Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 44.822
Filtrar
1.
Medicine (Baltimore) ; 99(23): e20634, 2020 Jun 05.
Artigo em Inglês | MEDLINE | ID: mdl-32502044

RESUMO

To evaluate the diagnostic efficiency of computer-aided diagnosis (CAD) system and 111 radiologists with different experience in identifying benign and malignant thyroid nodules, and to summarize the ultrasound features that may affect the diagnostic of CAD and radiologists.Fifty thyroid nodules and 111 radiologists were enrolled in this study. All the 50 nodules were diagnosed by the 111 radiologists and the CAD system simultaneously. The diagnostic performance of the CAD system, senior and junior radiologists with the maximum accuracy were calculated and compared. Interobserver agreement for different ultrasound characteristics between the CAD and senior radiologist were analyzed.CAD system showed a higher specificity than junior radiologist (87.5% vs 70.4%, P = .03), and a lower sensitivity than the senior radiologist and junior radiologist but the statistics were not significant (76.9% vs 86.9%, P > .5; 76.9% vs 82.6%, P > .5). The CAD system and senior radiologist got larger AUC than junior radiologist but the differences were not statistically significant (0.82 vs 0.76, respectively; P = .5). The interobserver agreement for the US characteristics between the CAD system and senior radiologist were: substantial agreement for hypoechoic and taller than wide (kappa value = 0.66, 0.78), and moderate agreement for irregular margin and micro-calcifications (kappa value = 0.52, 0.42).The CAD system achieved equal diagnostic accuracy to the senior radiologists and higher accuracy than the junior radiologists. The interobserver agreements in the US features between the CAD system and senior radiologist were substantial agreement for hypoechoic and taller than wide; moderate agreement for irregular margin and micro-calcifications. The location of a thyroid nodule and the feature of macrocalcification with wide acoustic shadow may influence the analysis of the CAD system.


Assuntos
Interpretação de Imagem Assistida por Computador/normas , Radiologia/normas , Nódulo da Glândula Tireoide/diagnóstico por imagem , Humanos , Sensibilidade e Especificidade , Neoplasias da Glândula Tireoide , Nódulo da Glândula Tireoide/patologia , Ultrassonografia
2.
Medicine (Baltimore) ; 99(22): e20503, 2020 May 29.
Artigo em Inglês | MEDLINE | ID: mdl-32481470

RESUMO

To investigate the feasibility of 3D arterial spin labeling (ASL) as an alternative to dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) for the qualitative and quantitative evaluation of nasopharyngeal carcinoma (NPC) perfusion.Fifty-two newly diagnosed NPC patients underwent 3D ASL and DCE-MRI scans on a 3.0-T MRI system. The visual qualitative evaluation of the NPC perfusion level was scored from 0 to 3 (0 = no contrast to normal peripheral soft tissue, 3 = pronounced contrast to normal peripheral soft tissue). The visual evaluation of the NPC outline was scored from 0 to 2 (0 = very vague outline, 2 = clear outline). Comparisons of the ASL-derived blood flow (BF) with the DCE-MRI-derived positive enhancement integral, maximum slope of increase, maximum slope of decrease, and time to peak (TTP) were conducted between NPC and non-NPC areas with independent samples t-tests. The diagnostic performance of these parameters was assessed by receiver operating characteristic curve analysis. The correlations between ASL BF and DCE parameters were assessed by Spearman correlation analysis.There was no difference in the visual scores of the NPC perfusion level between the 2 perfusion methods (P= .963). ASL had a lower visual score for describing the outline of NPC than DCE-MRI (P < .001). The ASL and DCE parameters of the NPC areas were significantly different from those of the non-NPC areas (P < .001). The ASL BF showed the largest area under the receiver operating characteristic curve (AUC) of 0.936 for identifying NPC. When all NPC and non-NPC areas were taken into account, significant correlations were observed between the ASL BF and the DCE parameters positive enhancement integral (r = 0.503, P < .001), maximum slope of increase (r = 0.616, P < .001), maximum slope of decrease (r = 0.380, P < .001), and TTP (r = -0.601, P < .001).3D ASL could reveal the hyperperfusion of NPC in a qualitative and quantitative manner without using contrast agent. Additionally, the ASL BF correlated significantly with the semiquantitative DCE-MRI parameters.


