Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 15 de 15
Filter
1.
J Oral Pathol Med ; 2024 Jun 04.
Article in English | MEDLINE | ID: mdl-38831737

ABSTRACT

BACKGROUND: Neural tumors are difficult to distinguish based solely on cellularity and often require immunohistochemical staining to aid in identifying the cell lineage. This article investigates the potential of a Convolutional Neural Network for the histopathological classification of the three most prevalent benign neural tumor types: neurofibroma, perineurioma, and schwannoma. METHODS: A model was developed, trained, and evaluated for classification using the ResNet-50 architecture, with a database of 30 whole-slide images stained in hematoxylin and eosin (106, 782 patches were generated from and divided among the training, validation, and testing subsets, with strategies to avoid data leakage). RESULTS: The model achieved an accuracy of 70% (64% normalized), and showed satisfactory results for differentiating two of the three classes, reaching approximately 97% and 77% as true positives for neurofibroma and schwannoma classes, respectively, and only 7% for perineurioma class. The AUROC curves for neurofibroma and schwannoma classes was 0.83%, and 0.74% for perineurioma. However, the specificity rate for the perineurioma class was greater (83%) than in the other two classes (neurofibroma with 61%, and schwannoma with 60%). CONCLUSION: This investigation demonstrated significant potential for proficient performance with a limitation regarding the perineurioma class (the limited feature variability observed contributed to a lower performance).

2.
Head Neck Pathol ; 18(1): 45, 2024 Jun 09.
Article in English | MEDLINE | ID: mdl-38853193

ABSTRACT

BACKGROUND: Salivary gland cystadenoma (SGCA) is a rare benign tumor that predominantly occurs in the parotid gland. SGCAs affecting the minor salivary glands are uncommon and often resemble, clinically and histopathologically, other salivary gland lesions. METHODS: This study aimed to describe a series of four cases of SGCA affecting intraoral sites and performed a literature review of well-reported SGCA published in the English-language literature. RESULTS: SGCA cases included in this series were diagnosed in the buccal mucosa, lip, and hard palate of female patients aged between 19 and 78 years. All cases underwent excisional biopsy and were histologically characterized by a multicystic growth with variable degrees of capsule formation and were lined by several types of epithelium, including some cell types that are infrequently reported in SGCA. In some cases, a small collection of lymphocytes was observed adjacent to cystic formations. All SGCA were positive for periodic acid-Schiff, and immunohistochemical reactions were positive for CK7 and p63. The follow-up time ranged widely from 3 to 53 months, and to date, no recurrence has been observed. CONCLUSION: The literature review revealed a total of 33 published studies accounting for 55 SGCA cases.


Subject(s)
Cystadenoma , Salivary Gland Neoplasms , Humans , Female , Salivary Gland Neoplasms/pathology , Adult , Middle Aged , Cystadenoma/pathology , Aged , Young Adult
3.
J Oral Pathol Med ; 2024 May 28.
Article in English | MEDLINE | ID: mdl-38807455

ABSTRACT

BACKGROUND: The purpose of this systematic review (SR) is to gather evidence on the use of machine learning (ML) models in the diagnosis of intraosseous lesions in gnathic bones and to analyze the reliability, impact, and usefulness of such models. This SR was performed in accordance with the PRISMA 2022 guidelines and was registered in the PROSPERO database (CRD42022379298). METHODS: The acronym PICOS was used to structure the inquiry-focused review question "Is Artificial Intelligence reliable for the diagnosis of intraosseous lesions in gnathic bones?" The literature search was conducted in various electronic databases, including PubMed, Embase, Scopus, Cochrane Library, Web of Science, Lilacs, IEEE Xplore, and Gray Literature (Google Scholar and ProQuest). Risk of bias assessment was performed using PROBAST, and the results were synthesized by considering the task and sampling strategy of the dataset. RESULTS: Twenty-six studies were included (21 146 radiographic images). Ameloblastomas, odontogenic keratocysts, dentigerous cysts, and periapical cysts were the most frequently investigated lesions. According to TRIPOD, most studies were classified as type 2 (randomly divided). The F1 score was presented in only 13 studies, which provided the metrics for 20 trials, with a mean of 0.71 (±0.25). CONCLUSION: There is no conclusive evidence to support the usefulness of ML-based models in the detection, segmentation, and classification of intraosseous lesions in gnathic bones for routine clinical application. The lack of detail about data sampling, the lack of a comprehensive set of metrics for training and validation, and the absence of external testing limit experiments and hinder proper evaluation of model performance.

