Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 22.819
Filtrar
2.
Comput Biol Med ; 121: 103792, 2020 06.
Artículo en Inglés | MEDLINE | ID: mdl-32568675

RESUMEN

The novel coronavirus 2019 (COVID-2019), which first appeared in Wuhan city of China in December 2019, spread rapidly around the world and became a pandemic. It has caused a devastating effect on both daily lives, public health, and the global economy. It is critical to detect the positive cases as early as possible so as to prevent the further spread of this epidemic and to quickly treat affected patients. The need for auxiliary diagnostic tools has increased as there are no accurate automated toolkits available. Recent findings obtained using radiology imaging techniques suggest that such images contain salient information about the COVID-19 virus. Application of advanced artificial intelligence (AI) techniques coupled with radiological imaging can be helpful for the accurate detection of this disease, and can also be assistive to overcome the problem of a lack of specialized physicians in remote villages. In this study, a new model for automatic COVID-19 detection using raw chest X-ray images is presented. The proposed model is developed to provide accurate diagnostics for binary classification (COVID vs. No-Findings) and multi-class classification (COVID vs. No-Findings vs. Pneumonia). Our model produced a classification accuracy of 98.08% for binary classes and 87.02% for multi-class cases. The DarkNet model was used in our study as a classifier for the you only look once (YOLO) real time object detection system. We implemented 17 convolutional layers and introduced different filtering on each layer. Our model (available at (https://github.com/muhammedtalo/COVID-19)) can be employed to assist radiologists in validating their initial screening, and can also be employed via cloud to immediately screen patients.


Asunto(s)
Betacoronavirus , Infecciones por Coronavirus/diagnóstico por imagen , Infecciones por Coronavirus/diagnóstico , Aprendizaje Profundo , Redes Neurales de la Computación , Neumonía Viral/diagnóstico por imagen , Neumonía Viral/diagnóstico , Interpretación de Imagen Radiográfica Asistida por Computador , Biología Computacional , Infecciones por Coronavirus/clasificación , Bases de Datos Factuales , Diagnóstico por Computador , Femenino , Humanos , Pulmón/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Pandemias/clasificación , Neumonía/diagnóstico , Neumonía/diagnóstico por imagen , Neumonía Viral/clasificación
3.
An Acad Bras Cienc ; 92(1): e20190554, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32491128

RESUMEN

Skin is the outermost and largest organ of the human body that protects us from the external agents. Among the various types of diseases affecting the skin, melanoma (skin cancer) is the most dangerous and deadliest disease. Though it is one of the dangerous forms of cancer, it has a high survival rate if and only if it is diagnosed at the earliest. In this study, skin cancer classification (SCC) system is developed using dermoscopic images. It is considered as a classification problem with the help of Bendlet Transform (BT) as features and Support Vector Machine (SVM) as a classifier. First, the unwanted information's such as hair and noises are removed using median filtering approach. Then, directional representation based feature extraction system that precisely classifies curvature, location and orientation is employed. Finally, two SVM classifiers are designed for the classification. The performance of the SCC system based on Bendlet is superior to other image representation systems such as Wavelets, Curvelets, Contourlets and Shearlets.


Asunto(s)
Dermoscopía/métodos , Melanoma/diagnóstico por imagen , Neoplasias Cutáneas/diagnóstico por imagen , Máquina de Vectores de Soporte , Diagnóstico por Computador , Humanos , Reproducibilidad de los Resultados , Sensibilidad y Especificidad
5.
Medicine (Baltimore) ; 99(26): e20787, 2020 Jun 26.
Artículo en Inglés | MEDLINE | ID: mdl-32590758