Assuntos
Angiografia por Ressonância Magnética/métodos , Imagem por Ressonância Magnética/métodos , Carcinoma Nasofaríngeo/diagnóstico por imagem , Neoplasias Nasofaríngeas/diagnóstico por imagem , Adolescente , Adulto , Idoso , Meios de Contraste , Estudos de Viabilidade , Feminino , Gadolínio DTPA , Humanos , Interpretação de Imagem Assistida por Computador , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos , Marcadores de Spin
3.
J Comput Assist Tomogr ; 44(4): 485-489, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32558766

RESUMO

PURPOSE: To evaluate tamoxifen-related endometrial changes in premenopausal female patients with diffusion-weighted magnetic resonance imaging (DWI). METHODS: This prospective study was performed on 71 premenopausal female patients (mean age, 41 years) who were receiving tamoxifen therapy. All patients underwent magnetic resonance imaging with DWI of the pelvis and hysteroscopic-guided endometrial biopsy. The apparent diffusion coefficient (ADC) values of the endometrial plate were calculated and correlated with pathological results. RESULTS: The mean ADCs of tamoxifen-related benign endometrial lesions (1.35 ± 0.19 and 1.32 ± 0.13 × 10 mm/s) were significantly higher (P = 0.001) than those of normal endometrial plate (0.95 ± 0.11 and 0.93 ± 0.11 × 10 mm/s) by both reviewers, respectively. The cutoff ADC values used to differentiate tamoxifen-related benign endometrial lesions from normal endometrium were 1.07 and 1.02 × 10 mm/s with areas under the curve of 0.94 and 0.93 and accuracy of 94.4 and 95.8 by both reviewers, respectively. The mean ADC values of endometrial polyp (EP) (1.44 ± 0.19 and 1.42 ± 0.22 × 10 mm/s) were significantly higher (P = 0.001) than those of endometrial hyperplasia (EH) (1.25 ± 0.19 and 1.23 ± 0.19 × 10 mm/s) by both reviewers, respectively. The cutoff ADC values used to differentiate EP from EH were 1.38 × 10 and 1.36 × 10 mm/s with areas under the curve of 0.81 and 0.77 and accuracy of 80% and 70% by both reviewers, respectively. There was an insignificant difference in ADC value between typical and atypical EH. The ADC values of endometrial cancer (0.80 and 0.78 × 10 mm/s) were lower than those of tamoxifen-related benign endometrial lesions. The final diagnosis was normal endometrium (n = 36), benign endometrial lesions either EH (n = 17), or EP (n = 16), and endometrial cancer in only 2 patients. CONCLUSIONS: We concluded that DWI helps in detection and characterization of different tamoxifen-related endometrial changes in the premenopausal female patients.


Assuntos
Neoplasias da Mama/tratamento farmacológico , Hiperplasia Endometrial/diagnóstico por imagem , Neoplasias do Endométrio/diagnóstico por imagem , Endométrio/efeitos dos fármacos , Tamoxifeno/efeitos adversos , Adulto , Imagem de Difusão por Ressonância Magnética , Hiperplasia Endometrial/induzido quimicamente , Neoplasias do Endométrio/induzido quimicamente , Endométrio/diagnóstico por imagem , Feminino , Humanos , Interpretação de Imagem Assistida por Computador , Pessoa de Meia-Idade , Variações Dependentes do Observador , Pré-Menopausa , Estudos Prospectivos , Tamoxifeno/uso terapêutico
4.
Surg Clin North Am ; 100(3): 499-506, 2020 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-32402296

RESUMO

The past decade has brought about dramatic changes in the diagnosis and management of cancer. Advancements in imaging and minimally invasive interventional techniques combine to rapidly diagnose, stage, and in certain cases, treat various forms of cancer. Physicians treating patients with cancer are confronted with many challenges beginning with the initial diagnosis. Imaging plays an integral role in every step of caring for the patient with cancer. Advances in imaging allow the earlier detection and staging of the disease and aid in decision making and treatment planning.


