HSV) and varicella zoster virus (VZV) reactivation showed a number of biases. Two well-differentiated cases (confirmed by a Tzanck test) with various diseases and conditioning evolutions of immune parameters showed an interesting pathway. Exponential decreases in specific IgGs after HSCT preceded virus replication were observed, with a cytopathic effect (shingles, VZV encephalitis and HSV-induced mucositis). The minima (lowest IgG levels) before herpesvirus reactivation were 234.23 mIU/mL and 94 RU/mL for VZV and HSV, respectively. This coincided with a low CD4 titer, but without other infectious processes. Other immune response parameters such as Treg, cytotoxic T cells, and complement and total IgG level were the same as they were before the transplant procedure. Interestingly, a second wave of immunoreconstitution with an anamnestic antibody response was not always observed. It coincided with prolonged herpes viral infection. A patient with lymphocyte depletion in conditioning showed an earlier second wave of immunoreconstitution (6th vs. 14th month). Conclusions: As is typical for infancy, the kinetics of the IgG level is unique after HSCT (the decline phase is first). Host microbiome factors (e.g., HHV1–3-serostatus) should be taken into account to predict risk of non-relapse mortality and survival after HSCT. The levels of specific antibodies help in predicting prognoses and improve disease management. A lack of differentiation and the confusing bias of the assessor (i.e., observer selection bias) are the main obstacles in statistical HHV1–3 research. Such time-lapse case studies may be the first to build evidence of a pathway and an association between immune parameters and HHV disease.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Two Waves of Specific B Cell Memory Immunoreconstruction Observed in Anti-HHV1–3 IgG Kinetics after Hematopoietic Stem Cell Transplantation

Zdziarski,

Gamian

2024

Biomedicines

View full text Add to dashboard Cite

show abstract

“…In recent years, machine learning methods have been gradually integrated into various fields of medicine to improve the accuracy of diagnosis and prognosis prediction. Examples include the evaluation of imaging or histopathological studies (Noyan et al., 2020) and the prediction of survival (Wongvibulsin et al., 2019) or postoperative surgical complications (Chan et al., 2006). Machine learning can be defined as the discipline that focuses on improving the ability of computers to process more data.…”

Section: Introductionmentioning

confidence: 99%

Establishment of a model to predict mortality after decompression craniotomy for traumatic brain injury

Wu,

Zhang,

Chen

et al. 2024

Brain and Behavior

View full text Add to dashboard Cite

BackgroundThe mortality rate of patients with traumatic brain injury (TBI) is still high even while undergoing decompressive craniectomy (DC), and the expensive treatment costs bring huge economic burden to the families of patients.ObjectiveThe aim of this study was to identify preoperative indicators that influence patient outcomes and to develop a risk model for predicting patient mortality by a retrospective analysis of TBI patients undergoing DC.MethodsA total of 288 TBI patients treated with DC, admitted to the First Affiliated Hospital of Shantou University Medical School from August 2015 to April 2021, were used for univariate and multivariate logistic regression analysis to determine the risk factors for death after DC in TBI patients. We also built a risk model for the identified risk factors and conducted internal verification and model evaluation.ResultsUnivariate and multivariate logistic regression analysis identified four risk factors: Glasgow Coma Scale, age, activated partial thrombin time, and mean CT value of the superior sagittal sinus. These risk factors can be obtained before DC. In addition, we also developed a 3‐month mortality risk model and conducted a bootstrap 1000 resampling internal validation, with C‐indices of 0.852 and 0.845, respectively.ConclusionsWe developed a risk model that has clinical significance for the early identification of patients who will still die after DC. Interestingly, we also identified a new early risk factor for TBI patients after DC, that is, preoperative mean CT value of the superior sagittal sinus (p < .05).

show abstract

“…Most of these illnesses are long-lasting, and patients experience symptoms, including desquamation; however, some may be contagious. It is necessary to comprehend the immunopathologic character of the lesion to administer effective treatment [ 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence’s Use in the Diagnosis of Mouth Ulcers: A Systematic Review

Tiwari,

Gupta,

Singla

et al. 2023

Cureus

View full text Add to dashboard Cite

Artificial intelligence (AI) has been cited as being helpful in the diagnosis of diseases, the prediction of prognoses, and the development of patient-specific therapeutic strategies. AI can help dentists, in particular, when they need to make important judgments quickly. It can eliminate human mistakes in making decisions, resulting in superior and consistent medical treatment while lowering the workload on dentists. The existing studies relevant to the study and application of AI in the diagnosis of various forms of mouth ulcers are reviewed in this work. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards were followed in the preparation of the review. There were no rule violations, with the significant exception of the use of a better search method that led to more accurate findings. Using search terms mainly such as AI, oral health, oral ulcers, oral herpes simplex, oral lichen planus, pemphigus vulgaris, recurrent aphthous ulcer (RAU), oral cancer, premalignant and malignant disorders, etc., a comprehensive search was carried out in the reliable sources of literature, namely PubMed, Scopus, Embase, Web of Science, Ovid, Global Health, and PsycINFO. For all papers, exhaustive searches were done using inclusion criteria as well as exclusion criteria between June 28, 2018, and June 28, 2023. An AI framework for the automatic categorization of oral ulcers from oral clinical photographs was developed by the authors, and it performed satisfactorily. The newly designed AI model works better than the current convolutional neural network image categorization techniques and shows a fair level of precision in the classification of oral ulcers. However, despite being useful for identifying oral ulcers, the suggested technique needs a broader set of data for validation and training purposes before being used in clinical settings. Automated OCSCC identification using a deep learning-based technique is a quick, harmless, affordable, and practical approach to evaluating the effectiveness of cancer treatment. The categorization and identification of RAU lesions through the use of non-intrusive oral pictures using the previously developed ResNet50 and YOLOV algorithms demonstrated better accuracy as well as adequate potential for the future, which could be helpful in clinical practice. Moreover, the most reliable projections for the likelihood of the presence or absence of RAU were made by the optimized neural network. The authors also discovered variables associated with RAU that might be used as input information to build artificial neural networks that anticipate RAU.

show abstract

TzanckNet: a convolutional neural network to identify cells in the cytology of erosive-vesiculobullous diseases

Cited by 17 publications

References 38 publications

Two Waves of Specific B Cell Memory Immunoreconstruction Observed in Anti-HHV1–3 IgG Kinetics after Hematopoietic Stem Cell Transplantation

Two Waves of Specific B Cell Memory Immunoreconstruction Observed in Anti-HHV1–3 IgG Kinetics after Hematopoietic Stem Cell Transplantation

Establishment of a model to predict mortality after decompression craniotomy for traumatic brain injury

Artificial Intelligence’s Use in the Diagnosis of Mouth Ulcers: A Systematic Review

Contact Info

Product

Resources

About