4.
J Oral Pathol Med ; 52(10): 988-995, 2023 Nov.
Article in English | MEDLINE | ID: mdl-37712132

ABSTRACT

BACKGROUND: Odontogenic tumors (OT) are composed of heterogeneous lesions, which can be benign or malignant, with different behavior and histology. Within this classification, ameloblastoma and ameloblastic carcinoma (AC) represent a diagnostic challenge in daily histopathological practice due to their similar characteristics and the limitations that incisional biopsies represent. From these premises, we wanted to test the usefulness of models based on artificial intelligence (AI) in the field of oral and maxillofacial pathology for differential diagnosis. The main advantages of integrating Machine Learning (ML) with microscopic and radiographic imaging is the ability to significantly reduce intra-and inter observer variability and improve diagnostic objectivity and reproducibility. METHODS: Thirty Digitized slides were collected from different diagnostic centers of oral pathology in Brazil. After performing manual annotation in the region of interest, the images were segmented and fragmented into small patches. In the supervised learning methodology for image classification, three models (ResNet50, DenseNet, and VGG16) were focus of investigation to provide the probability of an image being classified as class0 (i.e., ameloblastoma) or class1 (i.e., Ameloblastic carcinoma). RESULTS: The training and validation metrics did not show convergence, characterizing overfitting. However, the test results were satisfactory, with an average for ResNet50 of 0.75, 0.71, 0.84, 0.65, and 0.77 for accuracy, precision, sensitivity, specificity, and F1-score, respectively. CONCLUSIONS: The models demonstrated a strong potential of learning, but lack of generalization ability. The models learn fast, reaching a training accuracy of 98%. The evaluation process showed instability in validation; however, acceptable performance in the testing process, which may be due to the small data set. This first investigation opens an opportunity for expanding collaboration to incorporate more complementary data; as well as, developing and evaluating new alternative models.


Subject(s)
Ameloblastoma , Carcinoma , Deep Learning , Odontogenic Tumors , Humans , Ameloblastoma/diagnostic imaging , Ameloblastoma/pathology , Artificial Intelligence , Reproducibility of Results , Odontogenic Tumors/diagnostic imaging , Odontogenic Tumors/pathology
5.
Head Neck Pathol ; 17(3): 832-850, 2023 Sep.
Article in English | MEDLINE | ID: mdl-37540486

ABSTRACT

Low-grade myofibroblastic sarcoma (LGMS) represents an atypical tumor composed of myofibroblasts with a variety of histological patterns and with a high tendency to local recurrence and a low probability of distant metastases. LGMS has predilection for the head and neck regions, especially the oral cavity. This study aimed to report 13 new cases of LGMS arising in the oral and maxillofacial region. This study included LGMS cases from five oral and maxillofacial pathology laboratories in four different countries (Brazil, Peru, Guatemala, and South Africa). Their clinical, radiographic, histopathological, and immunohistochemical findings were evaluated. In this current international case series, most patients were females with a mean age of 38.7 years, and commonly presenting a nodular lesion in maxilla. Microscopically, all cases showed a neoplasm formed by oval to spindle cells in a fibrous stroma with myxoid and dense areas, some atypical mitoses, and prominent nucleoli. The immunohistochemical panel showed positivity for smooth muscle actin (12 of 13 cases), HHF35 (2 of 4 cases), ß-catenin (3 of 5 cases), desmin (3 of 11 cases), and Ki-67 (range from 5 to 50%). H-caldesmon was negative for all cases. The diagnosis of LGMS was confirmed in all cases. LGMS shows predominance in young adults, with a slight predilection for the female sex, and maxillary region. LGMS should be a differential diagnosis of myofibroblastic lesions that show a proliferation of spindle cells in a fibrous stroma with myxoid and dense areas and some atypical mitoses, supporting the diagnosis with a complementary immunohistochemical study. Complete surgical excision with clear margins is the treatment of choice. However, long-term follow-up information is required before definitive conclusions can be drawn regarding the incidence of recurrence and the possibility of metastasis.