Assuntos
Diagnóstico por Imagem/métodos , Neoplasias/diagnóstico por imagem , Neoplasias/terapia , Radiologia Intervencionista , Meios de Contraste , Fluordesoxiglucose F18 , Humanos , Aumento da Imagem/métodos , Interpretação de Imagem Assistida por Computador/métodos , Biópsia Guiada por Imagem/métodos , Imagem por Ressonância Magnética/métodos , Estadiamento de Neoplasias , Neoplasias/patologia , Tomografia por Emissão de Pósitrons/métodos , Tomografia Computadorizada por Raios X/métodos , Resultado do Tratamento , Ultrassonografia/métodos
5.
Surg Clin North Am ; 100(3): 669-680, 2020 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-32402308

RESUMO

Although the vast majority of soft tissue extremity masses are benign, approximately 13,000 people in the United States were diagnosed with soft tissue sarcoma in 2019. This article focuses on the optimal workup of soft tissue masses including the indications for ultrasound and MRI, as well as use of preoperative core needle biopsy. Current AJCC staging, surgical principles of soft tissue sarcoma management, and data regarding indications for radiation therapy and chemotherapy are reviewed. As up to 50% of patients with soft tissue sarcoma will develop recurrent disease, surgical management of locally recurrent and distant metastatic disease is discussed.


Assuntos
Extremidades/cirurgia , Neoplasias de Tecidos Moles/cirurgia , Biópsia por Agulha Fina , Quimiorradioterapia , Terapia Combinada , Extremidades/patologia , Humanos , Interpretação de Imagem Assistida por Computador , Lipoma/patologia , Lipoma/cirurgia , Imagem por Ressonância Magnética , Margens de Excisão , Estadiamento de Neoplasias , Prognóstico , Radioterapia Adjuvante , Sarcoma/patologia , Sarcoma/cirurgia , Neoplasias de Tecidos Moles/patologia
7.
PLoS One ; 15(5): e0232127, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32365142

RESUMO

In this study, we proposed a novel convolutional neural network (CNN) architecture for classification of benign and malignant breast cancer (BC) in histological images. To improve the delivery and use of feature information, we chose the DenseNet as the basic building block and interleaved it with the squeeze-and-excitation (SENet) module. We conducted extensive experiments with the proposed framework by using the public domain BreakHis dataset and demonstrated that the proposed framework can produce significantly improved accuracy in BC classification, compared with the state-of-the-art CNN methods reported in the literature.


Assuntos
Neoplasias da Mama/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Algoritmos , Neoplasias da Mama/classificação , Feminino , Humanos , Redes Neurais de Computação
8.
PLoS One ; 15(5): e0232353, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32369500

