RESUMEN
INTRODUCTION: Achalasia has been linked to viruses. We have observed cases of rapid-developing achalasia post-coronavirus disease 2019 (COVID-19). METHODS: We aimed to prospectively evaluate esophageal muscle for severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) from patients with rapid-onset achalasia post-COVID-19 and compare them with achalasia predating COVID-19 and achalasia with no COVID-19. RESULTS: Compared with long-standing achalasia predating COVID-19 and long-standing achalasia with no COVID-19, the subjects with achalasia post-COVID-19 had significantly higher levels of messenger RNA for the SARS-CoV-2 nucleocapsid (N) protein, which correlated with a significant increase in the inflammatory markers NOD-like receptor family pyrin domain-containing 3 and tumor necrosis factor. DISCUSSION: SARS-CoV-2, the virus responsible for COVID-19, is a possible trigger for achalasia.
Asunto(s)
COVID-19 , Acalasia del Esófago , SARS-CoV-2 , Humanos , Acalasia del Esófago/virología , COVID-19/complicaciones , Masculino , Femenino , Persona de Mediana Edad , Adulto , Estudios Prospectivos , Anciano , Esófago/virología , Proteínas de la Nucleocápside de Coronavirus , Fosfoproteínas/metabolismo , Reacción en Cadena de la Polimerasa/métodos , ARN Mensajero/metabolismoRESUMEN
Pancreatic ductal adenocarcinoma (PDAC) is the primary reason for cancer-related deaths in the US. Genetic mutations, drug resistance, the involvement of multiple signaling pathways, cancer stem cells (CSCs), and desmoplastic stroma, which hinders drug penetrance, contribute to poor chemotherapeutic efficacy. Hence, there is a need to identify novel drugs with improved delivery to improve treatment outcomes. Curcumin is one such compound that can inhibit multiple signaling pathways and CSCs. However, curcumin's clinical applicability for treating PDAC is limited because of its poor solubility in water and metabolic instability. Hence, we developed a difluorinated curcumin (CDF) analog that accumulates selectively in the pancreas and inhibits PDAC growth in vitro and in vivo. In the present work, we developed its 2-hydroxy-propyl-ß-cyclodextrin (HCD) inclusion complex to increase its water solubility and hydrolytic stability. The CDFHCD inclusion complex was characterized by spectroscopic, thermal, and microscopic techniques. The inclusion complex exhibited increased aqueous solubility, hydrolytic stability, and antiproliferative activity compared to parent CDF. Moreover, CDF and CDFHCD inhibited colony and spheroid formation, and induced cell cycle and apoptosis in PDAC cell lines. Hence, CDFHCD self-assembly is an efficient approach to increase water solubility and anticancer therapeutic efficacy, which now warrants advancement towards a clinical proof of concept in PDAC patients.
Asunto(s)
Carcinoma Ductal Pancreático , Curcumina , Neoplasias Pancreáticas , Humanos , Curcumina/química , 2-Hidroxipropil-beta-Ciclodextrina/farmacología , 2-Hidroxipropil-beta-Ciclodextrina/uso terapéutico , Neoplasias Pancreáticas/tratamiento farmacológico , Neoplasias Pancreáticas/metabolismo , Carcinoma Ductal Pancreático/tratamiento farmacológico , Solubilidad , Agua , Neoplasias PancreáticasRESUMEN
After lung cancer, breast cancer is the second leading cause of death in women. If breast cancer is detected early, mortality rates in women can be reduced. Because manual breast cancer diagnosis takes a long time, an automated system is required for early cancer detection. This paper proposes a new framework for breast cancer classification from ultrasound images that employs deep learning and the fusion of the best selected features. The proposed framework is divided into five major steps: (i) data augmentation is performed to increase the size of the original dataset for better learning of Convolutional Neural Network (CNN) models; (ii) a pre-trained DarkNet-53 model is considered and the output layer is modified based on the augmented dataset classes; (iii) the modified model is trained using transfer learning and features are extracted from the global average pooling layer; (iv) the best features are selected using two improved optimization algorithms known as reformed differential evaluation (RDE) and reformed gray wolf (RGW); and (v) the best selected features are fused using a new probability-based serial approach and classified using machine learning algorithms. The experiment was conducted on an augmented Breast Ultrasound Images (BUSI) dataset, and the best accuracy was 99.1%. When compared with recent techniques, the proposed framework outperforms them.