Subject(s)
Fibrosarcoma , Humans , Female , Adult , Male , Fibrosarcoma/pathology , Myofibroblasts/pathology , Head/pathology , Diagnosis, Differential , Brazil
7.
J Oral Pathol Med ; 52(2): 109-118, 2023 Feb.
Article in English | MEDLINE | ID: mdl-36599081

ABSTRACT

INTRODUCTION: Artificial intelligence models and networks can learn and process dense information in a short time, leading to an efficient, objective, and accurate clinical and histopathological analysis, which can be useful to improve treatment modalities and prognostic outcomes. This paper targets oral pathologists, oral medicinists, and head and neck surgeons to provide them with a theoretical and conceptual foundation of artificial intelligence-based diagnostic approaches, with a special focus on convolutional neural networks, the state-of-the-art in artificial intelligence and deep learning. METHODS: The authors conducted a literature review, and the convolutional neural network's conceptual foundations and functionality were illustrated based on a unique interdisciplinary point of view. CONCLUSION: The development of artificial intelligence-based models and computer vision methods for pattern recognition in clinical and histopathological image analysis of head and neck cancer has the potential to aid diagnosis and prognostic prediction.


Subject(s)
Artificial Intelligence , Oral Medicine , Humans , Pathology, Oral , Neural Networks, Computer , Machine Learning
8.
Nanomaterials (Basel) ; 11(11)2021 Nov 13.
Article in English | MEDLINE | ID: mdl-34835816

ABSTRACT

Inspired by the knowledge of the thermocatalytic CO2 reduction process, novel nanocrystalline CuZnAl-oxide based catalysts with pyramidal mesoporous structures are here proposed for the CO2 electrochemical reduction under ambient conditions. The XPS analyses revealed that the co-presence of ZnO and Al2O3 into the Cu-based catalyst stabilize the CuO crystalline structure and introduce basic sites on the ternary as-synthesized catalyst. In contrast, the as-prepared CuZn- and Cu-based materials contain a higher amount of superficial Cu0 and Cu1+ species. The CuZnAl-catalyst exhibited enhanced catalytic performance for the CO and H2 production, reaching a Faradaic efficiency (FE) towards syngas of almost 95% at -0.89 V vs. RHE and a remarkable current density of up to 90 mA cm-2 for the CO2 reduction at -2.4 V vs. RHE. The physico-chemical characterizations confirmed that the pyramidal mesoporous structure of this material, which is constituted by a high pore volume and small CuO crystals, plays a fundamental role in its low diffusional mass-transfer resistance. The CO-productivity on the CuZnAl-catalyst increased at more negative applied potentials, leading to the production of syngas with a tunable H2/CO ratio (from 2 to 7), depending on the applied potential. These results pave the way to substitute state-of-the-art noble metals (e.g., Ag, Au) with this abundant and cost-effective catalyst to produce syngas. Moreover, the post-reaction analyses demonstrated the stabilization of Cu2O species, avoiding its complete reduction to Cu0 under the CO2 electroreduction conditions.

9.
Ciudad Autónoma de Buenos Aires; Argentina. Ministerio de Salud de la Nación. Dirección de Investigación en Salud; jul. 2016. 1-23 p. tab, graf.
Non-conventional in Spanish | ARGMSAL, BINACIS | ID: biblio-1400842

ABSTRACT

INTRODUCCIÓN La anemia es un problema de salud pública en los países de bajos y medianos ingresos. Al no existir consenso sobre cómo evaluar el nivel de hierro en las poblaciones, la prevalencia de la deficiencia de hierro suele inferirse a partir de la concentración de hemoglobina. El HemoCue es un método recomendado por la OMS para realizar la cuantificación de la hemoglobina a nivel poblacional. OBJETIVO Describir la experiencia inédita de haber utilizado el HemoCue en la red de atención pública de la ciudad de Rosario. MÉTODOS Se realizó un estudio retrospectivo, de corte transversal, en niños de 6 a 42 meses de edad. Las variables de interés fueron el registro del HemoCue en la historia clínica del niño y la toma de conducta (diagnóstica, preventiva o terapéutica) durante la consulta pediátrica. Además se recolectó información (edad, sexo, antecedentes de desnutrición y/o anemia, peso, talla, etc.) con el fin de describir la muestra del estudio. Los datos se analizaron de forma global y según diagnóstico de anemia. Se utilizó el programa R. RESULTADOS Se incluyó un total de 500 niños provenientes de cinco centros de salud. La mediana de la edad fue de 17 meses. A nivel global se registró el HemoCue en un 42% y en alrededor de la mitad de estos casos se tomó algún tipo conducta clínica. En el grupo de niños con anemia (n=242), la toma de conducta basada en el resultado del HemoCue fue mayor (75%, 1C 95%: 660/0-820/0) en comparación con los niños sin anemia (n=258) que contaban con registro del HemoCue (33 0 0). La solicitud de un hemograma de rutina fue la intervención diagnóstica más frecuente y la ìnvestigación para suplementación con hierro por vía oral fue la intervención más utilizada para prevención y/o tratamiento de la anemia. DISCUSIÓN Nuestros hallazgos sugieren que el HemoCue es un método potencialmente útil para el control de la anemia infantil en el sistema público. La evidencia generada a partir de este estudio debería ser considerada en futuras investigaciones