RESUMO

IMPORTANCE: Neovascular age-related macular degeneration (nAMD) is a leading cause of blindness with several intravitreal anti-vascular endothelial growth factor (anti-VEGF) agents available for its management such as aflibercept, bevacizumab, and ranibizumab. However, direct comparisons between these three agents among the same patient population are limited. OBJECTIVE: To assess the rate and growth of complete retinal pigment epithelium and outer retinal atrophy (cRORA) in eyes with nAMD treated with aflibercept, bevacizumab, and/or ranibizumab. METHOD: Retrospective cohort study of patients with treatment-naïve neovascular AMD seen at an academic hospital between October 2006 and February 2019. Study eyes were treated with intravitreal injections of aflibercept, bevacizumab, and/or ranibizumab and followed for two years. MAIN OUTCOMES AND MEASURES: cRORA prevalence, location, size, and growth rate. Eyes were imaged with Cirrus spectral domain optical coherence tomography (SD-OCT). Presence and size of cRORA were calculated using the FDA-approved Advanced RPE Analysis software. Linear regression models were used to correlate cRORA progression with baseline demographic and ocular characteristics, anti-VEGF drug, and number of injections. Unpaired t-tests, ANOVA, and linear regression models were computed with SAS 9.4. RESULTS: 197 eyes from 158 patients (mean age 78.9, 62.9% women) received an average of 13 anti-VEGF injections over 24 months. 22% developed new cRORA. Mean cRORA area increased from 1.71 mm2 to 2.93 mm2. At 24 months, eyes with 11+ injections had significantly less cRORA area (11+ injections, 4.02 mm2; ≤ 10 injections, 2.46 mm2; p = 0.01) and growth rate (11+ injections, 0.41 mm2/year; ≤ 10 injections, 1.05 mm2/year; p = 0.02). Choice of anti-VEGF drug yielded no significant difference in cRORA progression. CONCLUSIONS AND RELEVANCE: Treating nAMD with aflibercept, bevacizumab or ranibizumab demonstrated comparable cRORA development at 24 months. Number of injections inversely correlated with cRORA area and growth. These results warrant further investigation in the pathophysiology of cRORA in anti-VEGF treated eyes.


Assuntos
Inibidores da Angiogênese/uso terapêutico , Degeneração Retiniana/tratamento farmacológico , Degeneração Retiniana/patologia , Epitélio Pigmentado da Retina/efeitos dos fármacos , Epitélio Pigmentado da Retina/patologia , Fator A de Crescimento do Endotélio Vascular/antagonistas & inibidores , Idoso , Idoso de 80 Anos ou mais , Atrofia , Bevacizumab/uso terapêutico , Feminino , Seguimentos , Humanos , Interpretação de Imagem Assistida por Computador , Injeções Intravítreas , Masculino , Ranibizumab/uso terapêutico , Receptores de Fatores de Crescimento do Endotélio Vascular/uso terapêutico , Proteínas Recombinantes de Fusão/uso terapêutico , Degeneração Retiniana/diagnóstico por imagem , Epitélio Pigmentado da Retina/diagnóstico por imagem , Estudos Retrospectivos , Tomografia de Coerência Óptica , Resultado do Tratamento
9.
Cancer Imaging ; 20(1): 33, 2020 May 01.
Artigo em Inglês | MEDLINE | ID: mdl-32357923

RESUMO

During the last decade, there is an increasing usage of quantitative methods in Radiology in an effort to reduce the diagnostic variability associated with a subjective manner of radiological interpretation. Combined approaches where visual assessment made by the radiologist is augmented by quantitative imaging biomarkers are gaining attention. Advances in machine learning resulted in the rise of radiomics that is a new methodology referring to the extraction of quantitative information from medical images. Radiomics are based on the development of computational models, referred to as "Radiomic Signatures", trying to address either unmet clinical needs, mostly in the field of oncologic imaging, or to compare radiomics performance with that of radiologists. However, to explore this new technology, initial publications did not consider best practices in the field of machine learning resulting in publications with questionable clinical value. In this paper, our effort was concentrated on how to avoid methodological mistakes and consider critical issues in the workflow of the development of clinically meaningful radiomic signatures.