Asunto(s)
Neoplasias de la Mama , Aprendizaje Profundo , Mama , Neoplasias de la Mama/diagnóstico por imagen , Femenino , Humanos , Probabilidad , Ultrasonografía MamariaRESUMEN
Fumarate hydratase-deficient renal cell carcinoma (FH-deficient RCC) is typically considered a high-grade, aggressive subtype of RCC that frequently arises in the setting of hereditary leiomyomatosis-renal cell carcinoma (HLRCC) syndrome. Increasing experience with HLRCC-associated RCC and FH-deficient RCC has resulted in recognition of tumors with lower grade morphologic features, overlapping with those of succinate dehydrogenase-deficient RCC and other low-grade oncocytic tumors. In this review article, we report a previously unpublished case that was recently encountered in our practice and review cases in the current literature with an aim of getting a better understanding of these oncocytic tumors and their morphologic spectrum. The 13 cases reviewed were approximately equally distributed across males and females, occurred at a younger age, and were more frequently seen in the right kidney, with both unifocal and multifocal presentations. While most presented an exclusive, low-grade oncocytic morphology, in 4 cases they were associated with either separate high-grade tumors, or as a secondary pattern in an otherwise conventional high-grade FH-deficient RCC. Loss of FH and 2 succinyl cysteine (2SC) positivity by immunohistochemistry supported their diagnosis, and are recommended to be performed alongside CD117, CK7, and CK20 in to aid classification in challenging oncocytic tumors. When occurring in isolation, these tumors are distinctive from their high-grade counterparts, with no reported adverse outcomes in cases reported thus far. As such, accurate diagnosis of this low-grade pattern among FH-deficient RCCs is worthwhile not only due to its association with HLRCC and need of genetic counseling and surveillance, but also due to more favorable prognosis. Finally, increasing experience with the low-grade end of the morphologic spectrum of FH deficient RCC reiterates that not all tumors of this subtype of RCC have a uniformly aggressive outcome.
Asunto(s)
Productos Biológicos , Carcinoma de Células Renales , Neoplasias Renales , Leiomiomatosis , Carcinoma de Células Renales/diagnóstico , Carcinoma de Células Renales/genética , Diagnóstico Diferencial , Femenino , Fumarato Hidratasa/genética , Humanos , Neoplasias Renales/diagnóstico , Neoplasias Renales/genética , Leiomiomatosis/diagnóstico , Leiomiomatosis/genética , MasculinoRESUMEN
The urinary bladder may be involved by a variety of secondary tumors that originate from other organs. Bladder secondary tumors are rare and may be mistaken as bladder primary tumors because of their overlapping morphologic features. To avoid the diagnostic pitfalls, we analyzed the clinicopathologic features of bladder secondary tumors in a large cohort of patients. Our patient cohort consisted of 45 females and 38 males with a mean age of 58.7 ± 15.4 years (range 10-87 years). The tumors involved the bladder via direct extension from adjacent organs (n = 42) and distant metastasis (n = 41). In females, the majority of secondary tumors originated from the gynecologic tract (n = 25), and other common origins included the colon/rectum (n = 5) and breast (n = 4). In males, the most common origin was the prostate (n = 18), followed by the colon/rectum (n = 4) and kidney (n = 3). 75.9% of the secondary tumors were adenocarcinoma (n = 63), and other common tumor types included sarcoma (n = 6), squamous cell carcinoma (n = 5), melanoma (n = 4), and neuroendocrine carcinoma (n = 3). 67.5% of patients (n = 56) died of the disease with a median overall survival of 23 months from the time of secondary involvement of the bladder. Patients with secondary tumors via direct extension had a median survival time of 20 months, which was not significantly different from that for patients with secondary involvement via distant metastasis (24 months) (p = 0.83). Median survival in cases with prostate primary was 20 months as compared to 23 months for all other tumor types (p = 0.68). The majority of secondary tumors are composed of adenocarcinoma, which highlights the importance of differentiating primary from secondary involvement in bladder adenocarcinoma. Regardless of the origin, bladder secondary tumors are associated with a poor prognosis.