Subject(s)
Pediatrics , Retrospective Studies , Hemoglobinometry , Anemia
10.
Perspect. nutr. hum ; 18(1): 11-23, ene.-jun. 2016. tab
Article in Spanish | LILACS | ID: biblio-955286

ABSTRACT

RESUMEN Antecedentes: determinar el estado nutricional y los síntomas depresivos en personas adultas, son factores importantes a tener en cuenta para el diseño de estrategias que contribuyan a mejorar las condiciones de vida. Objetivo: describir la relación entre factores sociodemográficos, nutricionales y síntomas depresivos en adultos de 50 o más años. Materiales y métodos: estudio descriptivo transversal, en el cual se determinaron variables sociodemográficas, antropométricas, nutricionales y de salud mental en 168 adultos de 50 o más años, pertenecientes al Programa Adulto Mayor (PAM) de Sabaneta (Antioquia). Resultados: se encontraron diferencias significativas entre las variables Índice de Masa Corporal (IMC), sexo y estado civil, al igual que en el puntaje de la Minivaloración Nutricional (MNA) en relación con el estado civil (p<0,05); en cuanto al puntaje de depresión de Beck no se determinaron relaciones significativas con las variables sociodemográficas (p>0,05), pero sí con el MNA (p<0,001). Conclusiones: los hallazgos permiten establecer según el IMC y el MNA, que los participantes en general presentan una situación socioeconómica favorable y un estado nutricional adecuado; además la frecuencia de síntomas depresivos que se encontró fue mínima, lo cual contribuye al estado de salud y bienestar de los adultos pertenecientes al PAM.


ABSTRACT Background: To determine nutritional status and symptoms of depression in adults, factors which are importantto consider in the design of strategies that contribute to increasing quality of life. Objetive: To describe the relationbetween sociodomographic, nutritional, and depression factors in adults 50 years of age and older. Materials and methods: Descriptive cross-sectional study, in which sociodemographic, anthropometric, nutritional and mental healthvariables were determined in 168 adults aged 50 years and over, who belong to the Older Adult Program (PAM) of thecity of Sabaneta, Antioquia. Results: We found significant differences between the variables body mass index (BMI),sex, and marital status, as well as in the nutritional minivaloration score (MNA) in relation to marital status (p <0.05).With the Beck depression score no significant relationships were found with sociodeomograhpic variables (P> 0.05),but significance was found with with MNA score (p <0.001). Conclusions: The findings make it possible to establishaccording to BMI and MNA, that participants generally have a favorable socioeconomic situation and an adequatenutritional status; In addition, the frequency was low of depression symptoms, contributing to the health status andwell-being of adults belonging to the PAM.

11.
Arch. argent. pediatr ; 112(2): 183-191, abr. 2014.
Article in Spanish | LILACS, BINACIS | ID: biblio-1159587

ABSTRACT

Las infecciones de piel y partes blandas son una causa frecuente de consulta en los centros de atención primaria de la salud. Los datos de la epidemiología local de estas infecciones son escasos; el Staphylococcus aureus y el Streptococcus pyogenes son los principales agentes etiológicos. La emergencia, en los últimos años, de cepas de S. aureus meticilino resistentes provenientes de la comunidad y S. pyogenes resistentes a eritromicina plantea controversia en la elección del tratamiento empírico inicial. Este consenso nacional está dirigido a médicos pediatras, de familia, dermatólogos, infectólogos y otros profesionales de la salud. Trata el manejo clínico, especialmente el diagnóstico y tratamiento, de las infecciones de piel y partes blandas de origen bacteriano provenientes de la comunidad en pacientes inmunocompetentes menores de 19 años de edad.


Skin and soft tissue infections are a common reason for consultation in primary health care centers. Data from the local epidemiology of these infections are rare, but Staphylococcus aureus and Streptococcus pyogenes are known to be the major etiologic agents. The appearance in recent years of community-originated strains of methicillin-resistant S. aureus and erythromycin-resistant pyogenes raises controversy in the choice of initial empirical treatment. This national consensus is for pediatricians, dermatologists, infectologists and other health professionals. It is about clinical management, especially the diagnosis and treatment of community-originated skin and soft tissue infections in immunocompetent patients under the age of 19.