Assuntos
Interpretação de Imagem Assistida por Computador/métodos , Neoplasias/diagnóstico por imagem , Humanos , Processamento de Imagem Assistida por Computador/métodos , Aprendizado de Máquina , Guias de Prática Clínica como Assunto
10.
Eur J Clin Microbiol Infect Dis ; 39(7): 1379-1389, 2020 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-32337662

RESUMO

Early classification of 2019 novel coronavirus disease (COVID-19) is essential for disease cure and control. Compared with reverse-transcription polymerase chain reaction (RT-PCR), chest computed tomography (CT) imaging may be a significantly more trustworthy, useful, and rapid technique to classify and evaluate COVID-19, specifically in the epidemic region. Almost all hospitals have CT imaging machines; therefore, the chest CT images can be utilized for early classification of COVID-19 patients. However, the chest CT-based COVID-19 classification involves a radiology expert and considerable time, which is valuable when COVID-19 infection is growing at rapid rate. Therefore, an automated analysis of chest CT images is desirable to save the medical professionals' precious time. In this paper, a convolutional neural networks (CNN) is used to classify the COVID-19-infected patients as infected (+ve) or not (-ve). Additionally, the initial parameters of CNN are tuned using multi-objective differential evolution (MODE). Extensive experiments are performed by considering the proposed and the competitive machine learning techniques on the chest CT images. Extensive analysis shows that the proposed model can classify the chest CT images at a good accuracy rate.


Assuntos
Infecções por Coronavirus/diagnóstico por imagem , Aprendizado Profundo , Interpretação de Imagem Assistida por Computador/métodos , Pulmão/diagnóstico por imagem , Pneumonia Viral/diagnóstico por imagem , Betacoronavirus , Técnicas de Laboratório Clínico , Infecções por Coronavirus/diagnóstico , Reações Falso-Negativas , Reações Falso-Positivas , Humanos , Redes Neurais de Computação , Pandemias , Pneumonia Viral/diagnóstico , Reação em Cadeia da Polimerase Via Transcriptase Reversa , Sensibilidade e Especificidade , Tomografia Computadorizada por Raios X
11.
AJR Am J Roentgenol ; 214(5): 995-1007, 2020 05.
Artigo em Inglês | MEDLINE | ID: mdl-32228326

RESUMO

OBJECTIVE. Functional MRI (fMRI) is clinically used for localization of eloquent cortex before surgical intervention, most commonly motor and language function in patients with tumors or epilepsy. In the pediatric population, special considerations for fMRI relate to limited examination tolerance, small head size, developing anatomy and physiology, and diverse potential abnormalities. In this article, we will highlight pearls and pitfalls of clinical pediatric fMRI including blood oxygenation level-dependent imaging principles, patient preparation, study acquisition, data postprocessing, and examination interpretation. CONCLUSION. Clinical fMRI is indicated for presurgical localization of eloquent cortex in patients with tumors, epilepsy, or other neurologic conditions and requires a solid understanding of technical considerations and data processing. In children, special approaches are needed for patient preparation as well as study design, acquisition, and interpretation. Radiologists should be cognizant of developmental neuroanatomy, causes of neuropathology, and capacity for neuroplasticity in the pediatric population.


Assuntos
Encefalopatias/diagnóstico por imagem , Imagem por Ressonância Magnética/métodos , Neuroimagem/métodos , Criança , Meios de Contraste , Humanos , Aumento da Imagem , Interpretação de Imagem Assistida por Computador
12.
PLoS One ; 15(4): e0227240, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32298265