RESUMEN

Convolutional neural networks (CNNs), a particular type of deep learning architecture, are positioned to become one of the most transformative technologies for medical applications. The aim of the current study was to evaluate the efficacy of deep CNN algorithm for the identification and classification of dental implant systems.A total of 5390 panoramic and 5380 periapical radiographic images from 3 types of dental implant systems, with similar shape and internal conical connection, were randomly divided into training and validation dataset (80%) and a test dataset (20%). We performed image preprocessing and transfer learning techniques, based on fine-tuned and pre-trained deep CNN architecture (GoogLeNet Inception-v3). The test dataset was used to assess the accuracy, sensitivity, specificity, receiver operating characteristic curve, area under the receiver operating characteristic curve (AUC), and confusion matrix compared between deep CNN and periodontal specialist.We found that the deep CNN architecture (AUC = 0.971, 95% confidence interval 0.963-0.978) and board-certified periodontist (AUC = 0.925, 95% confidence interval 0.913-0.935) showed reliable classification accuracies.This study demonstrated that deep CNN architecture is useful for the identification and classification of dental implant systems using panoramic and periapical radiographic images.


Asunto(s)
Algoritmos , Implantes Dentales , Diagnóstico por Computador/métodos , Redes Neurales de la Computación , Radiografía Dental/métodos , Aprendizaje Profundo , Implantes Dentales/clasificación , Implantes Dentales/normas , Humanos , Proyectos Piloto , Radiografía Panorámica/métodos , Reproducibilidad de los Resultados , Resultado del Tratamiento
6.
Medicine (Baltimore) ; 99(22): e20419, 2020 May 29.
Artículo en Inglés | MEDLINE | ID: mdl-32481437

RESUMEN

We explored the potential of combining carcinoembryonic antigen (CEA) and salivary mRNAs for gastric cancer (GC) detection.This study included 2 phases of study: a biomarker discovery phase and an independent validation phase. In the discovery phase, we measured CEA levels in blood samples and expression level of messenger RNAs (SPINK7, PPL, SEMA4B, SMAD4) in saliva samples of 140 GC patients and 140 healthy controls. We evaluated the clinical performance of each biomarker and developed a predictive model using machine-learning algorithm to differentiate GC patients and healthy controls.Our biomarker panel successfully discriminated GC patients from healthy controls with both high sensitivity (0.94) and high specificity (0.91). We next applied our biomarker panel in the independent validation phase, in which we recruited a new patient cohort of 60 GC patients and 60 healthy controls. Using our biomarker panel, the GC patients were discriminated from healthy controls in the validation phase, with sensitivity of 0.92 and specificity of 0.87.A combination of blood CEA and salivary messenger RNA could be a promising approach to detect GC.


Asunto(s)
Antígeno Carcinoembrionario/metabolismo , ARN Mensajero/metabolismo , Neoplasias Gástricas/diagnóstico , Biomarcadores de Tumor/metabolismo , Estudios de Cohortes , Diagnóstico por Computador , Femenino , Humanos , Aprendizaje Automático , Masculino , Persona de Mediana Edad , Plaquinas/metabolismo , Prueba de Estudio Conceptual , Saliva/metabolismo , Semaforinas/metabolismo , Sensibilidad y Especificidad , Inhibidores de Serinpeptidasas Tipo Kazal/metabolismo , Proteína Smad4/metabolismo , Neoplasias Gástricas/metabolismo
8.
Radiology ; 295(3): 517-526, 2020 Jun.
Artículo en Inglés | MEDLINE | ID: mdl-32228293