Subject(s)
Humans , Child , Skin Diseases, Infectious/diagnosis , Skin Diseases, Infectious/therapy , Soft Tissue Infections/diagnosis , Soft Tissue Infections/therapy
12.
Arch Argent Pediatr ; 112(2): 183-91, 2014 Apr.
Article in Spanish | MEDLINE | ID: mdl-24584795

ABSTRACT

Skin and soft tissue infections are a common reason for consultation in primary health care centers. Data from the local epidemiology of these infections are rare, but Staphylococcus aureus and Streptococcus pyogenes are known to be the major etiologic agents. The appearance in recent years of community-originated strains of methicillin-resistant S. aureus and erythromycin-resistant pyogenes raises controversy in the choice of initial empirical treatment. This national consensus is for pediatricians, dermatologists, infectologists and other health professionals. It is about clinical management, especially the diagnosis and treatment of community-originated skin and soft tissue infections in immunocompetent patients under the age of 19.


Subject(s)
Skin Diseases, Infectious/diagnosis , Skin Diseases, Infectious/therapy , Soft Tissue Infections/diagnosis , Soft Tissue Infections/therapy , Child , Humans
13.
Arch Argent Pediatr ; 112(2): 183-91, 2014 Apr.
Article in Spanish | BINACIS | ID: bin-133623

ABSTRACT

Skin and soft tissue infections are a common reason for consultation in primary health care centers. Data from the local epidemiology of these infections are rare, but Staphylococcus aureus and Streptococcus pyogenes are known to be the major etiologic agents. The appearance in recent years of community-originated strains of methicillin-resistant S. aureus and erythromycin-resistant pyogenes raises controversy in the choice of initial empirical treatment. This national consensus is for pediatricians, dermatologists, infectologists and other health professionals. It is about clinical management, especially the diagnosis and treatment of community-originated skin and soft tissue infections in immunocompetent patients under the age of 19.

14.
Arch Argent Pediatr ; 109(5): e104-8, 2011 10.
Article in Spanish | MEDLINE | ID: mdl-22042064

ABSTRACT

Priapism is a prolonged penis erection, triggered by sexual stimulation or not; it is uncommon in children, but its knowledge is of great importance since it may lead to suspect serious diseases, such as leukemia, and it can lead to permanent erectile dysfunction if appropriate treatment is not timely done. We present the case of a 16-year-old boy with priapism which lead to a diagnosis of chronic myeloid leukemia. Knowledge of an uncommon pathology in children, like priapism, it is very important in order to establish the suitable and timely treatment, to prevent the irreversible sequelaes and complications of this disease.


Subject(s)
Leukemia, Myelogenous, Chronic, BCR-ABL Positive/complications , Priapism/etiology , Adolescent , Humans , Male
15.
Arch. argent. pediatr ; 109(5): 104-108, sept.-oct. 2011. tab
Article in Spanish | LILACS | ID: lil-633205

ABSTRACT

El priapismo es una erección peneana prolongada, desencadenada o no por estímulo sexual. Es poco frecuente en pediatría, pero importa su conocimiento pues su presencia puede trasuntar enfermedades graves, como la leucemia, y también puede complicarse con la disfunción sexual eréctil irreversible, si no se establece el tratamiento oportuno. Se informa el caso de un niño de 16 años, que debuta con priapismo como presentación de una leucemia mieloide crónica. El conocimiento del cuadro de priapismo permite realizar un enfoque adecuado, aplicar de forma sistemática las exploraciones y establecer un tratamiento para prevenir sus complicaciones.


Priapism is a prolonged penis erection, triggered by sexual stimulation or not; it is uncommon in children, but its knowledge is of great importance since it may lead to suspect serious diseases, such as leukemia, and it can lead to permanent erectile dysfunction if appropriate treatment is not timely done. We present the case of a 16-year-old boy with priapism which lead to a diagnosis of chronic myeloid leukemia. Knowledge of an uncommon pathology in children, like priapism, it is very important in order to establish the suitable and timely treatment, to prevent the irreversible sequelaes and complications of this disease.


Subject(s)
Adolescent , Humans , Male , Leukemia, Myelogenous, Chronic, BCR-ABL Positive/complications , Priapism/etiology
SELECTION OF CITATIONS
SEARCH DETAIL
...