RESUMO

This study examined and compared outcomes of deep learning (DL) in identifying swept-source optical coherence tomography (OCT) images without myopic macular lesions [i.e., no high myopia (nHM) vs. high myopia (HM)], and OCT images with myopic macular lesions [e.g., myopic choroidal neovascularization (mCNV) and retinoschisis (RS)]. A total of 910 SS-OCT images were included in the study as follows and analyzed by k-fold cross-validation (k = 5) using DL's renowned model, Visual Geometry Group-16: nHM, 146 images; HM, 531 images; mCNV, 122 images; and RS, 111 images (n = 910). The binary classification of OCT images with or without myopic macular lesions; the binary classification of HM images and images with myopic macular lesions (i.e., mCNV and RS images); and the ternary classification of HM, mCNV, and RS images were examined. Additionally, sensitivity, specificity, and the area under the curve (AUC) for the binary classifications as well as the correct answer rate for ternary classification were examined. The classification results of OCT images with or without myopic macular lesions were as follows: AUC, 0.970; sensitivity, 90.6%; specificity, 94.2%. The classification results of HM images and images with myopic macular lesions were as follows: AUC, 1.000; sensitivity, 100.0%; specificity, 100.0%. The correct answer rate in the ternary classification of HM images, mCNV images, and RS images were as follows: HM images, 96.5%; mCNV images, 77.9%; and RS, 67.6% with mean, 88.9%.Using noninvasive, easy-to-obtain swept-source OCT images, the DL model was able to classify OCT images without myopic macular lesions and OCT images with myopic macular lesions such as mCNV and RS with high accuracy. The study results suggest the possibility of conducting highly accurate screening of ocular diseases using artificial intelligence, which may improve the prevention of blindness and reduce workloads for ophthalmologists.


Assuntos
Neovascularização de Coroide/diagnóstico , Aprendizado Profundo , Interpretação de Imagem Assistida por Computador/métodos , Miopia/diagnóstico , Retinosquise/diagnóstico , Adulto , Idoso , Cegueira/prevenção & controle , Corioide/diagnóstico por imagem , Neovascularização de Coroide/complicações , Conjuntos de Dados como Assunto , Diagnóstico Diferencial , Feminino , Humanos , Macula Lutea/diagnóstico por imagem , Masculino , Programas de Rastreamento/métodos , Pessoa de Meia-Idade , Miopia/etiologia , Curva ROC , Retinosquise/complicações , Índice de Gravidade de Doença , Tomografia de Coerência Óptica
13.
AJR Am J Roentgenol ; 214(6): 1239-1247, 2020 06.
Artigo em Inglês | MEDLINE | ID: mdl-32228325

RESUMO

OBJECTIVE. The objective of our study was to subjectively and quantitatively assess shape features of peripheral zone (PZ) tumors at DWI compared with pathologic outcomes. MATERIALS AND METHODS. During the study period, 241 consecutive men with PZ dominant prostate tumors underwent 3-T MRI including DWI before undergoing radical prostatectomy. DW images of these patients were retrospectively assessed by two blinded radiologists. The reviewers assigned Prostate Imaging Reporting and Data System (PI-RADS) shape categories (round or oval, crescentic [i.e., conforming to PZ], linear or wedge-shaped) and segmented tumors for quantitative shape analysis. Discrepancies were resolved by consensus. Comparisons were performed with Gleason score (GS) and pathologic stage. RESULTS. Consensus review results were as follows: 63.9% (154/241) of tumors were round or oval; 22.8% (55/241), crescentic; and 13.3% (32/241), linear or wedge-shaped. Agreement for shape assessment was moderate (κ = 0.41). Round or oval tumors were higher grade (GS 6 = 1.3%, GS 7 = 78.0%, GS ≥ 8 = 20.7%) than crescentic tumors (GS 6 = 9.1%, GS 7 = 74.6%, GS ≥ 8 = 16.3%) and linear or wedge-shaped tumors (GS 6 = 6.3%, GS 7 = 78.1%, GS ≥ 8 = 15.6%) (p = 0.011). In addition, round or oval tumors had higher rates of extraprostatic extension (EPE) and seminal vesicle invasion (SVI) (EPE and SVI: 70.1% and 26.0%) than crescentic tumors (67.3% and 9.1%; p = 0.003) and linear or wedge-shaped tumors (40.6% and 9.4%; p = 0.008). Quantitatively, the shape features termed "circularity" and "roundness" were associated with EPE (p < 0.001 and p = 0.003), SVI (p < 0.001 and p = 0.029), and increasing GS (p = 0.009 and p = 0.021), but there was overlap between groups. CONCLUSION. In this study, approximately 10% of resected PZ tumors were linear or wedge-shaped on DWI. PZ tumors that were judged subjectively and evaluated quantitatively to be round or oval were associated with increased prostate cancer aggressiveness.