RESUMEN

Background Higher peak enhancement and washout component values measured on preoperative breast MRI scans with computer-aided diagnosis (CAD) are presumed to be associated with worse recurrence-free survival. Purpose To investigate whether CAD-extracted kinetic features of breast cancer and the heterogeneity of these features at preoperative MRI are associated with distant metastasis-free survival in women with invasive breast cancer. Materials and Methods Consecutive women with newly diagnosed invasive breast cancer who underwent preoperative MRI were retrospectively evaluated between 2011 and 2012. A commercially available CAD system was used to extract the peak enhancement and delayed enhancement profiles of each breast cancer case from preoperative MRI data. The kinetic heterogeneity of these features (a measure of heterogeneity in the proportions of tumor pixels with delayed washout, plateau, and persistent components within a tumor) was calculated to evaluate intratumoral heterogeneity. Cox proportional hazards models were used to investigate the associations between CAD-extracted kinetic features and distant metastasis-free survival after adjusting for clinical-pathologic factors. Results A total of 276 consecutive women (mean age, 53 years) were evaluated. In 28 of 276 (10.1%) women, distant metastasis developed at a median follow-up of 79 months. A higher degree of kinetic heterogeneity was observed in women with distant metastases than in those without distant metastases (mean, 0.70 ± 0.2 vs 0.43 ± 0.3; P < .001). Multivariable Cox proportional hazards analysis revealed that a higher degree of kinetic heterogeneity (hazard ratio [HR], 19.2; 95% confidence interval [CI]: 4.2, 87.1; P < .001), higher peak enhancement (HR, 1.001; 95% CI: 1.000, 1.002; P = .045), the presence of lymphovascular invasion (HR, 3.3; 95% CI: 1.5, 7.5; P = .004), and a higher histologic grade (ie, grade 3) (HR, 2.2; 95% CI: 1.0, 4.9; P = .044) were associated with worse distant metastasis-free survival. Conclusion Higher values of kinetic heterogeneity and peak enhancement as determined with computer-aided diagnosis of preoperative MRI were associated with worse distant metastasis-free survival in women with invasive breast cancer. © RSNA, 2020 See also the editorial by El Khouli and Jacobs in this issue.


Asunto(s)
Neoplasias de la Mama/diagnóstico por imagen , Diagnóstico por Computador/métodos , Imagen por Resonancia Magnética/métodos , Mamografía/métodos , Neoplasias de la Mama/mortalidad , Neoplasias de la Mama/cirugía , Femenino , Estudios de Seguimiento , Humanos , Metástasis Linfática , Persona de Mediana Edad , Invasividad Neoplásica , Cuidados Preoperatorios , Supervivencia sin Progresión , Modelos de Riesgos Proporcionales , Estudios Retrospectivos
9.
Radiology ; 295(3): 626-637, 2020 06.
Artículo en Inglés | MEDLINE | ID: mdl-32255417

RESUMEN

Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.


Asunto(s)
Inteligencia Artificial , Encefalopatías/diagnóstico por imagen , Encéfalo/diagnóstico por imagen , Diagnóstico por Computador/métodos , Imagen por Resonancia Magnética/métodos , Adulto , Anciano , Diagnóstico Diferencial , Femenino , Humanos , Masculino , Persona de Mediana Edad , Enfermedades Raras , Estudios Retrospectivos , Sensibilidad y Especificidad
10.
Medicine (Baltimore) ; 99(16): e19664, 2020 Apr.
Artículo en Inglés | MEDLINE | ID: mdl-32311939

RESUMEN

To examine the correlation of qualitative and quantitative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) results with 95-gene classifier or Curebest 95-gene classifier Breast (95GC) results for recurrence prediction in estrogen receptor-positive breast cancer (ERPBC).This retrospective study included 78 ERPBC patients (age range, 24-74 years) classified into high- (n = 33) and low- (n = 45) risk groups for recurrence based on 95GC and who underwent DCE-MRI between July 2006 and November 2012. For qualitative evaluation, mass shape, margin, and internal enhancement based on BI-RADS MRI lexicon and multiplicity were determined by consensus interpretation by 2 breast radiologists. For quantitative evaluation, mass size, volume ratios of the DCE-MRI kinetics, and both the kurtosis and the skewness of the intensity histogram for the whole mass in the initial and delayed phases were determined. Differences between the 2 risk-groups were analyzed using univariate logistic regression analyses and multiple logistic regression analyses. Receiver-operating characteristic curve cut-off values were used to define the groups.As for the qualitative findings, the difference between the 2 groups was not significant. For the quantitative data, the volume ratio of "medium" in the initial phase differed significantly between the 2 groups (P = .049). The volume ratio of "medium" (P = .006) and of "slow-persistent" (P = .005), and the delayed phase kurtosis (P = .012) in the univariate logistic regression analyses, and in the multiple logistic regression, volume ratio of "medium" >38.9% and delayed phase kurtosis >3.31 were identified as significant high-risk indicators (odds ratio, 5.83 and 3.55; 95% confidence interval, 1.58 to 21.42 and 1.24 to 10.15; P = .008 and P = .018, respectively).A high volume ratio of "medium" in the initial phase and/or high kurtosis in the delayed phase for quantitative evaluation could predict high ERPBC recurrence risk based on 95GC.


Asunto(s)
Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/genética , Imagen por Resonancia Magnética , Recurrencia Local de Neoplasia/diagnóstico , Adulto , Anciano , Diagnóstico por Computador , Femenino , Predisposición Genética a la Enfermedad , Humanos , Persona de Mediana Edad , Pronóstico , Receptores Estrogénicos , Estudios Retrospectivos , Medición de Riesgo/métodos , Adulto Joven
11.
PLoS One ; 15(4): e0231113, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32294085

RESUMEN

BACKGROUND: Stroke recognition systems have been developed to reduce time delays, however, a comprehensive triaging score identifying stroke subtypes is needed to guide appropriate management. We aimed to develop a prehospital scoring system for rapid stroke recognition and identify stroke subtype simultaneously. METHODS AND FINDINGS: In prospective database of regional emergency and stroke center, Clinical Information, Vital signs, and Initial Labs (CIVIL) of 1,599 patients suspected of acute stroke was analyzed from an automatically-stored electronic health record. Final confirmation was performed with neuroimaging. Using multiple regression analyses, we determined independent predictors of tier 1 (true-stroke or not), tier 2 (hemorrhagic stroke or not), and tier 3 (emergent large vessel occlusion [ELVO] or not). The diagnostic performance of the stepwise CIVIL scoring system was investigated using internal validation. A new scoring system characterized by a stepwise clinical assessment has been developed in three tiers. Tier 1: Seven CIVIL-AS3A2P items (total score from -7 to +6) were deduced for true stroke as Age (≥ 60 years); Stroke risks without Seizure or psychiatric disease, extreme Sugar; "any Asymmetry", "not Ambulating"; abnormal blood Pressure at a cut-off point ≥ 1 with diagnostic sensitivity of 82.1%, specificity of 56.4%. Tier 2: Four items for hemorrhagic stroke were identified as the CIVIL-MAPS indicating Mental change, Age below 60 years, high blood Pressure, no Stroke risks with cut-point ≥ 2 (sensitivity 47.5%, specificity 85.4%). Tier 3: For ELVO diagnosis: we applied with CIVIL-GFAST items (Gaze, Face, Arm, Speech) with cut-point ≥ 3 (sensitivity 66.5%, specificity 79.8%). The main limitation of this study is its retrospective nature and require a prospective validation of the CIVIL scoring system. CONCLUSIONS: The CIVIL score is a comprehensive and versatile system that recognizes strokes and identifies the stroke subtype simultaneously.


Asunto(s)
Diagnóstico por Computador/métodos , Registros Electrónicos de Salud/estadística & datos numéricos , Accidente Cerebrovascular/diagnóstico , Triaje/métodos , Anciano , Anciano de 80 o más Años , Encéfalo/diagnóstico por imagen , Diagnóstico Diferencial , Servicio de Urgencia en Hospital/estadística & datos numéricos , Estudios de Factibilidad , Femenino , Humanos , Masculino , Anamnesis , Persona de Mediana Edad , Neuroimagen , Valor Predictivo de las Pruebas , Estudios Retrospectivos , Sensibilidad y Especificidad , Accidente Cerebrovascular/sangre
13.
AJR Am J Roentgenol ; 214(6): 1445-1452, 2020 06.
Artículo en Inglés | MEDLINE | ID: mdl-32319794

RESUMEN

OBJECTIVE. The objective of this study was to assess the impact of artificial intelligence (AI)-based decision support (DS) on breast ultrasound (US) lesion assessment. MATERIALS AND METHODS. A multicenter retrospective review of 900 breast lesions (470/900 [52.2%] benign; 430/900 [47.8%] malignant) on US by 15 physicians (11 radiologists, two surgeons, two obstetrician/gynecologists). An AI system (Koios DS for Breast, Koios Medical) evaluated images and assigned them to one of four categories: benign, probably benign, suspicious, and probably malignant. Each reader reviewed cases twice: 750 cases with US only or with US plus DS; 4 weeks later, cases were reviewed in the opposite format. One hundred fifty additional cases were presented identically in each session. DS and reader sensitivity, specificity, and positive likelihood ratios (PLRs) were calculated as well as reader AUCs with and without DS. The Kendall τ-b correlation coefficient was used to assess intraand interreader variability. RESULTS. Mean reader AUC for cases reviewed with US only was 0.83 (95% CI, 0.78-0.89); for cases reviewed with US plus DS, mean AUC was 0.87 (95% CI, 0.84-0.90). PLR for the DS system was 1.98 (95% CI, 1.78-2.18) and was higher than the PLR for all readers but one. Fourteen readers had better AUC with US plus DS than with US only. Mean Kendall τ-b for US-only interreader variability was 0.54 (95% CI, 0.53-0.55); for US plus DS, it was 0.68 (95% CI, 0.67-0.69). Intrareader variability improved with DS; class switching (defined as crossing from BI-RADS category 3 to BI-RADS category 4A or above) occurred in 13.6% of cases with US only versus 10.8% of cases with US plus DS (p = 0.04). CONCLUSION. AI-based DS improves accuracy of sonographic breast lesion assessment while reducing inter- and intraobserver variability.


Asunto(s)
Inteligencia Artificial , Neoplasias de la Mama/diagnóstico por imagen , Técnicas de Apoyo para la Decisión , Ultrasonografía Mamaria , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Biopsia , Neoplasias de la Mama/patología , Diagnóstico por Computador , Femenino , Humanos , Persona de Mediana Edad , Estudios Retrospectivos , Sensibilidad y Especificidad
14.
BMC Infect Dis ; 20(1): 255, 2020 Mar 30.
Artículo en Inglés | MEDLINE | ID: mdl-32228479

RESUMEN

BACKGROUND: Gastrointestinal tuberculosis (TB) is diagnostically challenging; therefore, many cases are treated presumptively. We aimed to describe features and outcomes of gastrointestinal TB, determine whether a clinical algorithm could distinguish TB from non-TB diagnoses, and calculate accuracy of diagnostic tests. METHODS: We conducted a prospective cohort study of hospitalized patients in Kota Kinabalu, Malaysia, with suspected gastrointestinal TB. We recorded clinical and laboratory characteristics and outcomes. Tissue samples were submitted for histology, microscopy, culture and GeneXpert MTB/RIF®. Patients were followed for up to 2 years. RESULTS: Among 88 patients with suspected gastrointestinal TB, 69 were included in analyses; 52 (75%) had a final diagnosis of gastrointestinal TB; 17 had a non-TB diagnosis. People with TB were younger (42.7 versus 61.5 years, p = 0.01) and more likely to have weight loss (91% versus 64%, p = 0.03). An algorithm using age < 44, weight loss, cough, fever, no vomiting, albumin > 26 g/L, platelets > 340 × 109/L and immunocompromise had good specificity (96.2%) in predicting TB, but very poor sensitivity (16.0%). GeneXpert® performed very well on gastrointestinal biopsies (sensitivity 95.7% versus 35.0% for culture against a gold standard composite case definition of confirmed TB). Most patients (79%) successfully completed treatment and no treatment failure occurred, however adverse events (21%) and mortality (13%) among TB cases were high. We found no evidence that 6 months of treatment was inferior to longer courses. CONCLUSIONS: The prospective design provides important insights for clinicians managing gastrointestinal TB. We recommend wider implementation of high-performing diagnostic tests such as GeneXpert® on extra-pulmonary samples.


Asunto(s)
Tuberculosis Gastrointestinal/diagnóstico , Adolescente , Adulto , Distribución por Edad , Anciano , Anciano de 80 o más Años , Algoritmos , Estudios de Cohortes , Diagnóstico por Computador , Pruebas Diagnósticas de Rutina , Femenino , Humanos , Malasia , Masculino , Microscopía , Persona de Mediana Edad , Mycobacterium tuberculosis/aislamiento & purificación , Estudios Prospectivos , Sensibilidad y Especificidad , Tuberculosis Gastrointestinal/tratamiento farmacológico , Tuberculosis Gastrointestinal/microbiología , Tuberculosis Gastrointestinal/patología
15.
Gastroenterol. hepatol. (Ed. impr.) ; 43(4): 222-232, abr. 2020. ilus, tab
Artículo en Español | IBECS | ID: ibc-190804

RESUMEN

El diagnóstico asistido por computador (DAC) constituye una herramienta con gran potencial para ayudar a los endoscopistas en las tareas de detección y clasificación histológica de los pólipos colorrectales. En los últimos años se han descrito diferentes tecnologías y ha aumentado la evidencia sobre su potencial utilidad, lo que ha generado grandes expectativas en las sociedades científicas. Sin embargo, la mayoría de estos trabajos son retrospectivos y utilizan imágenes de diferente calidad y características que son analizadas off-line. En esta revisión se pretende familiarizar a los gastroenterólogos con los métodos computacionales y las particularidades de la imagen endoscópica con impacto en el análisis del procesamiento de imágenes. Finalmente, se exponen las bases de datos de imágenes disponibles de forma pública que son necesarias para poder comparar y confirmar los resultados obtenidos con diferentes métodos


Computer-aided diagnosis (CAD) is a tool with great potential to help endoscopists in the tasks of detecting and histologically classifying colorectal polyps. In recent years, different technologies have been described and their potential utility has been increasingly evidenced, which has generated great expectations among scientific societies. However, most of these works are retrospective and use images of different quality and characteristics which are analysed off line. This review aims to familiarise gastroenterologists with computational methods and the particularities of endoscopic imaging, which have an impact on image processing analysis. Finally, the publicly available image databases, needed to compare and confirm the results obtained with different methods, are presented


Asunto(s)
Humanos , Pólipos/clasificación , Pólipos/diagnóstico por imagen , Colonografía Tomográfica Computarizada/métodos , Diagnóstico por Computador/métodos , Inteligencia Artificial
16.
Radiology ; 295(2): 407-415, 2020 05.
Artículo en Inglés | MEDLINE | ID: mdl-32181729