Asunto(s)
Adenocarcinoma/secundario , Neoplasias de la Vejiga Urinaria/mortalidad , Neoplasias de la Vejiga Urinaria/patología , Vejiga Urinaria/patología , Adenocarcinoma/diagnóstico , Adulto , Anciano , Carcinoma Neuroendocrino/diagnóstico , Carcinoma Neuroendocrino/secundario , Carcinoma de Células Escamosas/diagnóstico , Carcinoma de Células Escamosas/secundario , Estudios de Casos y Controles , Diagnóstico Diferencial , Femenino , Humanos , Masculino , Melanoma/diagnóstico , Melanoma/secundario , Persona de Mediana Edad , Evaluación de Resultado en la Atención de Salud , Pronóstico , Sarcoma/diagnóstico , Sarcoma/secundario , Análisis de Supervivencia , Neoplasias de la Vejiga Urinaria/secundarioRESUMEN
Secretory carcinoma of the salivary glands is a distinct entity with distinct morphologic features, immunohistochemical profile and molecular alterations. It mainly affects middle aged individuals with slight male predominance and parotid gland is the most common site of involvement. Although ETV6-NTRK3 gene fusion is considered pathognomonic for secretory carcinoma, advances in molecular profiling of this tumor have led to the discovery of novel ETV6 fusion partners and gene mutations. Herein, we describe a case of an adenocarcinoma of intercalated duct origin favor secretory carcinoma, in a unique location of von Ebner's glands of mobile tongue in a 40-year-old Caucasian female. Aside from being in a unique location, the tumor showed somatic mutation for PALB2 gene which has not been described so far in secretory carcinoma. Discovery of novel fusions and mutations have therapeutic implications with respect to targeted therapy.
Asunto(s)
Adenocarcinoma/genética , Proteína del Grupo de Complementación N de la Anemia de Fanconi/genética , Neoplasias de las Glándulas Salivales/genética , Glándulas de von Ebner/patología , Adenocarcinoma/patología , Adulto , Femenino , Humanos , Mutación , Neoplasias de las Glándulas Salivales/patologíaRESUMEN
The thymus is a dynamic organ that undergoes changes throughout life and can demonstrate a myriad of pathologic alterations. A number of benign entities of the thymus prove to be diagnostic dilemmas owing to their resemblance and association with true thymic tumors. These are usually discovered incidentally on routine imaging and most patients are either asymptomatic or present with signs and symptoms of compression of adjacent organs. The radiologic appearance of these lesions varies from simple cysts to complex masses that are suspicious for malignancy. The diagnosis is usually made purely on morphologic grounds, however, immunohistochemical stains can help rule out possible differential diagnoses. Surgical removal is usually curative in these lesions and recurrences are rare. The prognosis is excellent, however, some of these lesions may be associated with myasthenia gravis and/or thymomas. In this review, we describe non-neoplastic lesions and benign tumoral lesions of the thymus, with emphasis on the clinical, radiologic, and pathologic features. The differential diagnosis of each entity is also discussed.
Asunto(s)
Miastenia Gravis/patología , Timoma/patología , Timo/patología , Neoplasias del Timo/patología , Diagnóstico Diferencial , Humanos , Miastenia Gravis/diagnóstico , Pronóstico , Timoma/diagnóstico , Neoplasias del Timo/diagnósticoRESUMEN
Thymic mucoepidermoid carcinoma is a rare tumor that remains poorly characterized and a diagnostic challenge. The aim of this review is to characterize this tumor in a larger cohort of patients using all the available cases in the literature. We systematically searched the PubMed and Scopus database for primary thymic mucoepidermoid carcinoma. A total of 24 studies were included in the final analysis. A total of 41 patients were identified; 23 (56.1%) were male and 18 (43.9%) were female. Mean age was 49.8±21.3 years. Mean tumor size was 7.6±3.5 cm. Twenty (66.7%) were low grade and 8 (26.7%) were high grade. In total, 20 (55.6%) patients were treated with surgery alone. Nodal dissection was performed in 4 cases only. Two patients had MAML2 gene rearrangement and 2 were negative. Follow-up time varied from 2 to 93 months. A total of 13 (44.8%) patients died of disease with a median survival of 12 months. There seems to be a bimodal age distribution with peaks between second and third decades of life, and between sixth and eight decades. Lymph node sampling is frequently not performed; however, we recommend performing it, as it may lead to more accurate staging. There is limited data regarding the utility of MAML2 gene rearrangement in the thymic location. Histologic grade and tumor stage/resectability are the main prognostic factors.
Asunto(s)
Carcinoma Mucoepidermoide/patología , Carcinoma Mucoepidermoide/cirugía , Proteínas de Fusión Oncogénica/genética , Transactivadores/genética , Proteínas de Unión al ADN/genética , Humanos , Estadificación de Neoplasias , Proteínas Nucleares/genética , Factores de Transcripción/genéticaRESUMEN
BACKGROUND: There is contradictory evidence in literature with respect to diagnosis and management of follicular lesions of the thyroid gland. From surgical pathology stand point, pathologists require submission and processing of entire capsule for microscopic evaluation. This can be extremely challenging especially in larger lesions. METHOD: We studied the impact of submitting entire capsule on final pathologic diagnosis in cases on which only representative sections were submitted initially and entire capsule was submitted subsequently. RESULTS: A total of 80 specimens were identified. Mean size of the nodule in these cases was 4.4⯱â¯1.9â¯cm. Mean initial tissue sections submitted were 11.6⯱â¯3.6. Entire capsule was submitted subsequently in an additional 12.6⯱â¯13.3 sections. Submission of entire capsule contributed to final diagnosis in 3 (3.8%) cases whereby foci of capsular microinvasion were identified. There was no significant difference in the requirement of subsequent sections in specimens grossed by residents compared to those grossed by pathologist assistants (10.4⯱â¯10.8 vs. 14.4⯱â¯14.9, pâ¯=â¯0.18). The processing cost of additional sections of capsule was $ 4143 in these cases. CONCLUSION: Processing of entire capsule in thyroid follicular lesions has a definitive yield that comes at a high cost. Thin slicing and looking for areas of gross abnormality such as mushrooming may be more practical especially in larger lesions.
Asunto(s)
Adenocarcinoma Folicular/diagnóstico , Glándula Tiroides/patología , Neoplasias de la Tiroides/diagnóstico , Adenocarcinoma Folicular/patología , Adenocarcinoma Folicular/cirugía , Adulto , Biopsia/economía , Biopsia/métodos , Femenino , Humanos , Masculino , Estudios Retrospectivos , Sensibilidad y Especificidad , Neoplasias de la Tiroides/patología , Neoplasias de la Tiroides/cirugía , TiroidectomíaRESUMEN
BACKGROUND: Immune checkpoint inhibitors play an increasing role in oncologic care. PD-L1 expression is associated with survival and predicts response to PD-1 or PD-L1 inhibitors in a variety of tumors. Our aim is to evaluate the frequency and prognostic significance of PD-L1 expression in salivary duct carcinoma. DESIGN: We retrospectively evaluated the expression of PD-L1 by two different antibodies (PD-L1 28-8 and PD-L1 22C3) in salivary duct carcinomas. PD-L1 expression in at least 1% of tumor cells was considered immunoreactive. Kaplan-Meier analysis was performed to determine the impact of PD-L1 expression on survival; differences between survival curves were assessed by the chi-square test, and pairwise comparisons of factors were assessed with the log-rank test. RESULTS: A total of 113 patients' specimens were evaluated. Seventy-six (76%) of the patients were male. Mean age at time of presentation was 61.2 (SDâ¯=â¯12.4) years. PD-L1 expression was found in 26% of the samples. Median follow-up time was 36.6â¯months (rangeâ¯=â¯1.4-249 months). Overall survival at 3, 5 and 10â¯years were 52.6%, 37.9% and 25.6%, respectively. There was no statistical difference in survival between patients with PD-L1-immunoreactive tumors and those without, regardless of which antibody was used (chi2 result for all plots: pâ¯=â¯0.53; log rank test for pairwise comparison: pâ¯>â¯0.256). CONCLUSION: In our analysis, PD-L1 expression occurred in a small proportion of salivary duct carcinomas, usually at low levels, and did not correlate with survival. Its predictive value and utility in selecting patients with salivary duct carcinoma who might benefit from PD-1/PD-L1 inhibitors warrants further investigation.
Asunto(s)
Antígeno B7-H1/metabolismo , Carcinoma/diagnóstico , Receptor de Muerte Celular Programada 1/metabolismo , Neoplasias de las Glándulas Salivales/diagnóstico , Anciano , Antígeno B7-H1/antagonistas & inhibidores , Carcinoma/tratamiento farmacológico , Carcinoma/metabolismo , Carcinoma/patología , Femenino , Humanos , Inmunohistoquímica , Inmunoterapia , Estimación de Kaplan-Meier , Masculino , Persona de Mediana Edad , Pronóstico , Receptor de Muerte Celular Programada 1/antagonistas & inhibidores , Estudios Retrospectivos , Conductos Salivales/metabolismo , Conductos Salivales/patología , Neoplasias de las Glándulas Salivales/tratamiento farmacológico , Neoplasias de las Glándulas Salivales/metabolismo , Neoplasias de las Glándulas Salivales/patologíaRESUMEN
Advancement in genetic and molecular biology techniques has greatly helped our understanding of various diseases, especially hematological disorders. We describe a case of primary myelofibrosis (PMF) that transformed into acute myeloid leukemia with a very rare and unusual genetic translocation of (1;21). There are only five reported cases of this translocation in acute myeloid leukemia (AML) or myelodysplastic syndrome but none of them transformed from PMF. This case not only highlights the importance of rare genetic translocations but also provides the natural history of the disease and its poor prognosis. To the best of our knowledge our patient is the first reported case of AML transformed from PMF to have this unique translocation of (1;21).
Asunto(s)
Cromosomas Humanos Par 1/genética , Cromosomas Humanos Par 21/genética , Leucemia Mieloide Aguda/genética , Femenino , Humanos , Persona de Mediana Edad , Síndromes Mielodisplásicos/genética , Mielofibrosis Primaria/genética , Pronóstico , Translocación Genética/genéticaRESUMEN
Tumours of uterine corpus are the most common gynaecological malignancies. The clinicopathological features of most of these tumours are well understood; however, dedifferentiated endometrial carcinoma still requires a lot of research to establish adequate management guidelines. The entity was first described in 2006 and is an aggressive tumour with poor prognosis. We present two cases of this tumour with a literature review, emphasising morphologic and immunohistochemical features that may help in the differential diagnosis.
Asunto(s)
Carcinoma Endometrioide/diagnóstico , Neoplasias Endometriales/diagnóstico , Diagnóstico Diferencial , Femenino , Humanos , InmunohistoquímicaRESUMEN
Mesenteric vasculitis and resultant bowel ischemia is rare but serious complication of autoimmune disorders. Early detection and treatment is the key to avoid potentially fatal outcomes of bowel perforation and peritonitis. In this series, we present patients presenting with acute abdominal pain and having CT imaging features of bowel ischemia who responded well to immunosuppressive therapy. The aim of this work is to familiarize health professionals with possibility and imaging features of mesenteric vasculitis.
Asunto(s)
Abdomen Agudo/etiología , Enfermedades Autoinmunes/complicaciones , Intestinos/irrigación sanguínea , Isquemia/diagnóstico por imagen , Isquemia/etiología , Abdomen Agudo/diagnóstico por imagen , Adolescente , Adulto , Enfermedades Autoinmunes/diagnóstico por imagen , Femenino , Humanos , Intestinos/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Tomografía Computarizada por Rayos XRESUMEN
BACKGROUND: Emerging resistance to antimicrobial chemotherapy is becoming a challenge for medicine in recent times. Un-prescribed use of antibiotics is a major contributor to development of this problem. In Pakistan access to antibiotics remains unchecked and hence results in it are over use. The aim of this study was to assess knowledge of parents regarding use of antibiotics, its associated problems, their source of information and their expectations from Paediatricians for prescription of anti-biotics. METHODS: This is a questionnaire based cross sectional study conducted in Hayatabad town, District Peshawar. Parents who were consenting, had children aged between 0-16 years, and were not related to medical profession were included in study. Total number of participants interviewed was 400. Analysis was done using prevalence ratios. RESULTS: Most of the participants were mothers. Majority of respondents were literate with education up till level of Graduation. 64% mentioned that they enjoyed a good access to healthcare. Most common source for use of antibiotics was Physician. 35% mentioned that antibiotics must be administered in any case of fever, 47% thought antibiotics to increase recovery time and 51% knew that antibiotics have their own side effect. The most common reason to administer un-prescribed antibiotics was same antibiotic being prescribed by a physician earlier followed by family member or pharmacist recommending use of antibiotic. Lack of resources was denied as a reason for self-administration of antibiotics by majority of parents. CONCLUSION: There is a need of intervention to increase awareness regarding judicious use of antibiotics and to check un-prescribed dispensing of antibiotics.
Asunto(s)
Antibacterianos/uso terapéutico , Conocimientos, Actitudes y Práctica en Salud , Padres , Pautas de la Práctica en Medicina , Niño , Estudios Transversales , Humanos , PakistánRESUMEN
Automatic Urdu handwritten text recognition is a challenging task in the OCR industry. Unlike printed text, Urdu handwriting lacks a uniform font and structure. This lack of uniformity causes data inconsistencies and recognition issues. Different writing styles, cursive scripts, and limited data make Urdu text recognition a complicated task. Major languages, such as English, have experienced advances in automated recognition, whereas low-resource languages, such as Urdu, still lag. Transformer-based models are promising for automated recognition in high- and low-resource languages such as Urdu. This paper presents a transformer-based method called ET-Network that integrates self-attention into EfficientNet for feature extraction and a transformer for language modeling. The use of self-attention layers in EfficientNet helps to extract global and local features that capture long-range dependencies. These features proceeded into a vanilla transformer to generate text, and a prefix beam search is used for the finest outcome. NUST-UHWR, UPTI2.0, and MMU-OCR-21 are three datasets used to train and test the ET Network for a handwritten Urdu script. The ET-Network improved the character error rate by 4% and the word error rate by 1.55%, while establishing a new state-of-the-art character error rate of 5.27% and a word error rate of 19.09% for Urdu handwritten text.
Asunto(s)
Aprendizaje Profundo , Escritura Manual , Humanos , Lenguaje , Reconocimiento de Normas Patrones Automatizadas/métodos , AlgoritmosRESUMEN
Ectopic thyroid tissue is rare in the general population and more prevalent in people who have existing thyroid disease. Common anatomical sites of ectopic thyroid tissue include the lateral cervical region, thyroglossal duct, mediastinum, lingual, sublingual, and submandibular region. Intrathymic ectopic thyroid tissue is exceedingly rare. The purpose of this report is to describe one such case in a 52-year-old African-American female with Graves' disease. The patient presented for a physical exam and follow-up. During the exam, an incidental mediastinal mass was discovered, which was evaluated by imaging studies and subsequently was resected. Histologically, the mass was composed of variable-sized thyroid follicles lined by a monolayer of cuboidal to columnar follicular epithelial cells and filled with eosinophilic colloid, surrounded by a rim of unremarkable compressed thymic tissue.
RESUMEN
The prevalence of brain tumor disorders is currently a global issue. In general, radiography, which includes a large number of images, is an efficient method for diagnosing these life-threatening disorders. The biggest issue in this area is that it takes a radiologist a long time and is physically strenuous to look at all the images. As a result, research into developing systems based on machine learning to assist radiologists in diagnosis continues to rise daily. Convolutional neural networks (CNNs), one type of deep learning approach, have been pivotal in achieving state-of-the-art results in several medical imaging applications, including the identification of brain tumors. CNN hyperparameters are typically set manually for segmentation and classification, which might take a while and increase the chance of using suboptimal hyperparameters for both tasks. Bayesian optimization is a useful method for updating the deep CNN's optimal hyperparameters. The CNN network, however, can be considered a "black box" model because of how difficult it is to comprehend the information it stores because of its complexity. Therefore, this problem can be solved by using Explainable Artificial Intelligence (XAI) tools, which provide doctors with a realistic explanation of CNN's assessments. Implementation of deep learning-based systems in real-time diagnosis is still rare. One of the causes could be that these methods don't quantify the Uncertainty in the predictions, which could undermine trust in the AI-based diagnosis of diseases. To be used in real-time medical diagnosis, CNN-based models must be realistic and appealing, and uncertainty needs to be evaluated. So, a novel three-phase strategy is proposed for segmenting and classifying brain tumors. Segmentation of brain tumors using the DeeplabV3+ model is first performed with tuning of hyperparameters using Bayesian optimization. For classification, features from state-of-the-art deep learning models Darknet53 and mobilenetv2 are extracted and fed to SVM for classification, and hyperparameters of SVM are also optimized using a Bayesian approach. The second step is to understand whatever portion of the images CNN uses for feature extraction using XAI algorithms. Using confusion entropy, the Uncertainty of the Bayesian optimized classifier is finally quantified. Based on a Bayesian-optimized deep learning framework, the experimental findings demonstrate that the proposed method outperforms earlier techniques, achieving a 97â¯% classification accuracy and a 0.98 global accuracy.
Asunto(s)
Teorema de Bayes , Neoplasias Encefálicas , Aprendizaje Profundo , Imagen por Resonancia Magnética , Humanos , Neoplasias Encefálicas/diagnóstico por imagen , Neoplasias Encefálicas/clasificación , Imagen por Resonancia Magnética/métodos , Imagen por Resonancia Magnética/normas , Redes Neurales de la Computación , Neuroimagen/métodos , Neuroimagen/normasRESUMEN
Alzheimer's disease (AD) is a neurodegenerative illness that impairs cognition, function, and behavior by causing irreversible damage to multiple brain areas, including the hippocampus. The suffering of the patients and their family members will be lessened with an early diagnosis of AD. The automatic diagnosis technique is widely required due to the shortage of medical experts and eases the burden of medical staff. The automatic artificial intelligence (AI)-based computerized method can help experts achieve better diagnosis accuracy and precision rates. This study proposes a new automated framework for AD stage prediction based on the ResNet-Self architecture and Fuzzy Entropy-controlled Path-Finding Algorithm (FEcPFA). A data augmentation technique has been utilized to resolve the dataset imbalance issue. In the next step, we proposed a new deep-learning model based on the self-attention module. A ResNet-50 architecture is modified and connected with a self-attention block for important information extraction. The hyperparameters were optimized using Bayesian optimization (BO) and then utilized to train the model, which was subsequently employed for feature extraction. The self-attention extracted features were optimized using the proposed FEcPFA. The best features were selected using FEcPFA and passed to the machine learning classifiers for the final classification. The experimental process utilized a publicly available MRI dataset and achieved an improved accuracy of 99.9%. The results were compared with state-of-the-art (SOTA) techniques, demonstrating the improvement of the proposed framework in terms of accuracy and time efficiency.
RESUMEN
INTRODUCTION: This meta-analysis seeks to evaluate the efficacy of direct oral anticoagulants (DOACs) versus vitamin K antagonists (VKA) in individuals with chronic kidney disease (CKD), end-stage renal disease (ESRD), and undergoing hemodialysis (HD) who also have atrial fibrillation (AF). EVIDENCE ACQUISITION: A comprehensive search of MEDLINE, clinicaltrials.gov, EMBASE, and Cochrane Database for relevant studies reporting the usefulness of OAC therapy for CKD, ESRD, and HD patients with AF was conducted from its inception until 1st May 2023. The studies that reported OR, RR, or HR for adult AF patients to investigate the efficacy of OAC in CKD, ESRD, and HD were included. Statistical analysis was completed using a generic inverse variance and random-effects model to calculate the combined HR and their corresponding 95% CIs for all outcomes. EVIDENCE SYNTHESIS: The meta-analysis included 33 studies with 178,956 patients. The analysis revealed that the DOACs, when compared to VKA, significantly lowered the risk of stroke or systemic embolism (HR: 0.81 [95% CI: 0.70, 0.93]; P=0.002; I2=62%), bleeding (HR: 0.77, [95% CI: 0.67, 0.89]; P=0.0003; I2=83%), and intracranial hemorrhage (HR: 0.56, [95% CI 0.47, 0.66]; P<0.00001; I2=0%). Similarly, the risks of cardiovascular death (HR: 0.88, [95% CI 0.78, 1.00]; P=0.05; I2=0%), all-cause mortality (HR: 0.88, [95% CI 0.70, 1.10]; P=0.25; I2=96%), and myocardial infarction (HR: 0.80, [95% CI 0.54, 1.17]; P= 0.25; I2= 0%) were lowered by DOAC, but the result was insignificant. No significant difference was seen in the risk of gastrointestinal bleeding between DOAC and VKA as well (HR: 0.95, [95% CI 0.75, 1.20]; P=0.65; I2=83%). CONCLUSIONS: Our meta-analysis confirms that DOACs are effective for managing AF in patients with kidney disease, with potential clinical implications for AF and CKD management. Further research should explore DOACs' reno-protective effects.