Assuntos
Imagem de Difusão por Ressonância Magnética , Interpretação de Imagem Assistida por Computador/métodos , Prostatectomia , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/cirurgia , Humanos , Masculino , Pessoa de Meia-Idade , Gradação de Tumores , Neoplasias da Próstata/patologia , Estudos Retrospectivos
14.
AJR Am J Roentgenol ; 214(6): 1259-1268, 2020 06.
Artigo em Inglês | MEDLINE | ID: mdl-32286874

RESUMO

OBJECTIVE. The purpose of this article is to review the natural history and management of bladder cancer, with insight into MRI applications for the assessment of muscle invasiveness of bladder cancer using the newly developed Vesical Imaging Reporting and Data System (VI-RADS) score. CONCLUSION. Multiparametric MRI and the VI-RADS score have been consistently validated across several different institutions as appropriate tools for local staging of bladder cancer and have been proven to contribute to the diagnostic workup and management of urinary bladder cancer.


Assuntos
Imageamento por Ressonância Magnética Multiparamétrica , Neoplasias da Bexiga Urinária/diagnóstico por imagem , Meios de Contraste , Humanos , Interpretação de Imagem Assistida por Computador , Invasividade Neoplásica , Estadiamento de Neoplasias , Neoplasias da Bexiga Urinária/patologia , Neoplasias da Bexiga Urinária/terapia
16.
J Comput Assist Tomogr ; 44(3): 405-412, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32345804

RESUMO

OBJECTIVE: The aim of the study was to quantitatively analyze the enhancement of breast lesions by contrast-enhanced spectral mammography to improve the differential diagnosis ability of contrast-enhanced spectral mammography. METHODS: A total of 283 patients with breast lesions admitted from August 2017 to May 2018 were retrospectively analyzed. Quantitative analysis of all enhancing lesions was performed to measure the gray values of the lesion region of interest (ROI), the area close to the lesion (ROI1), the area close to the chest wall (ROI2), and the chest wall (ROI3). Differences in gray values between different ROIs of benign and malignant lesions were compared. Taking the pathological results as the criterion standard, we used the receiver operating characteristic curve to evaluate the diagnostic efficacy of the ROI gray value and relative gray value (rROI) for the lesions. RESULTS: A total of 299 lesions were found in 283 patients, including 101 benign lesions and 198 malignant lesions. The ROI gray value, rROI1, rROI2, and rROI3 of malignant lesions were all significantly greater than those of benign lesions. The areas under the ROC curve of ROI, rROI1, rROI2, and rROI3 gray values of benign and malignant lesions were 0.795, 0.833, 0.812, and 0.741, respectively. The statistically significant difference in the area under the ROC curve was only found between rROI1 and ROI gray value and rROI1 had the greatest diagnostic value. CONCLUSIONS: The gray value of malignant breast lesions was higher than that of benign lesions. The quantitative analysis of the gray value will help in the differential diagnosis of benign and malignant breast lesions.


Assuntos
Neoplasias da Mama/diagnóstico por imagem , Mama/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Mamografia/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , Meios de Contraste , Diagnóstico Diferencial , Feminino , Humanos , Pessoa de Meia-Idade , Valor Preditivo dos Testes , Estudos Retrospectivos , Adulto Jovem
17.
J Comput Assist Tomogr ; 44(3): 341-345, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32345805

RESUMO

OBJECTIVE: The aim of this study was to evaluate the usefulness of texture analysis of T2-weighted short inversion time inversion recovery (T2-STIR) for detecting myocardial tissue alterations in hypertrophic cardiomyopathy (HCM). METHODS: Twenty patients with HCM and 11 controls were examined. Texture analysis was performed for the hypertrophied regions with and without and abnormal hyperintensity (AHI) and for the interventricular septum of the controls on T2-STIR. T2 mapping was performed to measure myocardial T2 values. RESULTS: A gray-level nonuniformity value of 64.7 was the best discriminator between patients and controls with an area under the curve of 0.93 on a receiver operating characteristic curve. T2 values did not differ between them. The gray-level nonuniformity was significantly smaller in AHI regions than in the hypertrophied regions without AHI in HCM patients. CONCLUSIONS: Texture analysis is useful for quantitatively detecting myocardial tissue altenations, including AHI, associated with HCM on T2-STIR.


Assuntos
Cardiomiopatia Hipertrófica/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Imagem Cinética por Ressonância Magnética/métodos , Adulto , Idoso , Feminino , Coração/diagnóstico por imagem , Humanos , Masculino , Pessoa de Meia-Idade , Curva ROC , Adulto Jovem
18.
J Comput Assist Tomogr ; 44(3): 426-435, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32345807

RESUMO

The authors investigated the usefulness of diffusion-tensor imaging (DTI) for evaluating tumor invasion depth, histologic grade, and lymph node metastasis in patients with cervical carcinoma (CC). Fifteen consecutive patients with histologically confirmed CC underwent 1.5-T magnetic resonance imaging and DTI. The CCs were clearly depicted as hypointense areas on all DTI maps. Fractional anisotropy, mean diffusivity, and axial diffusivity showed significantly inverse correlations with CC histologic grades and were significantly different between metastatic and nonmetastatic lymph nodes.


Assuntos
Imagem de Tensor de Difusão/métodos , Interpretação de Imagem Assistida por Computador/métodos , Neoplasias do Colo do Útero/diagnóstico por imagem , Neoplasias do Colo do Útero/patologia , Adulto , Idoso , Idoso de 80 Anos ou mais , Colo do Útero/diagnóstico por imagem , Colo do Útero/patologia , Feminino , Humanos , Linfonodos/diagnóstico por imagem , Linfonodos/patologia , Pessoa de Meia-Idade , Estadiamento de Neoplasias , Estudos Prospectivos
19.
J Comput Assist Tomogr ; 44(3): 413-418, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32345809

RESUMO

OBJECTIVE: The aim of this study was to evaluate the diagnostic ability of support vector machine (SVM) for early breast cancer (BC) using dedicated breast positron emission tomography (dbPET). METHODS: We evaluated 116 abnormal fluorodeoxyglucose (FDG) uptakes less than 2 cm on dbPET images in 105 women. Fluorodeoxyglucose uptake patterns and quantitative PET parameters were compared between BC and noncancer groups. Diagnostic accuracy of the SVM model including quantitative parameters was compared with that of visual assessment based on FDG-uptake pattern. RESULTS: Age, maximum standardized uptake value, peak standardized uptake value, total lesion glycolysis, metabolic tumor volume, and lesion-to-contralateral background ratio were significantly different between BC and noncancer groups. Area under the curve, sensitivity, specificity, and accuracy for FDG-uptake pattern of visual assessment were 0.77, 0.57, 0.77, and 0.71, respectively; those of an SVM model including age, maximum standardized uptake value, total lesion glycolysis, and lesion-to-contralateral background ratio were 0.89, 0.94, 0.77, and 0.85, respectively. CONCLUSIONS: Support vector machine showed high diagnostic performance for BC using dbPET.


Assuntos
Neoplasias da Mama/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Tomografia por Emissão de Pósitrons/métodos , Máquina de Vetores de Suporte , Adulto , Idoso , Idoso de 80 Anos ou mais , Mama/diagnóstico por imagem , Mama/metabolismo , Neoplasias da Mama/metabolismo , Feminino , Fluordesoxiglucose F18/farmacocinética , Humanos , Pessoa de Meia-Idade , Estudos Retrospectivos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA