RESUMEN
BACKGROUND: Post-acute sequelae of SARS-CoV-2 infection (PASC) affects patients after recovering from acute coronavirus disease 2019 (COVID-19). This study investigates the impact of SARS-CoV-2 vaccination on PASC symptoms in children in Taiwan during the Omicron pandemic. METHODS: We enrolled children under 18 years with PASC symptoms persisting for more than 4 weeks. Data collected included demographics, clinical information, vaccination status, and symptom persistence. We used logistic regression models to compare symptoms in the acute and post-COVID-19 phases and to assess the association between vaccination and these symptoms. RESULTS: Among 500 PASC children, 292 (58.4%) were vaccinated, 282 (52.8%) were male, and the mean (SD) age was 7.6 (4.6) years. Vaccinated individuals exhibited higher odds of experiencing symptoms in the previous acute phase, such as cough (adjusted odds ratio [AOR] = 1.57; 95% confidence interval [CI]: 1.02-2.42), rhinorrhea/nasal congestion (AOR = 1.74; 95% CI: 1.13-2.67), sneezing (AOR = 1.68; 95% CI: 1.02-2.76), sputum production (AOR = 1.91; 95% CI: 1.15-3.19), headache/dizziness (AOR = 1.73; 95% CI: 1.04-2.87), and muscle soreness (AOR = 2.33; 95% CI: 1.13-4.80). In contrast, there were lower odds of experiencing abdominal pain (AOR = 0.49; 95% CI: 0.25-0.94) and diarrhea (AOR = 0.37; 95% CI: 0.17-0.78) in children who had received vaccination during the post-COVID-19 phase. CONCLUSIONS: This study revealed clinical features and vaccination effects in PASC children in Taiwan. Vaccination may reduce some gastrointestinal symptoms in the post-COVID-19 phase.
RESUMEN
A challenge in accurately identifying and classifying left ventricular hypertrophy (LVH) is distinguishing it from hypertrophic cardiomyopathy (HCM) and Fabry disease. The reliance on imaging techniques often requires the expertise of multiple specialists, including cardiologists, radiologists, and geneticists. This variability in the interpretation and classification of LVH leads to inconsistent diagnoses. LVH, HCM, and Fabry cardiomyopathy can be differentiated using T1 mapping on cardiac magnetic resonance imaging (MRI). However, differentiation between HCM and Fabry cardiomyopathy using echocardiography or MRI cine images is challenging for cardiologists. Our proposed system named the MRI short-axis view left ventricular hypertrophy classifier (MSLVHC) is a high-accuracy standardized imaging classification model developed using AI and trained on MRI short-axis (SAX) view cine images to distinguish between HCM and Fabry disease. The model achieved impressive performance, with an F1-score of 0.846, an accuracy of 0.909, and an AUC of 0.914 when tested on the Taipei Veterans General Hospital (TVGH) dataset. Additionally, a single-blinding study and external testing using data from the Taichung Veterans General Hospital (TCVGH) demonstrated the reliability and effectiveness of the model, achieving an F1-score of 0.727, an accuracy of 0.806, and an AUC of 0.918, demonstrating the model's reliability and usefulness. This AI model holds promise as a valuable tool for assisting specialists in diagnosing LVH diseases.
RESUMEN
An intensive care unit (ICU) is a special ward in the hospital for patients who require intensive care. It is equipped with many instruments monitoring patients' vital signs and supported by the medical staff. However, continuous monitoring demands a massive workload of medical care. To ease the burden, we aim to develop an automatic detection model to monitor when brain anomalies occur. In this study, we focus on electroencephalography (EEG), which monitors the brain electroactivity of patients continuously. It is mainly for the diagnosis of brain malfunction. We propose the gated-recurrent-unit-based (GRU-based) model for detecting brain anomalies; it predicts whether the spike or sharp wave happens within a short time window. Based on the banana montage setting, the proposed model exploits characteristics of multiple channels simultaneously to detect anomalies. It is trained, validated, and tested on separated EEG data and achieves more than 90% testing performance on sensitivity, specificity, and balanced accuracy. The proposed anomaly detection model detects the existence of a spike or sharp wave precisely; it will notify the ICU medical staff, who can provide immediate follow-up treatment. Consequently, it can reduce the medical workload in the ICU significantly.
RESUMEN
BACKGROUND AND OBJECTIVE: Local advanced rectal cancer (LARC) poses significant treatment challenges due to its location and high recurrence rates. Accurate early detection is vital for treatment planning. With magnetic resonance imaging (MRI) being resource-intensive, this study explores using artificial intelligence (AI) to interpret computed tomography (CT) scans as an alternative, providing a quicker, more accessible diagnostic tool for LARC. METHODS: In this retrospective study, CT images of 1070 T3-4 rectal cancer patients from 2010 to 2022 were analyzed. AI models, trained on 739 cases, were validated using two test sets of 134 and 197 cases. By utilizing techniques such as nonlocal mean filtering, dynamic histogram equalization, and the EfficientNetB0 algorithm, we identified images featuring characteristics of a positive circumferential resection margin (CRM) for the diagnosis of locally advanced rectal cancer (LARC). Importantly, this study employs an innovative approach by using both hard and soft voting systems in the second stage to ascertain the LARC status of cases, thus emphasizing the novelty of the soft voting system for improved case identification accuracy. The local recurrence rates and overall survival of the cases predicted by our model were assessed to underscore its clinical value. RESULTS: The AI model exhibited high accuracy in identifying CRM-positive images, achieving an area under the curve (AUC) of 0.89 in the first test set and 0.86 in the second. In a patient-based analysis, the model reached AUCs of 0.84 and 0.79 using a hard voting system. Employing a soft voting system, the model attained AUCs of 0.93 and 0.88, respectively. Notably, AI-identified LARC cases exhibited a significantly higher five-year local recurrence rate and displayed a trend towards increased mortality across various thresholds. Furthermore, the model's capability to predict adverse clinical outcomes was superior to those of traditional assessments. CONCLUSION: AI can precisely identify CRM-positive LARC cases from CT images, signaling an increased local recurrence and mortality rate. Our study presents a swifter and more reliable method for detecting LARC compared to traditional CT or MRI techniques.
RESUMEN
PURPOSE: This study seeks to build a normative database for the vessel density of the superficial retina (SVD) and evaluate how changes and trends in the retinal microvasculature may be influenced by age and axial length (AL) in non-glaucomatous eyes, as measured with optical coherence tomography angiography (OCTA). METHODS: We included 500 eyes of 290 healthy subjects visiting a county hospital. Each participant underwent comprehensive ophthalmological examinations and OCTA to measure the SVD and thickness of the macular and peripapillary areas. To analyze correlations between SVD and age or AL, multivariable linear regression models with generalized estimating equations were applied. RESULTS: Age was negatively correlated with the SVD of the superior, central, and inferior macular areas and the superior peripapillary area, with a decrease rate of 1.06%, 1.36%, 0.84%, and 0.66% per decade, respectively. However, inferior peripapillary SVD showed no significant correlation with age. AL was negatively correlated with the SVD of the inferior macular area and the superior and inferior peripapillary areas, with coefficients of -0.522%/mm, -0.733%/mm, and -0.664%/mm, respectively. AL was also negatively correlated with the thickness of the retinal nerve fiber layer and inferior ganglion cell complex (p = 0.004). CONCLUSION: Age and AL were the two main factors affecting changes in SVD. Furthermore, AL, a relative term to represent the degree of myopia, had a greater effect than age and showed a more significant effect on thickness than on SVD. This relationship has important implications because myopia is a significant issue in modern cities.
Asunto(s)
Miopía , Vasos Retinianos , Humanos , Retina , Tomografía de Coherencia Óptica/métodos , Fibras Nerviosas , EnvejecimientoRESUMEN
Cardiovascular diseases, particularly arrhythmias, remain a leading cause of mortality worldwide. Electrocardiogram (ECG) analysis plays a pivotal role in cardiovascular disease diagnosis. Although previous studies have focused on waveform analysis and model training, integrating additional clinical information, especially demographic data, remains challenging. In this study, we present an innovative approach to ECG classification by incorporating demographic information from patients' medical histories through a colorization technique. Our proposed method maps demographic features onto the (R, G, B) color space through normalized scaling. Each demographic feature corresponds to a distinct color, allowing for different ECG leads to be colored. This approach preserves the relationships between data by maintaining the color correlations in the statistical features, enhancing ECG analytics and supporting precision medicine. We conducted experiments with PTB-XL dataset and achieved 1%-6% improvements in the area under the receiving operator characteristic curve performance compared with other methods for various classification problems. Notably, our method excelled in multiclass and challenging classification tasks. The combined use of color features and the original waveform shape features enhanced prediction accuracy for various deep learning models. Our findings suggest that colorization is a promising avenue for advancing ECG classification and diagnosis, contributing to improved prediction and diagnosis of cardiovascular diseases and ultimately enhancing clinical outcomes.
Asunto(s)
Enfermedades Cardiovasculares , Aprendizaje Profundo , Humanos , Enfermedades Cardiovasculares/diagnóstico , Electrocardiografía , Medicina de PrecisiónRESUMEN
Chronic kidney disease (CKD) is a major public health concern. But there are limited machine learning studies on non-cancer patients with advanced CKD, and the results of machine learning studies on cancer patients with CKD may not apply directly on non-cancer patients. We aimed to conduct a comprehensive investigation of risk factors for a 3-year risk of death among non-cancer advanced CKD patients with an estimated glomerular filtration rateâ <â 60.0 mL/min/1.73m2 by several machine learning algorithms. In this retrospective cohort study, we collected data from in-hospital and emergency care patients from 2 hospitals in Taiwan from 2009 to 2019, including their international classification of disease at admission and laboratory data from the hospital's electronic medical records (EMRs). Several machine learning algorithms were used to analyze the potential impact and degree of influence of each factor on mortality and survival. Data from 2 hospitals in northern Taiwan were collected with 6565 enrolled patients. After data cleaning, 26 risk factors and approximately 3887 advanced CKD patients from Shuang Ho Hospital were used as the training set. The validation set contained 2299 patients from Taipei Medical University Hospital. Predictive variables, such as albumin, PT-INR, and age, were the top 3 significant risk factors with paramount influence on mortality prediction. In the receiver operating characteristic curve, the random forest had the highest values for accuracy above 0.80. MLP, and Adaboost had better performance on sensitivity and F1-score compared to other methods. Additionally, SVM with linear kernel function had the highest specificity of 0.9983, while its sensitivity and F1-score were poor. Logistic regression had the best performance, with an area under the curve of 0.8527. Evaluating Taiwanese advanced CKD patients' EMRs could provide physicians with a good approximation of the patients' 3-year risk of death by machine learning algorithms.
Asunto(s)
Hospitalización , Insuficiencia Renal Crónica , Humanos , Estudios Retrospectivos , Factores de Riesgo , Aprendizaje Automático , Insuficiencia Renal Crónica/complicacionesRESUMEN
BACKGROUND: Based solely on pre-ablation characteristics, previous risk scores have demonstrated variable predictive performance. This study aimed to predict the recurrence of AF after catheter ablation by using artificial intelligence (AI)-enabled pre-ablation computed tomography (PVCT) images and pre-ablation clinical data. METHODS: A total of 638 drug-refractory paroxysmal atrial fibrillation (AF) patients undergone ablation were recruited. For model training, we used left atria (LA) acquired from pre-ablation PVCT slices (126,288 images). A total of 29 clinical variables were collected before ablation, including baseline characteristics, medical histories, laboratory results, transthoracic echocardiographic parameters, and 3D reconstructed LA volumes. The I-Score was applied to select variables for model training. For the prediction of one-year AF recurrence, PVCT deep-learning and clinical variable machine-learning models were developed. We then applied machine learning to ensemble the PVCT and clinical variable models. RESULTS: The PVCT model achieved an AUC of 0.63 in the test set. Various combinations of clinical variables selected by I-Score can yield an AUC of 0.72, which is significantly better than all variables or features selected by nonparametric statistics (AUCs of 0.66 to 0.69). The ensemble model (PVCT images and clinical variables) significantly improved predictive performance up to an AUC of 0.76 (sensitivity of 86.7% and specificity of 51.0%). CONCLUSIONS: Before ablation, AI-enabled PVCT combined with I-Score features was applicable in predicting recurrence in paroxysmal AF patients. Based on all possible predictors, the I-Score is capable of identifying the most influential combination.
Asunto(s)
Fibrilación Atrial , Ablación por Catéter , Humanos , Fibrilación Atrial/diagnóstico por imagen , Fibrilación Atrial/cirugía , Inteligencia Artificial , Resultado del Tratamiento , Atrios Cardíacos/diagnóstico por imagen , Atrios Cardíacos/cirugía , Ablación por Catéter/métodos , Recurrencia , Valor Predictivo de las PruebasRESUMEN
BACKGROUND: Traditional methods for investigating work hours rely on an employee's physical presence at the worksite. However, accurately identifying break times at the worksite and distinguishing remote work outside the worksite poses challenges in work hour estimations. Machine learning has the potential to differentiate between human-smartphone interactions at work and off work. OBJECTIVE: In this study, we aimed to develop a novel approach called "probability in work mode," which leverages human-smartphone interaction patterns and corresponding GPS location data to estimate work hours. METHODS: To capture human-smartphone interactions and GPS locations, we used the "Staff Hours" app, developed by our team, to passively and continuously record participants' screen events, including timestamps of notifications, screen on or off occurrences, and app usage patterns. Extreme gradient boosted trees were used to transform these interaction patterns into a probability, while 1-dimensional convolutional neural networks generated successive probabilities based on previous sequence probabilities. The resulting probability in work mode allowed us to discern periods of office work, off-work, breaks at the worksite, and remote work. RESULTS: Our study included 121 participants, contributing to a total of 5503 person-days (person-days represent the cumulative number of days across all participants on which data were collected and analyzed). The developed machine learning model exhibited an average prediction performance, measured by the area under the receiver operating characteristic curve, of 0.915 (SD 0.064). Work hours estimated using the probability in work mode (higher than 0.5) were significantly longer (mean 11.2, SD 2.8 hours per day) than the GPS-defined counterparts (mean 10.2, SD 2.3 hours per day; P<.001). This discrepancy was attributed to the higher remote work time of 111.6 (SD 106.4) minutes compared to the break time of 54.7 (SD 74.5) minutes. CONCLUSIONS: Our novel approach, the probability in work mode, harnessed human-smartphone interaction patterns and machine learning models to enhance the precision and accuracy of work hour investigation. By integrating human-smartphone interactions and GPS data, our method provides valuable insights into work patterns, including remote work and breaks, offering potential applications in optimizing work productivity and well-being.
Asunto(s)
Aprendizaje Automático , Teléfono Inteligente , Humanos , Algoritmos , Redes Neurales de la Computación , ProbabilidadRESUMEN
BACKGROUND: To develop deep learning models for medical diagnosis, it is important to collect more medical data from several medical institutions. Due to the regulations for privacy concerns, it is infeasible to collect data from various medical institutions to one institution for centralized learning. Federated Learning (FL) provides a feasible approach to jointly train the deep learning model with data stored in various medical institutions instead of collected together. However, the resulting FL models could be biased towards institutions with larger training datasets. METHODOLOGY: In this study, we propose the applicable method of Dynamically Synthetic Images for Federated Learning (DSIFL) that aims to integrate the information of local institutions with heterogeneous types of data. The main technique of DSIFL is to develop a synthetic method that can dynamically adjust the number of synthetic images similar to local data that are misclassified by the current model. The resulting global model can handle the diversity in heterogeneous types of data collected in local medical institutions by including the training of synthetic images similar to misclassified cases in local collections. RESULTS: In model performance evaluation metrics, we focus on the accuracy of each client's dataset. Finally, the accuracy of the model of DSIFL in the experiments can achieve the higher accuracy of the FL approach. CONCLUSION: In this study, we propose the framework of DSIFL that achieves improvements over the conventional FL approach. We conduct empirical studies with two kinds of medical images. We compare the performance by variants of FL vs. DSIFL approaches. The performance by individual training is used as the baseline, whereas the performance by centralized learning is used as the target for the comparison studies. The empirical findings suggest that the DSIFL has improved performance over the FL via the technique of dynamically synthetic images in training.
Asunto(s)
Benchmarking , Privacidad , Humanos , Investigación EmpíricaRESUMEN
We demonstrate that isomorphically mapping gray-level medical image matrices onto energy spaces underlying the framework of fast data density functional transform (fDDFT) can achieve the unsupervised recognition of lesion morphology. By introducing the architecture of geometric deep learning and metrics of graph neural networks, gridized density functionals of the fDDFT establish an unsupervised feature-aware mechanism with global convolutional kernels to extract the most likely lesion boundaries and produce lesion segmentation. An AutoEncoder-assisted module reduces the computational complexity from [Formula: see text] to [Formula: see text], thus efficiently speeding up global convolutional operations. We validate their performance utilizing various open-access datasets and discuss limitations. The inference time of each object in large three-dimensional datasets is 1.76 s on average. The proposed gridized density functionals have activation capability synergized with gradient ascent operations, hence can be modularized and embedded in pipelines of modern deep neural networks. Algorithms of geometric stability and similarity convergence also raise the accuracy of unsupervised recognition and segmentation of lesion images. Their performance achieves the standard requirement for conventional deep neural networks; the median dice score is higher than 0.75. The experiment shows that the synergy of fDDFT and a naïve neural network improves the training and inference time by 58% and 51%, respectively, and the dice score raises to 0.9415. This advantage facilitates fast computational modeling in interdisciplinary applications and clinical investigation.
Asunto(s)
Neoplasias Encefálicas , Aprendizaje Profundo , Neoplasias Encefálicas/clasificación , Neoplasias Encefálicas/patología , Humanos , Redes Neurales de la Computación , Reconocimiento de Normas Patrones Automatizadas , Diagnóstico por Imagen , Conjuntos de Datos como AsuntoRESUMEN
BACKGROUND: The World Health Organization reported that cardiovascular disease is the most common cause of death worldwide. On average, one person dies of heart disease every 26 min worldwide. Deep learning approaches are characterized by the appropriate combination of abnormal features based on numerous annotated images. The constructed convolutional neural network (CNN) model can identify normal states of reversible and irreversible myocardial defects and alert physicians for further diagnosis. METHODS: Cadmium zinc telluride single-photon emission computed tomography myocardial perfusion resting-state images were collected at Chang Gung Memorial Hospital, Kaohsiung Medical Center, Kaohsiung, Taiwan, and were analyzed with a deep learning convolutional neural network to classify myocardial perfusion images for coronary heart diseases. RESULTS: In these grey-scale images, the heart blood flow distribution was the most crucial feature. The deep learning technique of You Only Look Once was used to determine the myocardial defect area and crop the images. After surrounding noise had been eliminated, a three-dimensional CNN model was used to identify patients with coronary heart diseases. The prediction area under the curve, accuracy, sensitivity, and specificity was 90.97, 87.08, 86.49, and 87.41%, respectively. CONCLUSION: Our prototype system can considerably reduce the time required for image interpretation and improve the quality of medical care. It can assist clinical experts by offering accurate coronary heart disease diagnosis in practice.
Asunto(s)
Enfermedad de la Arteria Coronaria , Aprendizaje Profundo , Isquemia Miocárdica , Imagen de Perfusión Miocárdica , Humanos , Imagen de Perfusión Miocárdica/métodos , Tomografía Computarizada de Emisión de Fotón Único/métodos , Isquemia Miocárdica/diagnóstico por imagen , CorazónRESUMEN
BACKGROUND: In recent years, the progress and generalization surrounding portable ultrasonic probes has made ultrasound (US) a useful tool for physicians when making a diagnosis. With the advent of machine learning and deep learning, the development of a computer-aided diagnostic system for screening renal US abnormalities can assist general practitioners in the early detection of pediatric kidney diseases. OBJECTIVE: In this paper, we sought to evaluate the diagnostic performance of deep learning techniques to classify kidney images as normal and abnormal. METHODS: We chose 330 normal and 1269 abnormal pediatric renal US images for establishing a model for artificial intelligence. The abnormal images involved stones, cysts, hyperechogenicity, space-occupying lesions, and hydronephrosis. We performed preprocessing of the original images for subsequent deep learning. We redefined the final connecting layers for classification of the extracted features as abnormal or normal from the ResNet-50 pretrained model. The performances of the model were tested by a validation data set using area under the receiver operating characteristic curve, accuracy, specificity, and sensitivity. RESULTS: The deep learning model, 94 MB parameters in size, based on ResNet-50, was built for classifying normal and abnormal images. The accuracy, (%)/area under curve, of the validated images of stone, cyst, hyperechogenicity, space-occupying lesions, and hydronephrosis were 93.2/0.973, 91.6/0.940, 89.9/0.940, 91.3/0.934, and 94.1/0.996, respectively. The accuracy of normal image classification in the validation data set was 90.1%. Overall accuracy of (%)/area under curve was 92.9/0.959.. CONCLUSIONS: We established a useful, computer-aided model for automatic classification of pediatric renal US images in terms of normal and abnormal categories.
RESUMEN
The treatment of acute ischemic stroke is heavily time-dependent, and even though, with the most efficient treatment, the long-term functional outcome is still highly variable. In this current study, the authors selected acute ischemic stroke patients who were qualified for intravenous thrombolysis with recombinant tissue plasminogen activator and followed by intra-arterial thrombectomy. With primary outcome defined by the functional level in a 1-year follow-up, we hypothesize that patients with older age are at a disadvantage in post-stroke recovery. However, an age-threshold should be determined to help clinicians in selection of patients to undergo such therapy. This is a retrospective chart review study that include 92 stroke patients in Changhua Christian hospital with a total of 68 evaluation indexes recorded. The current study utilized the forward stepwise regression model whose Adj-R2 and P value in search of important variables for outcome prediction. The chngpt package in R indicated the threshold point of the age factor directing the better future functionality of the stroke patients. Datasets revealed the threshold of the age set at 79 the most appropriate. Admission Barthel Index, Age, ipsilateral internal carotid artery resistance index (ICA RI), ipsilateral vertebral artery (VA) PI, contralateral middle cerebral artery (MCA) stenosis, contralateral external carotid artery (ECA) RI, and in-hospital pneumonia are the significant predicting variables. The higher the age, in-hospital pneumonia, contralateral MCA stenosis, ipsilateral ICA RI and ipsilateral VA PI, the less likely patient to recover from functional deficits as the result of acute ischemic stroke; the higher the value of contralateral ECA RI and admission Barthel Index, the better chance to full functional recovery at 1-year follow up. Parameters of pre-intervention datasets could provide important information to aid first-line clinicians in decision making. Especially, in patients whose age is above 79 receives diminish return in the benefit to undergo such intervention and should be considered seriously by both the patients and the physicians.
Asunto(s)
Isquemia Encefálica , Estenosis Carotídea , Accidente Cerebrovascular Isquémico , Accidente Cerebrovascular , Factores de Edad , Arteria Carótida Interna , Constricción Patológica , Humanos , Accidente Cerebrovascular Isquémico/cirugía , Estudios Retrospectivos , Trombectomía , Activador de Tejido Plasminógeno , Resultado del TratamientoRESUMEN
Automated glaucoma detection using deep learning may increase the diagnostic rate of glaucoma to prevent blindness, but generalizable models are currently unavailable despite the use of huge training datasets. This study aims to evaluate the performance of a convolutional neural network (CNN) classifier trained with a limited number of high-quality fundus images in detecting glaucoma and methods to improve its performance across different datasets. A CNN classifier was constructed using EfficientNet B3 and 944 images collected from one medical center (core model) and externally validated using three datasets. The performance of the core model was compared with (1) the integrated model constructed by using all training images from the four datasets and (2) the dataset-specific model built by fine-tuning the core model with training images from the external datasets. The diagnostic accuracy of the core model was 95.62% but dropped to ranges of 52.5-80.0% on the external datasets. Dataset-specific models exhibited superior diagnostic performance on the external datasets compared to other models, with a diagnostic accuracy of 87.50-92.5%. The findings suggest that dataset-specific tuning of the core CNN classifier effectively improves its applicability across different datasets when increasing training images fails to achieve generalization.
RESUMEN
BACKGROUND CONTEXT: Computer-aided diagnosis with artificial intelligence (AI) has been used clinically, and ground truth generalizability is important for AI performance in medical image analyses. The AI model was trained on one specific group of older adults (agedâ§60) has not yet been shown to work equally well in a younger adult group (aged 18-59). PURPOSE: To compare the performance of the developed AI model with ensemble method trained with the ground truth for those aged 60 years or older in identifying vertebral fractures (VFs) on plain lateral radiographs of spine (PLRS) between younger and older adult populations. STUDY DESIGN/SETTING: Retrospective analysis of PLRS in a single medical institution. OUTCOME MEASURES: Accuracy, sensitivity, specificity, and interobserver reliability (kappa value) were used to compare diagnostic performance of the AI model and subspecialists' consensus between the two groups. METHODS: Between January 2016 and December 2018, the ground truth of 941 patients (one PLRS per person) aged 60 years and older with 1101 VFs and 6358 normal vertebrae was used to set up the AI model. The framework of the developed AI model includes: object detection with You Only Look Once Version 3 (YOLOv3) at T0-L5 levels in the PLRS, data pre-preprocessing with image-size and quality processing, and AI ensemble model (ResNet34, DenseNet121, and DenseNet201) for identifying or grading VFs. The reported overall accuracy, sensitivity and specificity were 92%, 91% and 93%, respectively, and external validation was also performed. Thereafter, patients diagnosed as VFs and treated in our institution during October 2019 to August 2020 were the study group regardless of age. In total, 258 patients (339 VFs and 1725 normal vertebrae) in the older adult population (mean age 78±10.4; range, 60-106) were enrolled. In the younger adult population (mean age 36±9.43; range, 20-49), 106 patients (120 VFs and 728 normal vertebrae) were enrolled. After identification and grading of VFs based on the Genant method with consensus between two subspecialists', VFs in each PLRS with human labels were defined as the testing dataset. The corresponding CT or MRI scan was used for labeling in the PLRS. The bootstrap method was applied to the testing dataset. RESULTS: The model for clinical application, Digital Imaging and Communications in Medicine (DICOM) format, is uploaded directly (available at: http://140.113.114.104/vght_demo/svf-model (grading) and http://140.113.114.104/vght demo/svf-model2 (labeling). Overall accuracy, sensitivity and specificity in the older adult population were 93.36% (95% CI 93.34%-93.38%), 88.97% (95% CI 88.59%-88.99%) and 94.26% (95% CI 94.23%-94.29%), respectively. Overall accuracy, sensitivity and specificity in the younger adult population were 93.75% (95% CI 93.7%-93.8%), 65.00% (95% CI 64.33%-65.67%) and 98.49% (95% CI 98.45%-98.52%), respectively. Accuracy reached 100% in VFs grading once the VFs were labeled accurately. The unique pattern of limbus-like VFs, 43 (35.8%) were investigated only in the younger adult population. If limbus-like VFs from the dataset were not included, the accuracy increased from 93.75% (95% CI 93.70%-93.80%) to 95.78% (95% CI 95.73%-95.82%), sensitivity increased from 65.00% (95% CI 64.33%-65.67%) to 70.13% (95% CI 68.98%-71.27%) and specificity remained unchanged at 98.49% (95% CI 98.45%-98.52%), respectively. The main causes of false negative results in older adults were patients' lung markings, diaphragm or bowel airs (37%, n=14) followed by type I fracture (29%, n=11). The main causes of false negatives in younger adults were limbus-like VFs (45%, n=19), followed by type I fracture (26%, n=11). The overall kappa between AI discrimination and subspecialists' consensus in the older and younger adult populations were 0.77 (95% CI, 0.733-0.805) and 0.72 (95% CI, 0.6524-0.80), respectively. CONCLUSIONS: The developed VF-identifying AI ensemble model based on ground truth of older adults achieved better performance in identifying VFs in older adults and non-fractured thoracic and lumbar vertebrae in the younger adults. Different age distribution may have potential disease diversity and implicate the effect of ground truth generalizability on the AI model performance.
Asunto(s)
Fracturas de la Columna Vertebral , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Inteligencia Artificial , Humanos , Vértebras Lumbares/lesiones , Persona de Mediana Edad , Reproducibilidad de los Resultados , Estudios Retrospectivos , Fracturas de la Columna Vertebral/diagnóstico por imagen , Adulto JovenRESUMEN
The extraction of brain tumor tissues in 3D Brain Magnetic Resonance Imaging (MRI) plays an important role in diagnosis before the gamma knife radiosurgery (GKRS). In this article, the post-contrast T1 whole-brain MRI images had been collected by Taipei Veterans General Hospital (TVGH) and stored in DICOM format (dated from 1999 to 2018). The proposed method starts with the active contour model to get the region of interest (ROI) automatically and enhance the image contrast. The segmentation models are trained by MRI images with tumors to avoid imbalanced data problem under model construction. In order to achieve this objective, a two-step ensemble approach is used to establish such diagnosis, first, classify whether there is any tumor in the image, and second, segment the intracranial metastatic tumors by ensemble neural networks based on 2D U-Net architecture. The ensemble for classification and segmentation simultaneously also improves segmentation accuracy. The result of classification achieves a F1-measure of [Formula: see text], while the result of segmentation achieves an IoU of [Formula: see text] and a DICE score of [Formula: see text]. Significantly reduce the time for manual labeling from 30 min to 18 s per patient.
Asunto(s)
Neoplasias Encefálicas/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Radiocirugia/métodos , Neoplasias Encefálicas/cirugía , Humanos , Imagen por Resonancia Magnética/métodos , Modelos Teóricos , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND: This study aimed to compare the prediction performance of two-dimensional (2D) and three-dimensional (3D) semantic segmentation models for intracranial metastatic tumors with a volume ≥ 0.3 mL. METHODS: We used postcontrast T1 whole-brain magnetic resonance (MR), which was collected from Taipei Veterans General Hospital (TVGH). Also, the study was approved by the institutional review board (IRB) of TVGH. The 2D image segmentation model does not fully use the spatial information between neighboring slices, whereas the 3D segmentation model does. We treated the U-Net as the basic model for 2D and 3D architectures. RESULTS: For the prediction of intracranial metastatic tumors, the area under the curve (AUC) of the 3D model was 87.6% and that of the 2D model was 81.5%. CONCLUSION: Building a semantic segmentation model based on 3D deep convolutional neural networks might be crucial to achieve a high detection rate in clinical applications for intracranial metastatic tumors.
Asunto(s)
Neoplasias Encefálicas/diagnóstico por imagen , Aprendizaje Profundo , Imagenología Tridimensional , Imagen por Resonancia Magnética , Metástasis de la Neoplasia/diagnóstico por imagen , HumanosRESUMEN
BACKGROUND: In clinical applications, mucosal healing is a therapeutic goal in patients with ulcerative colitis (UC). Endoscopic remission is associated with lower rates of colectomy, relapse, hospitalization, and colorectal cancer. Differentiation of mucosal inflammatory status depends on the experience and subjective judgments of clinical physicians. We developed a computer-aided diagnostic system using deep learning and machine learning (DLML-CAD) to accurately diagnose mucosal healing in UC patients. METHODS: We selected 856 endoscopic colon images from 54 UC patients (643 images with endoscopic score 0-1 and 213 with score 2-3) from the endoscopic image database at Tri-Service General Hospital, Taiwan. Endoscopic grading using the Mayo endoscopic subscore (MES 0-3) was performed by two reviewers. A pretrained neural network extracted image features, which were used to train three different classifiers-deep neural network (DNN), support vector machine (SVM), and k-nearest neighbor (k-NN) network. RESULTS: DNN classified MES 0 to 1, representing mucosal healing, vs MES 2 to 3 images with 93.8% accuracy (sensitivity 84.6%, specificity 96.9%); SVM had 94.1% accuracy (sensitivity 89.2%, specificity 95.8%); and k-NN had 93.4% accuracy (sensitivity 86.2%, specificity 95.8%). Combined, ensemble learning achieved 94.5% accuracy (sensitivity 89.2%, specificity 96.3%). The system further differentiated between MES 0, representing complete mucosal healing, and MES 1 images with 89.1% accuracy (sensitivity 82.3%, specificity 92.2%). CONCLUSION: Our DLML-CAD diagnosis achieved 94.5% accuracy for endoscopic mucosal healing and 89.0% accuracy for complete mucosal healing. This system can provide clinical physicians with an accurate auxiliary diagnosis in treating UC.
Asunto(s)
Colitis Ulcerosa , Aprendizaje Profundo , Endoscopía , Membrana Mucosa/lesiones , Cicatrización de Heridas , Humanos , Membrana Mucosa/diagnóstico por imagen , Estudios Retrospectivos , Índice de Severidad de la Enfermedad , TaiwánRESUMEN
Polypoidal choroidal vasculopathy (PCV) and neovascular age-related macular degeneration (nAMD) share some similarity in clinical imaging manifestations. However, their disease entity and treatment strategy as well as visual outcomes are very different. To distinguish these two vision-threatening diseases is somewhat challenging but necessary. In this study, we propose a new artificial intelligence model using an ensemble stacking technique, which combines a color fundus photograph-based deep learning (DL) model and optical coherence tomography-based biomarkers, for differentiation of PCV from nAMD. Furthermore, we introduced multiple correspondence analysis, a method of transforming categorical data into principal components, to handle the dichotomous data for combining with another image DL system. This model achieved a robust performance with an accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of 83.67%, 80.76%, 84.72%, and 88.57%, respectively, by training nearly 700 active cases with suitable imaging quality and transfer learning architecture. This work could offer an alternative method of developing a multimodal DL model, improve its efficiency for distinguishing different diseases, and facilitate the broad application of medical engineering in a DL model design.