RESUMEN

Background Brain metastases are manually identified during stereotactic radiosurgery (SRS) treatment planning, which is time consuming and potentially challenging. Purpose To develop and investigate deep learning (DL) methods for detecting brain metastasis with MRI to aid in treatment planning for SRS. Materials and Methods In this retrospective study, contrast material-enhanced three-dimensional T1-weighted gradient-echo MRI scans from patients who underwent gamma knife SRS from January 2011 to August 2018 were analyzed. Brain metastases were manually identified and contoured by neuroradiologists and treating radiation oncologists. DL single-shot detector (SSD) algorithms were constructed and trained to map axial MRI slices to a set of bounding box predictions encompassing metastases and associated detection confidences. Performances of different DL SSDs were compared for per-lesion metastasis-based detection sensitivity and positive predictive value (PPV) at a 50% confidence threshold. For the highest-performing model, detection performance was analyzed by using free-response receiver operating characteristic analysis. Results Two hundred sixty-six patients (mean age, 60 years ± 14 [standard deviation]; 148 women) were randomly split into 80% training and 20% testing groups (212 and 54 patients, respectively). For the testing group, sensitivity of the highest-performing (baseline) SSD was 81% (95% confidence interval [CI]: 80%, 82%; 190 of 234) and PPV was 36% (95% CI: 35%, 37%; 190 of 530). For metastases measuring at least 6 mm, sensitivity was 98% (95% CI: 97%, 99%; 130 of 132) and PPV was 36% (95% CI: 35%, 37%; 130 of 366). Other models (SSD with a ResNet50 backbone, SSD with focal loss, and RetinaNet) yielded lower sensitivities of 73% (95% CI: 72%, 74%; 171 of 234), 77% (95% CI: 76%, 78%; 180 of 234), and 79% (95% CI: 77%, 81%; 184 of 234), respectively, and lower PPVs of 29% (95% CI: 28%, 30%; 171 of 581), 26% (95% CI: 26%, 26%; 180 of 681), and 13% (95% CI: 12%, 14%; 184 of 1412). Conclusion Deep-learning single-shot detector models detected nearly all brain metastases that were 6 mm or larger with limited false-positive findings using postcontrast T1-weighted MRI. © RSNA, 2020 See also the editorial by Kikinis and Wells in this issue.


Asunto(s)
Neoplasias Encefálicas/diagnóstico por imagen , Neoplasias Encefálicas/radioterapia , Neoplasias Encefálicas/secundario , Aprendizaje Profundo , Diagnóstico por Computador/métodos , Imagen por Resonancia Magnética/métodos , Radiocirugia/métodos , Medios de Contraste , Femenino , Humanos , Imagenología Tridimensional , Masculino , Persona de Mediana Edad , Estudios Retrospectivos
18.
PLoS One ; 15(3): e0229226, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32163427

RESUMEN

In medicine, a misdiagnosis or the absence of specialists can affect the patient's health, leading to unnecessary tests and increasing the costs of healthcare. In particular, the lack of specialists in otolaryngology in third world countries forces patients to seek medical attention from general practitioners, whom might not have enough training and experience for making correct diagnosis in this field. To tackle this problem, we propose and test a computer-aided system based on machine learning models and image processing techniques for otoscopic examination, as a support for a more accurate diagnosis of ear conditions at primary care before specialist referral; in particular, for myringosclerosis, earwax plug, and chronic otitis media. To characterize the tympanic membrane and ear canal for each condition, we implemented three different feature extraction methods: color coherence vector, discrete cosine transform, and filter bank. We also considered three machine learning algorithms: support vector machine (SVM), k-nearest neighbor (k-NN) and decision trees to develop the ear condition predictor model. To conduct the research, our database included 160 images as testing set and 720 images as training and validation sets of 180 patients. We repeatedly trained the learning models using the training dataset and evaluated them using the validation dataset to thus obtain the best feature extraction method and learning model that produce the highest validation accuracy. The results showed that the SVM and k-NN presented the best performance followed by decision trees model. Finally, we performed a classification stage -i.e., diagnosis- using testing data, where the SVM model achieved an average classification accuracy of 93.9%, average sensitivity of 87.8%, average specificity of 95.9%, and average positive predictive value of 87.7%. The results show that this system might be used for general practitioners as a reference to make better decisions in the ear pathologies diagnosis.


Asunto(s)
Enfermedades del Oído/diagnóstico por imagen , Interpretación de Imagen Asistida por Computador/métodos , Adolescente , Adulto , Cerumen/diagnóstico por imagen , Niño , Árboles de Decisión , Diagnóstico por Computador/métodos , Diagnóstico Precoz , Humanos , Masculino , Persona de Mediana Edad , Miringoesclerosis/diagnóstico por imagen , Otitis Media/diagnóstico por imagen , Sensibilidad y Especificidad , Máquina de Vectores de Soporte , Adulto Joven
19.
Einstein (Sao Paulo) ; 18: eAO4948, 2020.
Artículo en Inglés, Portugués | MEDLINE | ID: mdl-32159604

RESUMEN

OBJECTIVE: To develop a computational algorithm applied to magnetic resonance imaging for automatic segmentation of brain tumors. METHODS: A total of 130 magnetic resonance images were used in the T1c, T2 and FSPRG T1C sequences and in the axial, sagittal and coronal planes of patients with brain cancer. The algorithms employed contrast correction, histogram normalization and binarization techniques to disconnect adjacent structures from the brain and enhance the region of interest. Automatic segmentation was performed through detection by coordinates and arithmetic mean of the area. Morphological operators were used to eliminate undesirable elements and reconstruct the shape and texture of the tumor. The results were compared with manual segmentations by two radiologists to determine the efficacy of the algorithms implemented. RESULTS: The correlated correspondence between the segmentation obtained and the gold standard was 89.23%. CONCLUSION: It is possible to locate and define the tumor region automatically with no the need for user interaction, based on two innovative methods to detect brain extreme sites and exclude non-tumor tissues on magnetic resonance images.


Asunto(s)
Algoritmos , Neoplasias Encefálicas/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Encéfalo/diagnóstico por imagen , Diagnóstico por Computador/métodos , Humanos , Estándares de Referencia , Reproducibilidad de los Resultados
20.
Ann Thorac Surg ; 109(5): 1566-1573, 2020 05.
Artículo en Inglés | MEDLINE | ID: mdl-32032573

RESUMEN

BACKGROUND: Thoracoscopic resection of small pulmonary nodules can be challenging, which highlights the importance of preoperative localization. We report our experience with electromagnetic navigation-guided localization. METHODS: The clinical, radiographic, surgical, and pathologic data of patients who underwent electromagnetic navigation-guided preoperative localization for pulmonary tumors smaller than 2 cm were reviewed. Successful localization was defined as successful identification of target lesions during the thoracoscopic procedure without palpation. RESULT: Included were 30 patients with 35 nodules. There were 31 transthoracic and 5 transbronchial approaches performed. One patient received both approaches for the same tumor, and 3 received both approaches for localization of multiple targets. The median nodule size was 1.0 cm (interquartile range [IQR], 0.8-1.2 cm), and the median distance from the pleural surface was 1.1 cm (IQR, 0.6-2.0 cm). The most commonly used marker for localization was dye (n = 18), followed by microcoils (n =15). In nodules located with microcoils, the median distance between the microcoil and nodule was 1 mm (IQR, 0-3 mm). There were no complications related to the localization procedure. Successful localization was achieved in 27 of 30 patients (90.0%) and in 32 of 35 nodules (91.4%). The pathologic diagnosis was primary pulmonary malignancy in 29 nodules and secondary pulmonary malignancy in 6. CONCLUSIONS: Our experience with electromagnetic navigation-guided transbronchial and transthoracic preoperative localization of small, malignant pulmonary tumors shows this technique is feasible and appears to be a viable option for preoperative localization of pulmonary nodules that may be difficult to locate thoracoscopically.


Asunto(s)
Broncoscopía/métodos , Diagnóstico por Computador/métodos , Neoplasias Pulmonares/diagnóstico , Nódulos Pulmonares Múltiples/diagnóstico , Cirugía Torácica Asistida por Video/métodos , Anciano , Fenómenos Electromagnéticos , Femenino , Estudios de Seguimiento , Humanos , Neoplasias Pulmonares/cirugía , Masculino , Persona de Mediana Edad , Nódulos Pulmonares Múltiples/cirugía , Periodo Preoperatorio , Reproducibilidad de los Resultados , Estudios Retrospectivos , Tomografía Computarizada por Rayos X
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA